{"id":"a0b579f3-b47e-4350-b55b-8ef82bfd9391","entityType":"agent","slug":"clawhub-athola-nm-pensive-unified-review","name":"unified-review","canonicalUrl":"https://www.xpersona.co/agent/clawhub-athola-nm-pensive-unified-review","canonicalPath":"/agent/clawhub-athola-nm-pensive-unified-review","generatedAt":"2026-10-10T14:47:57.613Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-10T12:13:00.818Z","emptyReason":null},"description":"Orchestrates multi-domain review (code, arch, tests, security) in a single pass Skill: unified-review Owner: athola Summary: Orchestrates multi-domain review (code, arch, tests, security) in a single pass Tags: latest:1.9.19 Version history: v1.9.19 | 2026-08-26T13:19:45.599Z | user Release v1.9.19 v1.9.17 | 2026-07-30T05:39:54.341Z | user Release v1.9.17 v1.9.16 | 2026-07-14T19:56:41.998Z | user Release v1.9.16 v1.9.14 | 2026-06-30T18:04:50.733Z | user Release v1.9.14 v1.9.13 | 2026-06-27T16:22","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.4K downloads reported by the source. Last updated 10/10/2026.","installCommand":"clawhub skill install s17emme0e2m3cpf7k2jvp3a84984b8z9:nm-pensive-unified-review","sourceUrl":"https://clawhub.ai/athola/nm-pensive-unified-review","homepage":"https://clawhub.ai/athola/skills/nm-pensive-unified-review","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/athola/nm-pensive-unified-review","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/athola/skills/nm-pensive-unified-review","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":63,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Orchestrates multi-domain review (code, arch, tests, security) in a single pass Skill: unified-review Owner: athola Summary: Orchestrates multi-domain review (c"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T12:13:00.818Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T12:13:00.818Z","emptyReason":null},"stars":null,"forks":null,"downloads":1440,"packageName":null,"latestVersion":"1.9.19","tractionLabel":"1.4K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T12:13:00.818Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T12:13:00.818Z","lastCrawledAt":"2026-10-10T12:13:00.818Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T12:13:00.818Z","lastVerifiedAt":null,"highlights":[{"version":"1.9.19","createdAt":"2026-08-26T13:19:45.599Z","changelog":"Release v1.9.19","fileCount":6,"zipByteSize":10249},{"version":"1.9.17","createdAt":"2026-07-30T05:39:54.341Z","changelog":"Release v1.9.17","fileCount":6,"zipByteSize":10067},{"version":"1.9.16","createdAt":"2026-07-14T19:56:41.998Z","changelog":"Release v1.9.16","fileCount":6,"zipByteSize":10059},{"version":"1.9.14","createdAt":"2026-06-30T18:04:50.733Z","changelog":"Release v1.9.14","fileCount":6,"zipByteSize":10110},{"version":"1.9.13","createdAt":"2026-06-27T16:22:45.285Z","changelog":"Release v1.9.13","fileCount":6,"zipByteSize":10318},{"version":"1.9.12","createdAt":"2026-06-19T03:18:03.335Z","changelog":"Release v1.9.12","fileCount":6,"zipByteSize":10048},{"version":"1.0.3","createdAt":"2026-06-18T15:17:35.046Z","changelog":"Release v1.9.12","fileCount":6,"zipByteSize":10106},{"version":"1.0.2","createdAt":"2026-05-09T02:19:36.781Z","changelog":"Release v1.9.5","fileCount":6,"zipByteSize":9746}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17emme0e2m3cpf7k2jvp3a84984b8z9:nm-pensive-unified-review","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-pensive-unified-review/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-pensive-unified-review/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-pensive-unified-review/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-pensive-unified-review/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-pensive-unified-review/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-pensive-unified-review/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T14:47:57.610Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-pensive-unified-review/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-pensive-unified-review/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-pensive-unified-review/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-athola-nm-pensive-unified-review/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-10T12:13:00.818Z","emptyReason":null},"readme":"Skill: unified-review\n\nOwner: athola\n\nSummary: Orchestrates multi-domain review (code, arch, tests, security) in a single pass\n\nTags: latest:1.9.19\n\nVersion history:\n\nv1.9.19 | 2026-08-26T13:19:45.599Z | user\n\nRelease v1.9.19\n\nv1.9.17 | 2026-07-30T05:39:54.341Z | user\n\nRelease v1.9.17\n\nv1.9.16 | 2026-07-14T19:56:41.998Z | user\n\nRelease v1.9.16\n\nv1.9.14 | 2026-06-30T18:04:50.733Z | user\n\nRelease v1.9.14\n\nv1.9.13 | 2026-06-27T16:22:45.285Z | user\n\nRelease v1.9.13\n\nv1.9.12 | 2026-06-19T03:18:03.335Z | user\n\nRelease v1.9.12\n\nv1.0.3 | 2026-06-18T15:17:35.046Z | user\n\nRelease v1.9.12\n\nv1.0.2 | 2026-05-09T02:19:36.781Z | user\n\nRelease v1.9.5\n\nv1.0.1 | 2026-05-06T14:20:55.014Z | user\n\nRelease v1.9.4\n\nv1.0.0 | 2026-04-15T17:01:33.005Z | auto\n\n- Initial release of unified-review skill for orchestrating multiple review types into a single, integrated workflow.\n- Supports intelligent selection and execution of domain-specific review skills based on codebase analysis (Rust, API, tests, architecture, math, etc.).\n- Provides integrated, cross-domain reporting with executive summary, domain-specific reports, and unified action plans.\n- Features modular, hub-and-spoke architecture for efficient skill loading and reduced token usage.\n- Includes support for multiple review modes: auto-detect, focused, and full review.\n- Ensures evidence logging, quality gates, and backlog capture for deferred findings.\n\nArchive index:\n\nArchive v1.9.19: 6 files, 10249 bytes\n\nFiles: modules/output-format-templates.md (3699b), modules/quality-checklist-patterns.md (3503b), modules/review-workflow-core.md (3203b), skill-card.md (2351b), SKILL.md (9230b), _meta.json (145b)\n\nFile v1.9.19:SKILL.md\n\n---\nname: unified-review\ndescription: Orchestrates multi-domain review (code, arch, tests, security) in a single pass\nversion: 1.9.8\ntriggers:\n  - review\n  - orchestration\n  - code-quality\n  - analysis\n  - multi-domain\n  - comprehensive pre-release review is needed\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/pensive\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.pensive:shared\", \"night-market.imbue:proof-of-work\", \"night-market.imbue:structured-output\"]}}}\nsource: claude-night-market\nsource_plugin: pensive\n---\n\n> **Night Market Skill** — ported from [claude-night-market/pensive](https://github.com/athola/claude-night-market/tree/master/plugins/pensive). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n## Table of Contents\n\n- [Quick Start](#quick-start)\n- [When to Use](#when-to-use)\n- [Review Skill Selection Matrix](#review-skill-selection-matrix)\n- [Workflow](#workflow)\n- [1. Analyze Repository Context](#1-analyze-repository-context)\n- [2. Select Review Skills](#2-select-review-skills)\n- [3. Execute Reviews](#3-execute-reviews)\n- [4. Integrate Findings](#4-integrate-findings)\n- [Review Modes](#review-modes)\n- [Auto-Detect (default)](#auto-detect-(default))\n- [Focused Mode](#focused-mode)\n- [Full Review Mode](#full-review-mode)\n- [Quality Gates](#quality-gates)\n- [Deliverables](#deliverables)\n- [Executive Summary](#executive-summary)\n- [Domain-Specific Reports](#domain-specific-reports)\n- [Integrated Action Plan](#integrated-action-plan)\n- [Modular Architecture](#modular-architecture)\n- [Exit Criteria](#exit-criteria)\n\n\n# Unified Review Orchestration\n\nIntelligently selects and executes appropriate review skills based on codebase analysis and context.\n\n## Quick Start\n\n```bash\n# Auto-detect and run appropriate reviews\n/full-review\n\n# Focus on specific areas\n/full-review api          # API surface review\n/full-review architecture # Architecture review\n/full-review bugs         # Bug hunting\n/full-review tests        # Test suite review\n/full-review all          # Run all applicable skills\n```\n**Verification:** Run `pytest -v` to verify tests pass.\n\n## When To Use\n\n- Starting a full code review\n- Reviewing changes across multiple domains\n- Need intelligent selection of review skills\n- Want integrated reporting from multiple review types\n- Before merging major feature branches\n\n## When NOT To Use\n\n- Specific review type known\n  - use bug-review\n- Test-review\n- Architecture-only focus - use\n  architecture-review\n- Specific review type known\n  - use bug-review\n\n## Review Skill Selection Matrix\n\n| Codebase Pattern | Review Skills | Triggers |\n|-----------------|---------------|----------|\n| Rust files (`*.rs`, `Cargo.toml`) | rust-review, bug-review, api-review | Rust project detected |\n| API changes (`openapi.yaml`, `routes/`) | api-review, architecture-review | Public API surfaces |\n| Test files (`test_*.py`, `*_test.go`) | test-review, bug-review | Test infrastructure |\n| Makefile/build system | makefile-review, architecture-review | Build complexity |\n| Mathematical algorithms | math-review, bug-review | Numerical computation |\n| Architecture docs/ADRs | architecture-review, api-review | System design |\n| General code quality | bug-review, test-review | Default review |\n| Post-implementation audit | imbue:justify | High add/delete ratio, test changes, new abstractions |\n\n## Workflow\n\n### 1. Analyze Repository Context\n- Detect primary languages from extensions and manifests\n- Analyze git status and diffs for change scope\n- Identify project structure (monorepo, microservices, library)\n- Detect build systems, testing frameworks, documentation\n\n### 2. Select Review Skills\n```python\n# Detection logic\nif has_rust_files():\n    schedule_skill(\"rust-review\")\nif has_api_changes():\n    schedule_skill(\"api-review\")\nif has_test_files():\n    schedule_skill(\"test-review\")\nif has_makefiles():\n    schedule_skill(\"makefile-review\")\nif has_math_code():\n    schedule_skill(\"math-review\")\nif has_architecture_changes():\n    schedule_skill(\"architecture-review\")\n# Default\nschedule_skill(\"bug-review\")\n```\n**Verification:** Run `pytest -v` to verify tests pass.\n\n### 3. Execute Reviews\n\nDispatch selected skills concurrently via the Agent tool.\nUse this mapping to resolve skill names to agent types:\n\n| Skill Name | Agent Type | Notes |\n|---|---|---|\n| bug-review | `pensive:code-reviewer` | Covers bugs, API, tests |\n| api-review | `pensive:code-reviewer` | Same agent, API focus |\n| test-review | `pensive:code-reviewer` | Same agent, test focus |\n| architecture-review | `pensive:architecture-reviewer` | ADR compliance |\n| rust-review | `pensive:rust-auditor` | Rust-specific |\n| code-refinement | `pensive:code-refiner` | Duplication, quality |\n| math-review | `general-purpose` | Prompt: invoke `Skill(pensive:math-review)` |\n| makefile-review | `general-purpose` | Prompt: invoke `Skill(pensive:makefile-review)` |\n| shell-review | `general-purpose` | Prompt: invoke `Skill(pensive:shell-review)` |\n\n**Sub-agent isolation (required):**\n\nDispatch ALL selected agents in a SINGLE parallel Agent tool\ncall. Do not read or process any agent's output until ALL agents\nhave returned their results. Reading the first result before the\nothers are in anchors synthesis toward that perspective — each\nsubsequent result gets evaluated against the first rather than\nindependently. Collect all results, then synthesize once.\n\n**Rules:**\n- Never use skill names as agent types (e.g., `pensive:math-review` is NOT an agent)\n- When `pensive:code-reviewer` covers multiple domains, dispatch once with combined scope\n- For skills without dedicated agents, use `general-purpose` and instruct it to invoke the Skill tool\n- Maintain consistent evidence logging across all agents\n- Track progress via TodoWrite\n\n### 4. Integrate Findings\n\n- Consolidate findings across domains\n- Identify cross-domain patterns\n- Prioritize by impact and effort\n- Generate unified action plan\n\n**Deferred capture for backlog findings:**\nFindings that are triaged to the backlog (out-of-scope for\nthe current review or deferred by the team) should be\npreserved so they are not lost between review cycles.\nFor each finding assigned to the backlog, run:\n\n```bash\npython3 scripts/deferred_capture.py \\\n  --title \"<finding title>\" \\\n  --source review \\\n  --context \"Review dimension: <dimension>. <finding description>\"\n```\n\nThe `<dimension>` value should match the review skill that\nsurfaced the finding (e.g. `bug-review`, `api-review`,\n`architecture-review`).\nThis runs automatically after the action plan is finalised,\nwithout prompting the user.\n\n## Review Modes\n\n### Auto-Detect (default)\nAutomatically selects skills based on codebase analysis.\n\n### Focused Mode\nRun specific review domains:\n- `/full-review api` → api-review only\n- `/full-review architecture` → architecture-review only\n- `/full-review bugs` → bug-review only\n- `/full-review tests` → test-review only\n\n### Full Review Mode\nRun all applicable review skills:\n- `/full-review all` → Execute all detected skills\n\n## Quality Gates\n\nEach review must:\n1. Establish proper context\n2. Execute all selected skills successfully\n3. Document findings with evidence\n4. Prioritize recommendations by impact\n5. Create action plan with owners\n\n## Deliverables\n\n### Executive Summary\n- Overall codebase health assessment\n- Critical issues requiring immediate attention\n- Review frequency recommendations\n\n### Domain-Specific Reports\n- API surface analysis and consistency\n- Architecture alignment with ADRs\n- Test coverage gaps and improvements\n- Bug analysis and security findings\n- Performance and maintainability recommendations\n\n### Integrated Action Plan\n- Prioritized remediation tasks\n- Cross-domain dependencies\n- Assigned owners and target dates\n- Follow-up review schedule\n\n## Modular Architecture\n\nAll review skills use a hub-and-spoke architecture with progressive loading:\n\n- **`pensive:shared`**: Common workflow, output templates, quality checklists\n- **Each skill has `modules/`**: Domain-specific details loaded on demand\n- **Cross-plugin deps**: `imbue:proof-of-work`, `imbue:diff-analysis/modules/risk-assessment-framework`\n\nThis reduces token usage by 50-70% for focused reviews while maintaining full capabilities.\n\n## Exit Criteria\n\n- All selected review skills executed\n- Findings consolidated and prioritized\n- Action plan created with ownership\n- Evidence logged per structured output format\n## Supporting Modules\n\n- [Review workflow core](modules/review-workflow-core.md) - standard 5-step workflow pattern for all pensive reviews\n- [Output format templates](modules/output-format-templates.md) - finding entry, severity, action item templates\n- [Quality checklist patterns](modules/quality-checklist-patterns.md) - pre-review, analysis, evidence, deliverable checklists\n\n## Troubleshooting\n\n### Common Issues\n\nIf the auto-detection fails to identify the correct review skills, explicitly specify the mode (e.g., `/full-review rust` instead of just `/full-review`). If integration fails, check that `TodoWrite` logs are accessible and that evidence files were correctly written by the individual skills.\n\nFile v1.9.19:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-pensive-unified-review\",\n  \"version\": \"1.9.19\",\n  \"publishedAt\": 1787750385599\n}\n\nFile v1.9.19:modules/output-format-templates.md\n\n---\nname: output-format-templates\ndescription: Standard output format templates for pensive review deliverables\nparent_skill: pensive:shared\ncategory: review-infrastructure\ntags: [templates, output, formatting, structure]\nreusable_by: [pensive:bug-review, pensive:api-review, pensive:architecture-review, pensive:test-review, pensive:rust-review, pensive:makefile-review, pensive:math-review, pensive:unified-review]\nestimated_tokens: 350\n---\n\n# Output Format Templates\n\nStandard templates for consistent review deliverables.\n\n## Top-Level Structure\n\n```markdown\n# [Review Type] Review: [Subject]\n\n## Executive Summary\n[High-level overview, key findings count, overall assessment]\n\n## Findings Summary\n[Count by severity: Critical, High, Medium, Low]\n\n## Detailed Findings\n[Organized by category or severity]\n\n## Action Items\n[Prioritized recommendations with owner and next step]\n\n## Evidence Appendix\n[Supporting code snippets, references, measurements]\n```\n\n## Finding Entry Template\n\n```markdown\n### [Category]: [Short Title]\n\n**Severity**: [Critical|High|Medium|Low]\n**Location**: [File path:line numbers or component name]\n**Category**: [Specific category from domain]\n\n**Issue**:\n[Clear description of what's wrong]\n\n**Evidence**:\n[Code snippet, measurement, or observation]\n\n**Why This Matters**:\n[The underlying principle or rule being violated.\nExplain the concept, not just the symptom.]\n\n**Proof**:\n[Link to authoritative best-practice documentation.\nPrefer: language docs, OWASP, PEPs, style guides,\nRFCs. Summarize what the link teaches.]\n\n**Teachable Moment**:\n[How this lesson generalizes beyond this specific\nfinding. When else would this principle apply?]\n\n**Recommendation**:\n[Specific steps to resolve, with concrete next action]\n\n**References**: [Evidence appendix section or external docs]\n```\n\n### Educational Depth by Severity\n\n| Severity | Why | Proof Link | Teachable Moment |\n|----------|-----|------------|------------------|\n| Critical | Required | Required | Required |\n| High | Required | Required | Required |\n| Medium | Required | If available | Optional |\n| Low | Brief | Optional | Optional |\n\n## Severity Definitions\n\n**Critical**: Security vulnerability, data loss risk, system failure potential\n**High**: Significant functionality issues, major violations, substantial technical debt\n**Medium**: Moderate violations, code quality issues, maintainability concerns\n**Low**: Minor style issues, optimization opportunities, documentation gaps\n\n## Action Items Template\n\n```markdown\n## Action Items\n\n### Immediate (Critical/High Severity)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n\n### Short-term (Medium Severity)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n\n### Long-term (Low Severity / Improvements)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n```\n\n## Evidence Appendix Template\n\n```markdown\n## Evidence Appendix\n\n### E1: [Short Reference Name]\n**Related to**: Finding [X]\n**File**: `/path/to/file.ext:lines`\n\n```[language]\n[code snippet or measurement]\n```\n\n**Context**: [Why this evidence matters]\n\n---\n\n### E2: [Next Reference]\n...\n```\n\n## Summary Statistics Template\n\n```markdown\n## Review Statistics\n\n- **Total Items Reviewed**: [count]\n- **Findings by Severity**:\n  - Critical: [count]\n  - High: [count]\n  - Medium: [count]\n  - Low: [count]\n- **Categories Analyzed**: [list]\n- **Recommendations**: [count]\n```\n\n## Usage Notes\n\n1. Adapt section headings to domain (e.g., \"Endpoints\" for API, \"Components\" for architecture)\n2. Always link findings to evidence\n3. Keep Executive Summary under 5 sentences\n4. validate every finding has a concrete next step\n5. Use consistent severity assessment across entire review\n\nFile v1.9.19:modules/quality-checklist-patterns.md\n\n---\nname: quality-checklist-patterns\ndescription: Reusable quality checklist patterns for review validation\nparent_skill: pensive:shared\ncategory: review-infrastructure\ntags: [quality, checklist, validation, completeness]\nreusable_by: [pensive:bug-review, pensive:api-review, pensive:architecture-review, pensive:test-review, pensive:rust-review, pensive:makefile-review, pensive:math-review, pensive:unified-review]\nestimated_tokens: 300\n---\n\n# Quality Checklist Patterns\n\nStandard quality assurance checklists for review deliverables.\n\n## Pre-Review Checklist\n\nExecute before starting analysis:\n\n- [ ] Scope clearly defined and documented\n- [ ] Review criteria identified (use domain-specific patterns)\n- [ ] Success criteria established\n- [ ] Evidence logging strategy prepared\n- [ ] Output template selected and customized\n\n## Analysis Quality Checklist\n\nExecute during deep analysis phase:\n\n- [ ] All scope items examined\n- [ ] Domain-specific criteria applied consistently\n- [ ] Severity assessed using standard definitions\n- [ ] Patterns and anti-patterns identified\n- [ ] Cross-references validated\n- [ ] Edge cases considered\n\n## Evidence Quality Checklist\n\nExecute during evidence capture:\n\n- [ ] Every finding has supporting evidence\n- [ ] File paths and line numbers included\n- [ ] Code snippets are minimal and focused\n- [ ] Context preserved for each evidence item\n- [ ] Evidence appendix organized and referenced\n- [ ] Reasoning chains documented\n\n## Deliverable Completeness Checklist\n\nExecute before finalizing output:\n\n- [ ] Executive summary present and concise\n- [ ] All findings documented with required fields:\n  - [ ] Severity assigned\n  - [ ] Location specified\n  - [ ] Category identified\n  - [ ] Issue described\n  - [ ] Evidence provided\n  - [ ] Impact explained\n  - [ ] Recommendation actionable\n- [ ] Action items prioritized by severity\n- [ ] Evidence appendix complete\n- [ ] Summary statistics included\n- [ ] Output follows template structure\n\n## Recommendation Quality Checklist\n\nExecute for each recommendation:\n\n- [ ] Specific and actionable\n- [ ] Addresses root cause, not just symptoms\n- [ ] Feasible within project constraints\n- [ ] Prioritized appropriately\n- [ ] Linked to finding\n- [ ] Includes rationale\n\n## Review Consistency Checklist\n\nExecute before final delivery:\n\n- [ ] Severity levels applied consistently\n- [ ] Terminology used consistently\n- [ ] Categories align with domain standards\n- [ ] Similar issues grouped appropriately\n- [ ] No contradictory recommendations\n- [ ] Style and tone professional throughout\n\n## Exit Criteria Validation\n\nFinal check before completion:\n\n- [ ] All TodoWrite items marked complete\n- [ ] Workflow steps executed in sequence\n- [ ] Quality checklists satisfied\n- [ ] Output validated against template\n- [ ] Evidence complete and linked\n- [ ] Deliverable ready for stakeholder review\n\n## Usage Pattern\n\nIntegrate into Step 5 (Deliverable Assembly) of review workflow:\n\n```python\n# Before marking final todo as complete\nprint(\"Validating deliverable quality...\")\n# Run through Deliverable Completeness Checklist\n# Run through Review Consistency Checklist\n# Run through Exit Criteria Validation\n# Only then mark todo complete\n```\n\n## Customization\n\nDomain-specific reviews may extend these checklists with:\n- Additional domain criteria (e.g., security-specific checks)\n- Tool-specific validation (e.g., linter results)\n- Compliance requirements (e.g., regulatory standards)\n\nExtend, don't replace, these baseline checklists.\n\nFile v1.9.19:modules/review-workflow-core.md\n\n---\nname: review-workflow-core\ndescription: Core workflow patterns for all pensive review skills\nparent_skill: pensive:shared\ncategory: review-infrastructure\ntags: [workflow, core, review, patterns]\nreusable_by: [pensive:bug-review, pensive:api-review, pensive:architecture-review, pensive:test-review, pensive:rust-review, pensive:makefile-review, pensive:math-review, pensive:unified-review]\nestimated_tokens: 400\n---\n\n# Review Workflow Core\n\nStandard 5-step workflow pattern for all pensive review skills.\n\n## Workflow Structure\n\n### Step 1: Context Establishment\n**TodoWrite Item**: \"Establishing review context\"\n\nActions:\n1. Identify review scope and boundaries\n2. Gather relevant files and documentation\n3. Establish success criteria\n4. Load domain-specific patterns (if applicable)\n\n**Output**: Context summary with scope definition\n\n### Step 2: Scope Inventory\n**TodoWrite Item**: \"Creating scope inventory\"\n\nActions:\n1. Catalog all items to review (files, components, endpoints, etc.)\n2. Categorize by type, complexity, or domain area\n3. Prioritize based on risk, complexity, or impact\n4. Create initial structure for findings\n\n**Output**: Structured inventory with categories\n\n### Step 3: Deep Analysis\n**TodoWrite Item**: \"Performing deep analysis\"\n\nActions:\n1. Apply domain-specific review criteria\n2. Identify patterns, anti-patterns, violations\n3. Assess severity (Critical, High, Medium, Low)\n4. Cross-reference with best practices\n5. Capture evidence for each finding\n\n**Output**: Detailed findings with evidence\n\n### Step 4: Evidence Capture\n**TodoWrite Item**: \"Capturing evidence\"\n\nIntegration with `imbue:proof-of-work`:\n1. Document code snippets with file paths and line numbers\n2. Record reasoning chains for conclusions\n3. Link findings to specific violations or patterns\n4. Preserve context for future reference\n\n**Output**: Evidence appendix linked to findings\n\n### Step 5: Deliverable Assembly\n**TodoWrite Item**: \"Assembling final deliverable\"\n\nActions:\n1. Structure findings by severity and category\n2. Format recommendations with actionable steps\n3. Create prioritized action items\n4. Validate completeness against exit criteria\n5. Generate final output using templates\n\n**Output**: Complete review deliverable\n\n## TodoWrite Integration\n\nCreate tasks at workflow start:\n\n```python\nTodoWrite({\n    \"todos\": [\n        {\"content\": \"Establish review context\", \"status\": \"pending\", \"activeForm\": \"Establishing review context\"},\n        {\"content\": \"Create scope inventory\", \"status\": \"pending\", \"activeForm\": \"Creating scope inventory\"},\n        {\"content\": \"Perform deep analysis\", \"status\": \"pending\", \"activeForm\": \"Performing deep analysis\"},\n        {\"content\": \"Capture evidence\", \"status\": \"pending\", \"activeForm\": \"Capturing evidence\"},\n        {\"content\": \"Assemble final deliverable\", \"status\": \"pending\", \"activeForm\": \"Assembling final deliverable\"}\n    ]\n})\n```\n\nMark each as `in_progress` when starting, `completed` when finished.\n\n## Exit Criteria\n\nBefore marking workflow complete:\n- [ ] All scope items analyzed\n- [ ] Evidence captured for each finding\n- [ ] Recommendations are actionable\n- [ ] Output follows format templates\n- [ ] Quality checklist satisfied\n\nFile v1.9.19:skill-card.md\n\n## Description:\n\nOrchestrates multi-domain review (code, arch, tests, security) in a single pass.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[athola](https://clawhub.ai/user/athola)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineering teams use this skill to coordinate broad pre-merge or pre-release reviews across code quality, architecture, tests, API surfaces, security findings, and implementation risk.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Automatic deferred backlog capture may persist review-derived text locally without an explicit approval step.\n\nMitigation: Disable deferred capture or require user confirmation before saving backlog findings.\n\nRisk: Broad triggers such as review, analysis, and orchestration can activate the skill in contexts where a narrower review command was intended.\n\nMitigation: Limit activation to a unique command such as `full-review` before installation.\n\nRisk: The deferred capture behavior invokes a local persistence command.\n\nMitigation: Trust and review the local capture script before use, and invoke it with a safe argument-array API rather than shell interpolation.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-pensive-unified-review)\n- [Project homepage from ClawHub metadata](https://github.com/athola/claude-night-market/tree/master/plugins/pensive)\n- [Review workflow core](modules/review-workflow-core.md)\n- [Output format templates](modules/output-format-templates.md)\n- [Quality checklist patterns](modules/quality-checklist-patterns.md)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown review reports with findings, evidence, action items, and inline shell commands.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May coordinate multiple review domains and produce an integrated action plan.]\n\n## Skill Version(s):\n\n1.9.19 (source: ClawHub release metadata; artifact frontmatter reports 1.9.8)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.9.17: 6 files, 10067 bytes\n\nFiles: modules/output-format-templates.md (3699b), modules/quality-checklist-patterns.md (3503b), modules/review-workflow-core.md (3203b), skill-card.md (2048b), SKILL.md (9230b), _meta.json (145b)\n\nFile v1.9.17:SKILL.md\n\n---\nname: unified-review\ndescription: Orchestrates multi-domain review (code, arch, tests, security) in a single pass\nversion: 1.9.8\ntriggers:\n  - review\n  - orchestration\n  - code-quality\n  - analysis\n  - multi-domain\n  - comprehensive pre-release review is needed\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/pensive\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.pensive:shared\", \"night-market.imbue:proof-of-work\", \"night-market.imbue:structured-output\"]}}}\nsource: claude-night-market\nsource_plugin: pensive\n---\n\n> **Night Market Skill** — ported from [claude-night-market/pensive](https://github.com/athola/claude-night-market/tree/master/plugins/pensive). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n## Table of Contents\n\n- [Quick Start](#quick-start)\n- [When to Use](#when-to-use)\n- [Review Skill Selection Matrix](#review-skill-selection-matrix)\n- [Workflow](#workflow)\n- [1. Analyze Repository Context](#1-analyze-repository-context)\n- [2. Select Review Skills](#2-select-review-skills)\n- [3. Execute Reviews](#3-execute-reviews)\n- [4. Integrate Findings](#4-integrate-findings)\n- [Review Modes](#review-modes)\n- [Auto-Detect (default)](#auto-detect-(default))\n- [Focused Mode](#focused-mode)\n- [Full Review Mode](#full-review-mode)\n- [Quality Gates](#quality-gates)\n- [Deliverables](#deliverables)\n- [Executive Summary](#executive-summary)\n- [Domain-Specific Reports](#domain-specific-reports)\n- [Integrated Action Plan](#integrated-action-plan)\n- [Modular Architecture](#modular-architecture)\n- [Exit Criteria](#exit-criteria)\n\n\n# Unified Review Orchestration\n\nIntelligently selects and executes appropriate review skills based on codebase analysis and context.\n\n## Quick Start\n\n```bash\n# Auto-detect and run appropriate reviews\n/full-review\n\n# Focus on specific areas\n/full-review api          # API surface review\n/full-review architecture # Architecture review\n/full-review bugs         # Bug hunting\n/full-review tests        # Test suite review\n/full-review all          # Run all applicable skills\n```\n**Verification:** Run `pytest -v` to verify tests pass.\n\n## When To Use\n\n- Starting a full code review\n- Reviewing changes across multiple domains\n- Need intelligent selection of review skills\n- Want integrated reporting from multiple review types\n- Before merging major feature branches\n\n## When NOT To Use\n\n- Specific review type known\n  - use bug-review\n- Test-review\n- Architecture-only focus - use\n  architecture-review\n- Specific review type known\n  - use bug-review\n\n## Review Skill Selection Matrix\n\n| Codebase Pattern | Review Skills | Triggers |\n|-----------------|---------------|----------|\n| Rust files (`*.rs`, `Cargo.toml`) | rust-review, bug-review, api-review | Rust project detected |\n| API changes (`openapi.yaml`, `routes/`) | api-review, architecture-review | Public API surfaces |\n| Test files (`test_*.py`, `*_test.go`) | test-review, bug-review | Test infrastructure |\n| Makefile/build system | makefile-review, architecture-review | Build complexity |\n| Mathematical algorithms | math-review, bug-review | Numerical computation |\n| Architecture docs/ADRs | architecture-review, api-review | System design |\n| General code quality | bug-review, test-review | Default review |\n| Post-implementation audit | imbue:justify | High add/delete ratio, test changes, new abstractions |\n\n## Workflow\n\n### 1. Analyze Repository Context\n- Detect primary languages from extensions and manifests\n- Analyze git status and diffs for change scope\n- Identify project structure (monorepo, microservices, library)\n- Detect build systems, testing frameworks, documentation\n\n### 2. Select Review Skills\n```python\n# Detection logic\nif has_rust_files():\n    schedule_skill(\"rust-review\")\nif has_api_changes():\n    schedule_skill(\"api-review\")\nif has_test_files():\n    schedule_skill(\"test-review\")\nif has_makefiles():\n    schedule_skill(\"makefile-review\")\nif has_math_code():\n    schedule_skill(\"math-review\")\nif has_architecture_changes():\n    schedule_skill(\"architecture-review\")\n# Default\nschedule_skill(\"bug-review\")\n```\n**Verification:** Run `pytest -v` to verify tests pass.\n\n### 3. Execute Reviews\n\nDispatch selected skills concurrently via the Agent tool.\nUse this mapping to resolve skill names to agent types:\n\n| Skill Name | Agent Type | Notes |\n|---|---|---|\n| bug-review | `pensive:code-reviewer` | Covers bugs, API, tests |\n| api-review | `pensive:code-reviewer` | Same agent, API focus |\n| test-review | `pensive:code-reviewer` | Same agent, test focus |\n| architecture-review | `pensive:architecture-reviewer` | ADR compliance |\n| rust-review | `pensive:rust-auditor` | Rust-specific |\n| code-refinement | `pensive:code-refiner` | Duplication, quality |\n| math-review | `general-purpose` | Prompt: invoke `Skill(pensive:math-review)` |\n| makefile-review | `general-purpose` | Prompt: invoke `Skill(pensive:makefile-review)` |\n| shell-review | `general-purpose` | Prompt: invoke `Skill(pensive:shell-review)` |\n\n**Sub-agent isolation (required):**\n\nDispatch ALL selected agents in a SINGLE parallel Agent tool\ncall. Do not read or process any agent's output until ALL agents\nhave returned their results. Reading the first result before the\nothers are in anchors synthesis toward that perspective — each\nsubsequent result gets evaluated against the first rather than\nindependently. Collect all results, then synthesize once.\n\n**Rules:**\n- Never use skill names as agent types (e.g., `pensive:math-review` is NOT an agent)\n- When `pensive:code-reviewer` covers multiple domains, dispatch once with combined scope\n- For skills without dedicated agents, use `general-purpose` and instruct it to invoke the Skill tool\n- Maintain consistent evidence logging across all agents\n- Track progress via TodoWrite\n\n### 4. Integrate Findings\n\n- Consolidate findings across domains\n- Identify cross-domain patterns\n- Prioritize by impact and effort\n- Generate unified action plan\n\n**Deferred capture for backlog findings:**\nFindings that are triaged to the backlog (out-of-scope for\nthe current review or deferred by the team) should be\npreserved so they are not lost between review cycles.\nFor each finding assigned to the backlog, run:\n\n```bash\npython3 scripts/deferred_capture.py \\\n  --title \"<finding title>\" \\\n  --source review \\\n  --context \"Review dimension: <dimension>. <finding description>\"\n```\n\nThe `<dimension>` value should match the review skill that\nsurfaced the finding (e.g. `bug-review`, `api-review`,\n`architecture-review`).\nThis runs automatically after the action plan is finalised,\nwithout prompting the user.\n\n## Review Modes\n\n### Auto-Detect (default)\nAutomatically selects skills based on codebase analysis.\n\n### Focused Mode\nRun specific review domains:\n- `/full-review api` → api-review only\n- `/full-review architecture` → architecture-review only\n- `/full-review bugs` → bug-review only\n- `/full-review tests` → test-review only\n\n### Full Review Mode\nRun all applicable review skills:\n- `/full-review all` → Execute all detected skills\n\n## Quality Gates\n\nEach review must:\n1. Establish proper context\n2. Execute all selected skills successfully\n3. Document findings with evidence\n4. Prioritize recommendations by impact\n5. Create action plan with owners\n\n## Deliverables\n\n### Executive Summary\n- Overall codebase health assessment\n- Critical issues requiring immediate attention\n- Review frequency recommendations\n\n### Domain-Specific Reports\n- API surface analysis and consistency\n- Architecture alignment with ADRs\n- Test coverage gaps and improvements\n- Bug analysis and security findings\n- Performance and maintainability recommendations\n\n### Integrated Action Plan\n- Prioritized remediation tasks\n- Cross-domain dependencies\n- Assigned owners and target dates\n- Follow-up review schedule\n\n## Modular Architecture\n\nAll review skills use a hub-and-spoke architecture with progressive loading:\n\n- **`pensive:shared`**: Common workflow, output templates, quality checklists\n- **Each skill has `modules/`**: Domain-specific details loaded on demand\n- **Cross-plugin deps**: `imbue:proof-of-work`, `imbue:diff-analysis/modules/risk-assessment-framework`\n\nThis reduces token usage by 50-70% for focused reviews while maintaining full capabilities.\n\n## Exit Criteria\n\n- All selected review skills executed\n- Findings consolidated and prioritized\n- Action plan created with ownership\n- Evidence logged per structured output format\n## Supporting Modules\n\n- [Review workflow core](modules/review-workflow-core.md) - standard 5-step workflow pattern for all pensive reviews\n- [Output format templates](modules/output-format-templates.md) - finding entry, severity, action item templates\n- [Quality checklist patterns](modules/quality-checklist-patterns.md) - pre-review, analysis, evidence, deliverable checklists\n\n## Troubleshooting\n\n### Common Issues\n\nIf the auto-detection fails to identify the correct review skills, explicitly specify the mode (e.g., `/full-review rust` instead of just `/full-review`). If integration fails, check that `TodoWrite` logs are accessible and that evidence files were correctly written by the individual skills.\n\nFile v1.9.17:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-pensive-unified-review\",\n  \"version\": \"1.9.17\",\n  \"publishedAt\": 1785389994341\n}\n\nFile v1.9.17:modules/output-format-templates.md\n\n---\nname: output-format-templates\ndescription: Standard output format templates for pensive review deliverables\nparent_skill: pensive:shared\ncategory: review-infrastructure\ntags: [templates, output, formatting, structure]\nreusable_by: [pensive:bug-review, pensive:api-review, pensive:architecture-review, pensive:test-review, pensive:rust-review, pensive:makefile-review, pensive:math-review, pensive:unified-review]\nestimated_tokens: 350\n---\n\n# Output Format Templates\n\nStandard templates for consistent review deliverables.\n\n## Top-Level Structure\n\n```markdown\n# [Review Type] Review: [Subject]\n\n## Executive Summary\n[High-level overview, key findings count, overall assessment]\n\n## Findings Summary\n[Count by severity: Critical, High, Medium, Low]\n\n## Detailed Findings\n[Organized by category or severity]\n\n## Action Items\n[Prioritized recommendations with owner and next step]\n\n## Evidence Appendix\n[Supporting code snippets, references, measurements]\n```\n\n## Finding Entry Template\n\n```markdown\n### [Category]: [Short Title]\n\n**Severity**: [Critical|High|Medium|Low]\n**Location**: [File path:line numbers or component name]\n**Category**: [Specific category from domain]\n\n**Issue**:\n[Clear description of what's wrong]\n\n**Evidence**:\n[Code snippet, measurement, or observation]\n\n**Why This Matters**:\n[The underlying principle or rule being violated.\nExplain the concept, not just the symptom.]\n\n**Proof**:\n[Link to authoritative best-practice documentation.\nPrefer: language docs, OWASP, PEPs, style guides,\nRFCs. Summarize what the link teaches.]\n\n**Teachable Moment**:\n[How this lesson generalizes beyond this specific\nfinding. When else would this principle apply?]\n\n**Recommendation**:\n[Specific steps to resolve, with concrete next action]\n\n**References**: [Evidence appendix section or external docs]\n```\n\n### Educational Depth by Severity\n\n| Severity | Why | Proof Link | Teachable Moment |\n|----------|-----|------------|------------------|\n| Critical | Required | Required | Required |\n| High | Required | Required | Required |\n| Medium | Required | If available | Optional |\n| Low | Brief | Optional | Optional |\n\n## Severity Definitions\n\n**Critical**: Security vulnerability, data loss risk, system failure potential\n**High**: Significant functionality issues, major violations, substantial technical debt\n**Medium**: Moderate violations, code quality issues, maintainability concerns\n**Low**: Minor style issues, optimization opportunities, documentation gaps\n\n## Action Items Template\n\n```markdown\n## Action Items\n\n### Immediate (Critical/High Severity)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n\n### Short-term (Medium Severity)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n\n### Long-term (Low Severity / Improvements)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n```\n\n## Evidence Appendix Template\n\n```markdown\n## Evidence Appendix\n\n### E1: [Short Reference Name]\n**Related to**: Finding [X]\n**File**: `/path/to/file.ext:lines`\n\n```[language]\n[code snippet or measurement]\n```\n\n**Context**: [Why this evidence matters]\n\n---\n\n### E2: [Next Reference]\n...\n```\n\n## Summary Statistics Template\n\n```markdown\n## Review Statistics\n\n- **Total Items Reviewed**: [count]\n- **Findings by Severity**:\n  - Critical: [count]\n  - High: [count]\n  - Medium: [count]\n  - Low: [count]\n- **Categories Analyzed**: [list]\n- **Recommendations**: [count]\n```\n\n## Usage Notes\n\n1. Adapt section headings to domain (e.g., \"Endpoints\" for API, \"Components\" for architecture)\n2. Always link findings to evidence\n3. Keep Executive Summary under 5 sentences\n4. validate every finding has a concrete next step\n5. Use consistent severity assessment across entire review\n\nFile v1.9.17:modules/quality-checklist-patterns.md\n\n---\nname: quality-checklist-patterns\ndescription: Reusable quality checklist patterns for review validation\nparent_skill: pensive:shared\ncategory: review-infrastructure\ntags: [quality, checklist, validation, completeness]\nreusable_by: [pensive:bug-review, pensive:api-review, pensive:architecture-review, pensive:test-review, pensive:rust-review, pensive:makefile-review, pensive:math-review, pensive:unified-review]\nestimated_tokens: 300\n---\n\n# Quality Checklist Patterns\n\nStandard quality assurance checklists for review deliverables.\n\n## Pre-Review Checklist\n\nExecute before starting analysis:\n\n- [ ] Scope clearly defined and documented\n- [ ] Review criteria identified (use domain-specific patterns)\n- [ ] Success criteria established\n- [ ] Evidence logging strategy prepared\n- [ ] Output template selected and customized\n\n## Analysis Quality Checklist\n\nExecute during deep analysis phase:\n\n- [ ] All scope items examined\n- [ ] Domain-specific criteria applied consistently\n- [ ] Severity assessed using standard definitions\n- [ ] Patterns and anti-patterns identified\n- [ ] Cross-references validated\n- [ ] Edge cases considered\n\n## Evidence Quality Checklist\n\nExecute during evidence capture:\n\n- [ ] Every finding has supporting evidence\n- [ ] File paths and line numbers included\n- [ ] Code snippets are minimal and focused\n- [ ] Context preserved for each evidence item\n- [ ] Evidence appendix organized and referenced\n- [ ] Reasoning chains documented\n\n## Deliverable Completeness Checklist\n\nExecute before finalizing output:\n\n- [ ] Executive summary present and concise\n- [ ] All findings documented with required fields:\n  - [ ] Severity assigned\n  - [ ] Location specified\n  - [ ] Category identified\n  - [ ] Issue described\n  - [ ] Evidence provided\n  - [ ] Impact explained\n  - [ ] Recommendation actionable\n- [ ] Action items prioritized by severity\n- [ ] Evidence appendix complete\n- [ ] Summary statistics included\n- [ ] Output follows template structure\n\n## Recommendation Quality Checklist\n\nExecute for each recommendation:\n\n- [ ] Specific and actionable\n- [ ] Addresses root cause, not just symptoms\n- [ ] Feasible within project constraints\n- [ ] Prioritized appropriately\n- [ ] Linked to finding\n- [ ] Includes rationale\n\n## Review Consistency Checklist\n\nExecute before final delivery:\n\n- [ ] Severity levels applied consistently\n- [ ] Terminology used consistently\n- [ ] Categories align with domain standards\n- [ ] Similar issues grouped appropriately\n- [ ] No contradictory recommendations\n- [ ] Style and tone professional throughout\n\n## Exit Criteria Validation\n\nFinal check before completion:\n\n- [ ] All TodoWrite items marked complete\n- [ ] Workflow steps executed in sequence\n- [ ] Quality checklists satisfied\n- [ ] Output validated against template\n- [ ] Evidence complete and linked\n- [ ] Deliverable ready for stakeholder review\n\n## Usage Pattern\n\nIntegrate into Step 5 (Deliverable Assembly) of review workflow:\n\n```python\n# Before marking final todo as complete\nprint(\"Validating deliverable quality...\")\n# Run through Deliverable Completeness Checklist\n# Run through Review Consistency Checklist\n# Run through Exit Criteria Validation\n# Only then mark todo complete\n```\n\n## Customization\n\nDomain-specific reviews may extend these checklists with:\n- Additional domain criteria (e.g., security-specific checks)\n- Tool-specific validation (e.g., linter results)\n- Compliance requirements (e.g., regulatory standards)\n\nExtend, don't replace, these baseline checklists.\n\nFile v1.9.17:modules/review-workflow-core.md\n\n---\nname: review-workflow-core\ndescription: Core workflow patterns for all pensive review skills\nparent_skill: pensive:shared\ncategory: review-infrastructure\ntags: [workflow, core, review, patterns]\nreusable_by: [pensive:bug-review, pensive:api-review, pensive:architecture-review, pensive:test-review, pensive:rust-review, pensive:makefile-review, pensive:math-review, pensive:unified-review]\nestimated_tokens: 400\n---\n\n# Review Workflow Core\n\nStandard 5-step workflow pattern for all pensive review skills.\n\n## Workflow Structure\n\n### Step 1: Context Establishment\n**TodoWrite Item**: \"Establishing review context\"\n\nActions:\n1. Identify review scope and boundaries\n2. Gather relevant files and documentation\n3. Establish success criteria\n4. Load domain-specific patterns (if applicable)\n\n**Output**: Context summary with scope definition\n\n### Step 2: Scope Inventory\n**TodoWrite Item**: \"Creating scope inventory\"\n\nActions:\n1. Catalog all items to review (files, components, endpoints, etc.)\n2. Categorize by type, complexity, or domain area\n3. Prioritize based on risk, complexity, or impact\n4. Create initial structure for findings\n\n**Output**: Structured inventory with categories\n\n### Step 3: Deep Analysis\n**TodoWrite Item**: \"Performing deep analysis\"\n\nActions:\n1. Apply domain-specific review criteria\n2. Identify patterns, anti-patterns, violations\n3. Assess severity (Critical, High, Medium, Low)\n4. Cross-reference with best practices\n5. Capture evidence for each finding\n\n**Output**: Detailed findings with evidence\n\n### Step 4: Evidence Capture\n**TodoWrite Item**: \"Capturing evidence\"\n\nIntegration with `imbue:proof-of-work`:\n1. Document code snippets with file paths and line numbers\n2. Record reasoning chains for conclusions\n3. Link findings to specific violations or patterns\n4. Preserve context for future reference\n\n**Output**: Evidence appendix linked to findings\n\n### Step 5: Deliverable Assembly\n**TodoWrite Item**: \"Assembling final deliverable\"\n\nActions:\n1. Structure findings by severity and category\n2. Format recommendations with actionable steps\n3. Create prioritized action items\n4. Validate completeness against exit criteria\n5. Generate final output using templates\n\n**Output**: Complete review deliverable\n\n## TodoWrite Integration\n\nCreate tasks at workflow start:\n\n```python\nTodoWrite({\n    \"todos\": [\n        {\"content\": \"Establish review context\", \"status\": \"pending\", \"activeForm\": \"Establishing review context\"},\n        {\"content\": \"Create scope inventory\", \"status\": \"pending\", \"activeForm\": \"Creating scope inventory\"},\n        {\"content\": \"Perform deep analysis\", \"status\": \"pending\", \"activeForm\": \"Performing deep analysis\"},\n        {\"content\": \"Capture evidence\", \"status\": \"pending\", \"activeForm\": \"Capturing evidence\"},\n        {\"content\": \"Assemble final deliverable\", \"status\": \"pending\", \"activeForm\": \"Assembling final deliverable\"}\n    ]\n})\n```\n\nMark each as `in_progress` when starting, `completed` when finished.\n\n## Exit Criteria\n\nBefore marking workflow complete:\n- [ ] All scope items analyzed\n- [ ] Evidence captured for each finding\n- [ ] Recommendations are actionable\n- [ ] Output follows format templates\n- [ ] Quality checklist satisfied\n\nFile v1.9.17:skill-card.md\n\n## Description: <br>\nOrchestrates multi-domain review (code, arch, tests, security) in a single pass. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[athola](https://clawhub.ai/user/athola) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and engineering teams use this skill to coordinate broad code, architecture, test, security, and release-readiness reviews and consolidate findings into a single action plan. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Broad triggers can cause the review orchestration flow to activate for general review requests where a narrower review was intended. <br>\nMitigation: Install only when broad review orchestration is desired, or remove generic triggers before deployment. <br>\nRisk: The skill can run a project-local deferred capture script automatically after action-plan synthesis. <br>\nMitigation: Change deferred capture to a confirm-before-run or dry-run step before using the skill in sensitive repositories. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-pensive-unified-review) <br>\n- [Clawdis homepage](https://github.com/athola/claude-night-market/tree/master/plugins/pensive) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, guidance] <br>\n**Output Format:** [Markdown review reports with action items, evidence appendices, and inline shell command examples] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Produces consolidated review findings and prioritized remediation guidance from selected review domains.] <br>\n\n## Skill Version(s): <br>\n1.9.17 (source: server release metadata) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.9.16: 6 files, 10059 bytes\n\nFiles: modules/output-format-templates.md (3699b), modules/quality-checklist-patterns.md (3503b), modules/review-workflow-core.md (3203b), skill-card.md (2015b), SKILL.md (9230b), _meta.json (145b)\n\nFile v1.9.16:SKILL.md\n\n---\nname: unified-review\ndescription: Orchestrates multi-domain review (code, arch, tests, security) in a single pass\nversion: 1.9.8\ntriggers:\n  - review\n  - orchestration\n  - code-quality\n  - analysis\n  - multi-domain\n  - comprehensive pre-release review is needed\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/pensive\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.pensive:shared\", \"night-market.imbue:proof-of-work\", \"night-market.imbue:structured-output\"]}}}\nsource: claude-night-market\nsource_plugin: pensive\n---\n\n> **Night Market Skill** — ported from [claude-night-market/pensive](https://github.com/athola/claude-night-market/tree/master/plugins/pensive). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n## Table of Contents\n\n- [Quick Start](#quick-start)\n- [When to Use](#when-to-use)\n- [Review Skill Selection Matrix](#review-skill-selection-matrix)\n- [Workflow](#workflow)\n- [1. Analyze Repository Context](#1-analyze-repository-context)\n- [2. Select Review Skills](#2-select-review-skills)\n- [3. Execute Reviews](#3-execute-reviews)\n- [4. Integrate Findings](#4-integrate-findings)\n- [Review Modes](#review-modes)\n- [Auto-Detect (default)](#auto-detect-(default))\n- [Focused Mode](#focused-mode)\n- [Full Review Mode](#full-review-mode)\n- [Quality Gates](#quality-gates)\n- [Deliverables](#deliverables)\n- [Executive Summary](#executive-summary)\n- [Domain-Specific Reports](#domain-specific-reports)\n- [Integrated Action Plan](#integrated-action-plan)\n- [Modular Architecture](#modular-architecture)\n- [Exit Criteria](#exit-criteria)\n\n\n# Unified Review Orchestration\n\nIntelligently selects and executes appropriate review skills based on codebase analysis and context.\n\n## Quick Start\n\n```bash\n# Auto-detect and run appropriate reviews\n/full-review\n\n# Focus on specific areas\n/full-review api          # API surface review\n/full-review architecture # Architecture review\n/full-review bugs         # Bug hunting\n/full-review tests        # Test suite review\n/full-review all          # Run all applicable skills\n```\n**Verification:** Run `pytest -v` to verify tests pass.\n\n## When To Use\n\n- Starting a full code review\n- Reviewing changes across multiple domains\n- Need intelligent selection of review skills\n- Want integrated reporting from multiple review types\n- Before merging major feature branches\n\n## When NOT To Use\n\n- Specific review type known\n  - use bug-review\n- Test-review\n- Architecture-only focus - use\n  architecture-review\n- Specific review type known\n  - use bug-review\n\n## Review Skill Selection Matrix\n\n| Codebase Pattern | Review Skills | Triggers |\n|-----------------|---------------|----------|\n| Rust files (`*.rs`, `Cargo.toml`) | rust-review, bug-review, api-review | Rust project detected |\n| API changes (`openapi.yaml`, `routes/`) | api-review, architecture-review | Public API surfaces |\n| Test files (`test_*.py`, `*_test.go`) | test-review, bug-review | Test infrastructure |\n| Makefile/build system | makefile-review, architecture-review | Build complexity |\n| Mathematical algorithms | math-review, bug-review | Numerical computation |\n| Architecture docs/ADRs | architecture-review, api-review | System design |\n| General code quality | bug-review, test-review | Default review |\n| Post-implementation audit | imbue:justify | High add/delete ratio, test changes, new abstractions |\n\n## Workflow\n\n### 1. Analyze Repository Context\n- Detect primary languages from extensions and manifests\n- Analyze git status and diffs for change scope\n- Identify project structure (monorepo, microservices, library)\n- Detect build systems, testing frameworks, documentation\n\n### 2. Select Review Skills\n```python\n# Detection logic\nif has_rust_files():\n    schedule_skill(\"rust-review\")\nif has_api_changes():\n    schedule_skill(\"api-review\")\nif has_test_files():\n    schedule_skill(\"test-review\")\nif has_makefiles():\n    schedule_skill(\"makefile-review\")\nif has_math_code():\n    schedule_skill(\"math-review\")\nif has_architecture_changes():\n    schedule_skill(\"architecture-review\")\n# Default\nschedule_skill(\"bug-review\")\n```\n**Verification:** Run `pytest -v` to verify tests pass.\n\n### 3. Execute Reviews\n\nDispatch selected skills concurrently via the Agent tool.\nUse this mapping to resolve skill names to agent types:\n\n| Skill Name | Agent Type | Notes |\n|---|---|---|\n| bug-review | `pensive:code-reviewer` | Covers bugs, API, tests |\n| api-review | `pensive:code-reviewer` | Same agent, API focus |\n| test-review | `pensive:code-reviewer` | Same agent, test focus |\n| architecture-review | `pensive:architecture-reviewer` | ADR compliance |\n| rust-review | `pensive:rust-auditor` | Rust-specific |\n| code-refinement | `pensive:code-refiner` | Duplication, quality |\n| math-review | `general-purpose` | Prompt: invoke `Skill(pensive:math-review)` |\n| makefile-review | `general-purpose` | Prompt: invoke `Skill(pensive:makefile-review)` |\n| shell-review | `general-purpose` | Prompt: invoke `Skill(pensive:shell-review)` |\n\n**Sub-agent isolation (required):**\n\nDispatch ALL selected agents in a SINGLE parallel Agent tool\ncall. Do not read or process any agent's output until ALL agents\nhave returned their results. Reading the first result before the\nothers are in anchors synthesis toward that perspective — each\nsubsequent result gets evaluated against the first rather than\nindependently. Collect all results, then synthesize once.\n\n**Rules:**\n- Never use skill names as agent types (e.g., `pensive:math-review` is NOT an agent)\n- When `pensive:code-reviewer` covers multiple domains, dispatch once with combined scope\n- For skills without dedicated agents, use `general-purpose` and instruct it to invoke the Skill tool\n- Maintain consistent evidence logging across all agents\n- Track progress via TodoWrite\n\n### 4. Integrate Findings\n\n- Consolidate findings across domains\n- Identify cross-domain patterns\n- Prioritize by impact and effort\n- Generate unified action plan\n\n**Deferred capture for backlog findings:**\nFindings that are triaged to the backlog (out-of-scope for\nthe current review or deferred by the team) should be\npreserved so they are not lost between review cycles.\nFor each finding assigned to the backlog, run:\n\n```bash\npython3 scripts/deferred_capture.py \\\n  --title \"<finding title>\" \\\n  --source review \\\n  --context \"Review dimension: <dimension>. <finding description>\"\n```\n\nThe `<dimension>` value should match the review skill that\nsurfaced the finding (e.g. `bug-review`, `api-review`,\n`architecture-review`).\nThis runs automatically after the action plan is finalised,\nwithout prompting the user.\n\n## Review Modes\n\n### Auto-Detect (default)\nAutomatically selects skills based on codebase analysis.\n\n### Focused Mode\nRun specific review domains:\n- `/full-review api` → api-review only\n- `/full-review architecture` → architecture-review only\n- `/full-review bugs` → bug-review only\n- `/full-review tests` → test-review only\n\n### Full Review Mode\nRun all applicable review skills:\n- `/full-review all` → Execute all detected skills\n\n## Quality Gates\n\nEach review must:\n1. Establish proper context\n2. Execute all selected skills successfully\n3. Document findings with evidence\n4. Prioritize recommendations by impact\n5. Create action plan with owners\n\n## Deliverables\n\n### Executive Summary\n- Overall codebase health assessment\n- Critical issues requiring immediate attention\n- Review frequency recommendations\n\n### Domain-Specific Reports\n- API surface analysis and consistency\n- Architecture alignment with ADRs\n- Test coverage gaps and improvements\n- Bug analysis and security findings\n- Performance and maintainability recommendations\n\n### Integrated Action Plan\n- Prioritized remediation tasks\n- Cross-domain dependencies\n- Assigned owners and target dates\n- Follow-up review schedule\n\n## Modular Architecture\n\nAll review skills use a hub-and-spoke architecture with progressive loading:\n\n- **`pensive:shared`**: Common workflow, output templates, quality checklists\n- **Each skill has `modules/`**: Domain-specific details loaded on demand\n- **Cross-plugin deps**: `imbue:proof-of-work`, `imbue:diff-analysis/modules/risk-assessment-framework`\n\nThis reduces token usage by 50-70% for focused reviews while maintaining full capabilities.\n\n## Exit Criteria\n\n- All selected review skills executed\n- Findings consolidated and prioritized\n- Action plan created with ownership\n- Evidence logged per structured output format\n## Supporting Modules\n\n- [Review workflow core](modules/review-workflow-core.md) - standard 5-step workflow pattern for all pensive reviews\n- [Output format templates](modules/output-format-templates.md) - finding entry, severity, action item templates\n- [Quality checklist patterns](modules/quality-checklist-patterns.md) - pre-review, analysis, evidence, deliverable checklists\n\n## Troubleshooting\n\n### Common Issues\n\nIf the auto-detection fails to identify the correct review skills, explicitly specify the mode (e.g., `/full-review rust` instead of just `/full-review`). If integration fails, check that `TodoWrite` logs are accessible and that evidence files were correctly written by the individual skills.\n\nFile v1.9.16:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-pensive-unified-review\",\n  \"version\": \"1.9.16\",\n  \"publishedAt\": 1784059001998\n}\n\nFile v1.9.16:modules/output-format-templates.md\n\n---\nname: output-format-templates\ndescription: Standard output format templates for pensive review deliverables\nparent_skill: pensive:shared\ncategory: review-infrastructure\ntags: [templates, output, formatting, structure]\nreusable_by: [pensive:bug-review, pensive:api-review, pensive:architecture-review, pensive:test-review, pensive:rust-review, pensive:makefile-review, pensive:math-review, pensive:unified-review]\nestimated_tokens: 350\n---\n\n# Output Format Templates\n\nStandard templates for consistent review deliverables.\n\n## Top-Level Structure\n\n```markdown\n# [Review Type] Review: [Subject]\n\n## Executive Summary\n[High-level overview, key findings count, overall assessment]\n\n## Findings Summary\n[Count by severity: Critical, High, Medium, Low]\n\n## Detailed Findings\n[Organized by category or severity]\n\n## Action Items\n[Prioritized recommendations with owner and next step]\n\n## Evidence Appendix\n[Supporting code snippets, references, measurements]\n```\n\n## Finding Entry Template\n\n```markdown\n### [Category]: [Short Title]\n\n**Severity**: [Critical|High|Medium|Low]\n**Location**: [File path:line numbers or component name]\n**Category**: [Specific category from domain]\n\n**Issue**:\n[Clear description of what's wrong]\n\n**Evidence**:\n[Code snippet, measurement, or observation]\n\n**Why This Matters**:\n[The underlying principle or rule being violated.\nExplain the concept, not just the symptom.]\n\n**Proof**:\n[Link to authoritative best-practice documentation.\nPrefer: language docs, OWASP, PEPs, style guides,\nRFCs. Summarize what the link teaches.]\n\n**Teachable Moment**:\n[How this lesson generalizes beyond this specific\nfinding. When else would this principle apply?]\n\n**Recommendation**:\n[Specific steps to resolve, with concrete next action]\n\n**References**: [Evidence appendix section or external docs]\n```\n\n### Educational Depth by Severity\n\n| Severity | Why | Proof Link | Teachable Moment |\n|----------|-----|------------|------------------|\n| Critical | Required | Required | Required |\n| High | Required | Required | Required |\n| Medium | Required | If available | Optional |\n| Low | Brief | Optional | Optional |\n\n## Severity Definitions\n\n**Critical**: Security vulnerability, data loss risk, system failure potential\n**High**: Significant functionality issues, major violations, substantial technical debt\n**Medium**: Moderate violations, code quality issues, maintainability concerns\n**Low**: Minor style issues, optimization opportunities, documentation gaps\n\n## Action Items Template\n\n```markdown\n## Action Items\n\n### Immediate (Critical/High Severity)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n\n### Short-term (Medium Severity)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n\n### Long-term (Low Severity / Improvements)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n```\n\n## Evidence Appendix Template\n\n```markdown\n## Evidence Appendix\n\n### E1: [Short Reference Name]\n**Related to**: Finding [X]\n**File**: `/path/to/file.ext:lines`\n\n```[language]\n[code snippet or measurement]\n```\n\n**Context**: [Why this evidence matters]\n\n---\n\n### E2: [Next Reference]\n...\n```\n\n## Summary Statistics Template\n\n```markdown\n## Review Statistics\n\n- **Total Items Reviewed**: [count]\n- **Findings by Severity**:\n  - Critical: [count]\n  - High: [count]\n  - Medium: [count]\n  - Low: [count]\n- **Categories Analyzed**: [list]\n- **Recommendations**: [count]\n```\n\n## Usage Notes\n\n1. Adapt section headings to domain (e.g., \"Endpoints\" for API, \"Components\" for architecture)\n2. Always link findings to evidence\n3. Keep Executive Summary under 5 sentences\n4. validate every finding has a concrete next step\n5. Use consistent severity assessment across entire review\n\nFile v1.9.16:modules/quality-checklist-patterns.md\n\n---\nname: quality-checklist-patterns\ndescription: Reusable quality checklist patterns for review validation\nparent_skill: pensive:shared\ncategory: review-infrastructure\ntags: [quality, checklist, validation, completeness]\nreusable_by: [pensive:bug-review, pensive:api-review, pensive:architecture-review, pensive:test-review, pensive:rust-review, pensive:makefile-review, pensive:math-review, pensive:unified-review]\nestimated_tokens: 300\n---\n\n# Quality Checklist Patterns\n\nStandard quality assurance checklists for review deliverables.\n\n## Pre-Review Checklist\n\nExecute before starting analysis:\n\n- [ ] Scope clearly defined and documented\n- [ ] Review criteria identified (use domain-specific patterns)\n- [ ] Success criteria established\n- [ ] Evidence logging strategy prepared\n- [ ] Output template selected and customized\n\n## Analysis Quality Checklist\n\nExecute during deep analysis phase:\n\n- [ ] All scope items examined\n- [ ] Domain-specific criteria applied consistently\n- [ ] Severity assessed using standard definitions\n- [ ] Patterns and anti-patterns identified\n- [ ] Cross-references validated\n- [ ] Edge cases considered\n\n## Evidence Quality Checklist\n\nExecute during evidence capture:\n\n- [ ] Every finding has supporting evidence\n- [ ] File paths and line numbers included\n- [ ] Code snippets are minimal and focused\n- [ ] Context preserved for each evidence item\n- [ ] Evidence appendix organized and referenced\n- [ ] Reasoning chains documented\n\n## Deliverable Completeness Checklist\n\nExecute before finalizing output:\n\n- [ ] Executive summary present and concise\n- [ ] All findings documented with required fields:\n  - [ ] Severity assigned\n  - [ ] Location specified\n  - [ ] Category identified\n  - [ ] Issue described\n  - [ ] Evidence provided\n  - [ ] Impact explained\n  - [ ] Recommendation actionable\n- [ ] Action items prioritized by severity\n- [ ] Evidence appendix complete\n- [ ] Summary statistics included\n- [ ] Output follows template structure\n\n## Recommendation Quality Checklist\n\nExecute for each recommendation:\n\n- [ ] Specific and actionable\n- [ ] Addresses root cause, not just symptoms\n- [ ] Feasible within project constraints\n- [ ] Prioritized appropriately\n- [ ] Linked to finding\n- [ ] Includes rationale\n\n## Review Consistency Checklist\n\nExecute before final delivery:\n\n- [ ] Severity levels applied consistently\n- [ ] Terminology used consistently\n- [ ] Categories align with domain standards\n- [ ] Similar issues grouped appropriately\n- [ ] No contradictory recommendations\n- [ ] Style and tone professional throughout\n\n## Exit Criteria Validation\n\nFinal check before completion:\n\n- [ ] All TodoWrite items marked complete\n- [ ] Workflow steps executed in sequence\n- [ ] Quality checklists satisfied\n- [ ] Output validated against template\n- [ ] Evidence complete and linked\n- [ ] Deliverable ready for stakeholder review\n\n## Usage Pattern\n\nIntegrate into Step 5 (Deliverable Assembly) of review workflow:\n\n```python\n# Before marking final todo as complete\nprint(\"Validating deliverable quality...\")\n# Run through Deliverable Completeness Checklist\n# Run through Review Consistency Checklist\n# Run through Exit Criteria Validation\n# Only then mark todo complete\n```\n\n## Customization\n\nDomain-specific reviews may extend these checklists with:\n- Additional domain criteria (e.g., security-specific checks)\n- Tool-specific validation (e.g., linter results)\n- Compliance requirements (e.g., regulatory standards)\n\nExtend, don't replace, these baseline checklists.\n\nFile v1.9.16:modules/review-workflow-core.md\n\n---\nname: review-workflow-core\ndescription: Core workflow patterns for all pensive review skills\nparent_skill: pensive:shared\ncategory: review-infrastructure\ntags: [workflow, core, review, patterns]\nreusable_by: [pensive:bug-review, pensive:api-review, pensive:architecture-review, pensive:test-review, pensive:rust-review, pensive:makefile-review, pensive:math-review, pensive:unified-review]\nestimated_tokens: 400\n---\n\n# Review Workflow Core\n\nStandard 5-step workflow pattern for all pensive review skills.\n\n## Workflow Structure\n\n### Step 1: Context Establishment\n**TodoWrite Item**: \"Establishing review context\"\n\nActions:\n1. Identify review scope and boundaries\n2. Gather relevant files and documentation\n3. Establish success criteria\n4. Load domain-specific patterns (if applicable)\n\n**Output**: Context summary with scope definition\n\n### Step 2: Scope Inventory\n**TodoWrite Item**: \"Creating scope inventory\"\n\nActions:\n1. Catalog all items to review (files, components, endpoints, etc.)\n2. Categorize by type, complexity, or domain area\n3. Prioritize based on risk, complexity, or impact\n4. Create initial structure for findings\n\n**Output**: Structured inventory with categories\n\n### Step 3: Deep Analysis\n**TodoWrite Item**: \"Performing deep analysis\"\n\nActions:\n1. Apply domain-specific review criteria\n2. Identify patterns, anti-patterns, violations\n3. Assess severity (Critical, High, Medium, Low)\n4. Cross-reference with best practices\n5. Capture evidence for each finding\n\n**Output**: Detailed findings with evidence\n\n### Step 4: Evidence Capture\n**TodoWrite Item**: \"Capturing evidence\"\n\nIntegration with `imbue:proof-of-work`:\n1. Document code snippets with file paths and line numbers\n2. Record reasoning chains for conclusions\n3. Link findings to specific violations or patterns\n4. Preserve context for future reference\n\n**Output**: Evidence appendix linked to findings\n\n### Step 5: Deliverable Assembly\n**TodoWrite Item**: \"Assembling final deliverable\"\n\nActions:\n1. Structure findings by severity and category\n2. Format recommendations with actionable steps\n3. Create prioritized action items\n4. Validate completeness against exit criteria\n5. Generate final output using templates\n\n**Output**: Complete review deliverable\n\n## TodoWrite Integration\n\nCreate tasks at workflow start:\n\n```python\nTodoWrite({\n    \"todos\": [\n        {\"content\": \"Establish review context\", \"status\": \"pending\", \"activeForm\": \"Establishing review context\"},\n        {\"content\": \"Create scope inventory\", \"status\": \"pending\", \"activeForm\": \"Creating scope inventory\"},\n        {\"content\": \"Perform deep analysis\", \"status\": \"pending\", \"activeForm\": \"Performing deep analysis\"},\n        {\"content\": \"Capture evidence\", \"status\": \"pending\", \"activeForm\": \"Capturing evidence\"},\n        {\"content\": \"Assemble final deliverable\", \"status\": \"pending\", \"activeForm\": \"Assembling final deliverable\"}\n    ]\n})\n```\n\nMark each as `in_progress` when starting, `completed` when finished.\n\n## Exit Criteria\n\nBefore marking workflow complete:\n- [ ] All scope items analyzed\n- [ ] Evidence captured for each finding\n- [ ] Recommendations are actionable\n- [ ] Output follows format templates\n- [ ] Quality checklist satisfied\n\nFile v1.9.16:skill-card.md\n\n## Description: <br>\nOrchestrates multi-domain review across code, architecture, tests, security, and related quality areas in a single pass. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[athola](https://clawhub.ai/user/athola) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and engineering teams use this skill to coordinate comprehensive repository reviews, select relevant review domains, synthesize findings, and produce an integrated action plan before merges or releases. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill may activate on broad review-related requests. <br>\nMitigation: Invoke it only for explicit comprehensive review work or use a narrower review skill when the desired review domain is already known. <br>\nRisk: The skill may run a local backlog-capture write command without asking. <br>\nMitigation: Require user confirmation before executing write commands and review generated backlog entries before keeping them. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-pensive-unified-review) <br>\n- [Clawdis homepage](https://github.com/athola/claude-night-market/tree/master/plugins/pensive) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, guidance] <br>\n**Output Format:** [Markdown review report with findings, evidence, recommendations, and action items] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May include prioritized severity levels, evidence appendices, and suggested local commands.] <br>\n\n## Skill Version(s): <br>\n1.9.16 (source: server release metadata) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.9.14: 6 files, 10110 bytes\n\nFiles: modules/output-format-templates.md (3699b), modules/quality-checklist-patterns.md (3503b), modules/review-workflow-core.md (3203b), skill-card.md (2180b), SKILL.md (9230b), _meta.json (145b)\n\nFile v1.9.14:SKILL.md\n\n---\nname: unified-review\ndescription: Orchestrates multi-domain review (code, arch, tests, security) in a single pass\nversion: 1.9.8\ntriggers:\n  - review\n  - orchestration\n  - code-quality\n  - analysis\n  - multi-domain\n  - comprehensive pre-release review is needed\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/pensive\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.pensive:shared\", \"night-market.imbue:proof-of-work\", \"night-market.imbue:structured-output\"]}}}\nsource: claude-night-market\nsource_plugin: pensive\n---\n\n> **Night Market Skill** — ported from [claude-night-market/pensive](https://github.com/athola/claude-night-market/tree/master/plugins/pensive). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n## Table of Contents\n\n- [Quick Start](#quick-start)\n- [When to Use](#when-to-use)\n- [Review Skill Selection Matrix](#review-skill-selection-matrix)\n- [Workflow](#workflow)\n- [1. Analyze Repository Context](#1-analyze-repository-context)\n- [2. Select Review Skills](#2-select-review-skills)\n- [3. Execute Reviews](#3-execute-reviews)\n- [4. Integrate Findings](#4-integrate-findings)\n- [Review Modes](#review-modes)\n- [Auto-Detect (default)](#auto-detect-(default))\n- [Focused Mode](#focused-mode)\n- [Full Review Mode](#full-review-mode)\n- [Quality Gates](#quality-gates)\n- [Deliverables](#deliverables)\n- [Executive Summary](#executive-summary)\n- [Domain-Specific Reports](#domain-specific-reports)\n- [Integrated Action Plan](#integrated-action-plan)\n- [Modular Architecture](#modular-architecture)\n- [Exit Criteria](#exit-criteria)\n\n\n# Unified Review Orchestration\n\nIntelligently selects and executes appropriate review skills based on codebase analysis and context.\n\n## Quick Start\n\n```bash\n# Auto-detect and run appropriate reviews\n/full-review\n\n# Focus on specific areas\n/full-review api          # API surface review\n/full-review architecture # Architecture review\n/full-review bugs         # Bug hunting\n/full-review tests        # Test suite review\n/full-review all          # Run all applicable skills\n```\n**Verification:** Run `pytest -v` to verify tests pass.\n\n## When To Use\n\n- Starting a full code review\n- Reviewing changes across multiple domains\n- Need intelligent selection of review skills\n- Want integrated reporting from multiple review types\n- Before merging major feature branches\n\n## When NOT To Use\n\n- Specific review type known\n  - use bug-review\n- Test-review\n- Architecture-only focus - use\n  architecture-review\n- Specific review type known\n  - use bug-review\n\n## Review Skill Selection Matrix\n\n| Codebase Pattern | Review Skills | Triggers |\n|-----------------|---------------|----------|\n| Rust files (`*.rs`, `Cargo.toml`) | rust-review, bug-review, api-review | Rust project detected |\n| API changes (`openapi.yaml`, `routes/`) | api-review, architecture-review | Public API surfaces |\n| Test files (`test_*.py`, `*_test.go`) | test-review, bug-review | Test infrastructure |\n| Makefile/build system | makefile-review, architecture-review | Build complexity |\n| Mathematical algorithms | math-review, bug-review | Numerical computation |\n| Architecture docs/ADRs | architecture-review, api-review | System design |\n| General code quality | bug-review, test-review | Default review |\n| Post-implementation audit | imbue:justify | High add/delete ratio, test changes, new abstractions |\n\n## Workflow\n\n### 1. Analyze Repository Context\n- Detect primary languages from extensions and manifests\n- Analyze git status and diffs for change scope\n- Identify project structure (monorepo, microservices, library)\n- Detect build systems, testing frameworks, documentation\n\n### 2. Select Review Skills\n```python\n# Detection logic\nif has_rust_files():\n    schedule_skill(\"rust-review\")\nif has_api_changes():\n    schedule_skill(\"api-review\")\nif has_test_files():\n    schedule_skill(\"test-review\")\nif has_makefiles():\n    schedule_skill(\"makefile-review\")\nif has_math_code():\n    schedule_skill(\"math-review\")\nif has_architecture_changes():\n    schedule_skill(\"architecture-review\")\n# Default\nschedule_skill(\"bug-review\")\n```\n**Verification:** Run `pytest -v` to verify tests pass.\n\n### 3. Execute Reviews\n\nDispatch selected skills concurrently via the Agent tool.\nUse this mapping to resolve skill names to agent types:\n\n| Skill Name | Agent Type | Notes |\n|---|---|---|\n| bug-review | `pensive:code-reviewer` | Covers bugs, API, tests |\n| api-review | `pensive:code-reviewer` | Same agent, API focus |\n| test-review | `pensive:code-reviewer` | Same agent, test focus |\n| architecture-review | `pensive:architecture-reviewer` | ADR compliance |\n| rust-review | `pensive:rust-auditor` | Rust-specific |\n| code-refinement | `pensive:code-refiner` | Duplication, quality |\n| math-review | `general-purpose` | Prompt: invoke `Skill(pensive:math-review)` |\n| makefile-review | `general-purpose` | Prompt: invoke `Skill(pensive:makefile-review)` |\n| shell-review | `general-purpose` | Prompt: invoke `Skill(pensive:shell-review)` |\n\n**Sub-agent isolation (required):**\n\nDispatch ALL selected agents in a SINGLE parallel Agent tool\ncall. Do not read or process any agent's output until ALL agents\nhave returned their results. Reading the first result before the\nothers are in anchors synthesis toward that perspective — each\nsubsequent result gets evaluated against the first rather than\nindependently. Collect all results, then synthesize once.\n\n**Rules:**\n- Never use skill names as agent types (e.g., `pensive:math-review` is NOT an agent)\n- When `pensive:code-reviewer` covers multiple domains, dispatch once with combined scope\n- For skills without dedicated agents, use `general-purpose` and instruct it to invoke the Skill tool\n- Maintain consistent evidence logging across all agents\n- Track progress via TodoWrite\n\n### 4. Integrate Findings\n\n- Consolidate findings across domains\n- Identify cross-domain patterns\n- Prioritize by impact and effort\n- Generate unified action plan\n\n**Deferred capture for backlog findings:**\nFindings that are triaged to the backlog (out-of-scope for\nthe current review or deferred by the team) should be\npreserved so they are not lost between review cycles.\nFor each finding assigned to the backlog, run:\n\n```bash\npython3 scripts/deferred_capture.py \\\n  --title \"<finding title>\" \\\n  --source review \\\n  --context \"Review dimension: <dimension>. <finding description>\"\n```\n\nThe `<dimension>` value should match the review skill that\nsurfaced the finding (e.g. `bug-review`, `api-review`,\n`architecture-review`).\nThis runs automatically after the action plan is finalised,\nwithout prompting the user.\n\n## Review Modes\n\n### Auto-Detect (default)\nAutomatically selects skills based on codebase analysis.\n\n### Focused Mode\nRun specific review domains:\n- `/full-review api` → api-review only\n- `/full-review architecture` → architecture-review only\n- `/full-review bugs` → bug-review only\n- `/full-review tests` → test-review only\n\n### Full Review Mode\nRun all applicable review skills:\n- `/full-review all` → Execute all detected skills\n\n## Quality Gates\n\nEach review must:\n1. Establish proper context\n2. Execute all selected skills successfully\n3. Document findings with evidence\n4. Prioritize recommendations by impact\n5. Create action plan with owners\n\n## Deliverables\n\n### Executive Summary\n- Overall codebase health assessment\n- Critical issues requiring immediate attention\n- Review frequency recommendations\n\n### Domain-Specific Reports\n- API surface analysis and consistency\n- Architecture alignment with ADRs\n- Test coverage gaps and improvements\n- Bug analysis and security findings\n- Performance and maintainability recommendations\n\n### Integrated Action Plan\n- Prioritized remediation tasks\n- Cross-domain dependencies\n- Assigned owners and target dates\n- Follow-up review schedule\n\n## Modular Architecture\n\nAll review skills use a hub-and-spoke architecture with progressive loading:\n\n- **`pensive:shared`**: Common workflow, output templates, quality checklists\n- **Each skill has `modules/`**: Domain-specific details loaded on demand\n- **Cross-plugin deps**: `imbue:proof-of-work`, `imbue:diff-analysis/modules/risk-assessment-framework`\n\nThis reduces token usage by 50-70% for focused reviews while maintaining full capabilities.\n\n## Exit Criteria\n\n- All selected review skills executed\n- Findings consolidated and prioritized\n- Action plan created with ownership\n- Evidence logged per structured output format\n## Supporting Modules\n\n- [Review workflow core](modules/review-workflow-core.md) - standard 5-step workflow pattern for all pensive reviews\n- [Output format templates](modules/output-format-templates.md) - finding entry, severity, action item templates\n- [Quality checklist patterns](modules/quality-checklist-patterns.md) - pre-review, analysis, evidence, deliverable checklists\n\n## Troubleshooting\n\n### Common Issues\n\nIf the auto-detection fails to identify the correct review skills, explicitly specify the mode (e.g., `/full-review rust` instead of just `/full-review`). If integration fails, check that `TodoWrite` logs are accessible and that evidence files were correctly written by the individual skills.\n\nFile v1.9.14:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-pensive-unified-review\",\n  \"version\": \"1.9.14\",\n  \"publishedAt\": 1782842690733\n}\n\nFile v1.9.14:modules/output-format-templates.md\n\n---\nname: output-format-templates\ndescription: Standard output format templates for pensive review deliverables\nparent_skill: pensive:shared\ncategory: review-infrastructure\ntags: [templates, output, formatting, structure]\nreusable_by: [pensive:bug-review, pensive:api-review, pensive:architecture-review, pensive:test-review, pensive:rust-review, pensive:makefile-review, pensive:math-review, pensive:unified-review]\nestimated_tokens: 350\n---\n\n# Output Format Templates\n\nStandard templates for consistent review deliverables.\n\n## Top-Level Structure\n\n```markdown\n# [Review Type] Review: [Subject]\n\n## Executive Summary\n[High-level overview, key findings count, overall assessment]\n\n## Findings Summary\n[Count by severity: Critical, High, Medium, Low]\n\n## Detailed Findings\n[Organized by category or severity]\n\n## Action Items\n[Prioritized recommendations with owner and next step]\n\n## Evidence Appendix\n[Supporting code snippets, references, measurements]\n```\n\n## Finding Entry Template\n\n```markdown\n### [Category]: [Short Title]\n\n**Severity**: [Critical|High|Medium|Low]\n**Location**: [File path:line numbers or component name]\n**Category**: [Specific category from domain]\n\n**Issue**:\n[Clear description of what's wrong]\n\n**Evidence**:\n[Code snippet, measurement, or observation]\n\n**Why This Matters**:\n[The underlying principle or rule being violated.\nExplain the concept, not just the symptom.]\n\n**Proof**:\n[Link to authoritative best-practice documentation.\nPrefer: language docs, OWASP, PEPs, style guides,\nRFCs. Summarize what the link teaches.]\n\n**Teachable Moment**:\n[How this lesson generalizes beyond this specific\nfinding. When else would this principle apply?]\n\n**Recommendation**:\n[Specific steps to resolve, with concrete next action]\n\n**References**: [Evidence appendix section or external docs]\n```\n\n### Educational Depth by Severity\n\n| Severity | Why | Proof Link | Teachable Moment |\n|----------|-----|------------|------------------|\n| Critical | Required | Required | Required |\n| High | Required | Required | Required |\n| Medium | Required | If available | Optional |\n| Low | Brief | Optional | Optional |\n\n## Severity Definitions\n\n**Critical**: Security vulnerability, data loss risk, system failure potential\n**High**: Significant functionality issues, major violations, substantial technical debt\n**Medium**: Moderate violations, code quality issues, maintainability concerns\n**Low**: Minor style issues, optimization opportunities, documentation gaps\n\n## Action Items Template\n\n```markdown\n## Action Items\n\n### Immediate (Critical/High Severity)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n\n### Short-term (Medium Severity)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n\n### Long-term (Low Severity / Improvements)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n```\n\n## Evidence Appendix Template\n\n```markdown\n## Evidence Appendix\n\n### E1: [Short Reference Name]\n**Related to**: Finding [X]\n**File**: `/path/to/file.ext:lines`\n\n```[language]\n[code snippet or measurement]\n```\n\n**Context**: [Why this evidence matters]\n\n---\n\n### E2: [Next Reference]\n...\n```\n\n## Summary Statistics Template\n\n```markdown\n## Review Statistics\n\n- **Total Items Reviewed**: [count]\n- **Findings by Severity**:\n  - Critical: [count]\n  - High: [count]\n  - Medium: [count]\n  - Low: [count]\n- **Categories Analyzed**: [list]\n- **Recommendations**: [count]\n```\n\n## Usage Notes\n\n1. Adapt section headings to domain (e.g., \"Endpoints\" for API, \"Components\" for architecture)\n2. Always link findings to evidence\n3. Keep Executive Summary under 5 sentences\n4. validate every finding has a concrete next step\n5. Use consistent severity assessment across entire review\n\nFile v1.9.14:modules/quality-checklist-patterns.md\n\n---\nname: quality-checklist-patterns\ndescription: Reusable quality checklist patterns for review validation\nparent_skill: pensive:shared\ncategory: review-infrastructure\ntags: [quality, checklist, validation, completeness]\nreusable_by: [pensive:bug-review, pensive:api-review, pensive:architecture-review, pensive:test-review, pensive:rust-review, pensive:makefile-review, pensive:math-review, pensive:unified-review]\nestimated_tokens: 300\n---\n\n# Quality Checklist Patterns\n\nStandard quality assurance checklists for review deliverables.\n\n## Pre-Review Checklist\n\nExecute before starting analysis:\n\n- [ ] Scope clearly defined and documented\n- [ ] Review criteria identified (use domain-specific patterns)\n- [ ] Success criteria established\n- [ ] Evidence logging strategy prepared\n- [ ] Output template selected and customized\n\n## Analysis Quality Checklist\n\nExecute during deep analysis phase:\n\n- [ ] All scope items examined\n- [ ] Domain-specific criteria applied consistently\n- [ ] Severity assessed using standard definitions\n- [ ] Patterns and anti-patterns identified\n- [ ] Cross-references validated\n- [ ] Edge cases considered\n\n## Evidence Quality Checklist\n\nExecute during evidence capture:\n\n- [ ] Every finding has supporting evidence\n- [ ] File paths and line numbers included\n- [ ] Code snippets are minimal and focused\n- [ ] Context preserved for each evidence item\n- [ ] Evidence appendix organized and referenced\n- [ ] Reasoning chains documented\n\n## Deliverable Completeness Checklist\n\nExecute before finalizing output:\n\n- [ ] Executive summary present and concise\n- [ ] All findings documented with required fields:\n  - [ ] Severity assigned\n  - [ ] Location specified\n  - [ ] Category identified\n  - [ ] Issue described\n  - [ ] Evidence provided\n  - [ ] Impact explained\n  - [ ] Recommendation actionable\n- [ ] Action items prioritized by severity\n- [ ] Evidence appendix complete\n- [ ] Summary statistics included\n- [ ] Output follows template structure\n\n## Recommendation Quality Checklist\n\nExecute for each recommendation:\n\n- [ ] Specific and actionable\n- [ ] Addresses root cause, not just symptoms\n- [ ] Feasible within project constraints\n- [ ] Prioritized appropriately\n- [ ] Linked to finding\n- [ ] Includes rationale\n\n## Review Consistency Checklist\n\nExecute before final delivery:\n\n- [ ] Severity levels applied consistently\n- [ ] Terminology used consistently\n- [ ] Categories align with domain standards\n- [ ] Similar issues grouped appropriately\n- [ ] No contradictory recommendations\n- [ ] Style and tone professional throughout\n\n## Exit Criteria Validation\n\nFinal check before completion:\n\n- [ ] All TodoWrite items marked complete\n- [ ] Workflow steps executed in sequence\n- [ ] Quality checklists satisfied\n- [ ] Output validated against template\n- [ ] Evidence complete and linked\n- [ ] Deliverable ready for stakeholder review\n\n## Usage Pattern\n\nIntegrate into Step 5 (Deliverable Assembly) of review workflow:\n\n```python\n# Before marking final todo as complete\nprint(\"Validating deliverable quality...\")\n# Run through Deliverable Completeness Checklist\n# Run through Review Consistency Checklist\n# Run through Exit Criteria Validation\n# Only then mark todo complete\n```\n\n## Customization\n\nDomain-specific reviews may extend these checklists with:\n- Additional domain criteria (e.g., security-specific checks)\n- Tool-specific validation (e.g., linter results)\n- Compliance requirements (e.g., regulatory standards)\n\nExtend, don't replace, these baseline checklists.\n\nFile v1.9.14:modules/review-workflow-core.md\n\n---\nname: review-workflow-core\ndescription: Core workflow patterns for all pensive review skills\nparent_skill: pensive:shared\ncategory: review-infrastructure\ntags: [workflow, core, review, patterns]\nreusable_by: [pensive:bug-review, pensive:api-review, pensive:architecture-review, pensive:test-review, pensive:rust-review, pensive:makefile-review, pensive:math-review, pensive:unified-review]\nestimated_tokens: 400\n---\n\n# Review Workflow Core\n\nStandard 5-step workflow pattern for all pensive review skills.\n\n## Workflow Structure\n\n### Step 1: Context Establishment\n**TodoWrite Item**: \"Establishing review context\"\n\nActions:\n1. Identify review scope and boundaries\n2. Gather relevant files and documentation\n3. Establish success criteria\n4. Load domain-specific patterns (if applicable)\n\n**Output**: Context summary with scope definition\n\n### Step 2: Scope Inventory\n**TodoWrite Item**: \"Creating scope inventory\"\n\nActions:\n1. Catalog all items to review (files, components, endpoints, etc.)\n2. Categorize by type, complexity, or domain area\n3. Prioritize based on risk, complexity, or impact\n4. Create initial structure for findings\n\n**Output**: Structured inventory with categories\n\n### Step 3: Deep Analysis\n**TodoWrite Item**: \"Performing deep analysis\"\n\nActions:\n1. Apply domain-specific review criteria\n2. Identify patterns, anti-patterns, violations\n3. Assess severity (Critical, High, Medium, Low)\n4. Cross-reference with best practices\n5. Capture evidence for each finding\n\n**Output**: Detailed findings with evidence\n\n### Step 4: Evidence Capture\n**TodoWrite Item**: \"Capturing evidence\"\n\nIntegration with `imbue:proof-of-work`:\n1. Document code snippets with file paths and line numbers\n2. Record reasoning chains for conclusions\n3. Link findings to specific violations or patterns\n4. Preserve context for future reference\n\n**Output**: Evidence appendix linked to findings\n\n### Step 5: Deliverable Assembly\n**TodoWrite Item**: \"Assembling final deliverable\"\n\nActions:\n1. Structure findings by severity and category\n2. Format recommendations with actionable steps\n3. Create prioritized action items\n4. Validate completeness against exit criteria\n5. Generate final output using templates\n\n**Output**: Complete review deliverable\n\n## TodoWrite Integration\n\nCreate tasks at workflow start:\n\n```python\nTodoWrite({\n    \"todos\": [\n        {\"content\": \"Establish review context\", \"status\": \"pending\", \"activeForm\": \"Establishing review context\"},\n        {\"content\": \"Create scope inventory\", \"status\": \"pending\", \"activeForm\": \"Creating scope inventory\"},\n        {\"content\": \"Perform deep analysis\", \"status\": \"pending\", \"activeForm\": \"Performing deep analysis\"},\n        {\"content\": \"Capture evidence\", \"status\": \"pending\", \"activeForm\": \"Capturing evidence\"},\n        {\"content\": \"Assemble final deliverable\", \"status\": \"pending\", \"activeForm\": \"Assembling final deliverable\"}\n    ]\n})\n```\n\nMark each as `in_progress` when starting, `completed` when finished.\n\n## Exit Criteria\n\nBefore marking workflow complete:\n- [ ] All scope items analyzed\n- [ ] Evidence captured for each finding\n- [ ] Recommendations are actionable\n- [ ] Output follows format templates\n- [ ] Quality checklist satisfied\n\nFile v1.9.14:skill-card.md\n\n## Description: <br>\nOrchestrates multi-domain review across code, architecture, tests, and security in a single pass. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[athola](https://clawhub.ai/user/athola) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and engineers use this skill to select and coordinate code, architecture, test, security, and related review workflows before merging major changes or assessing a codebase. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill can automatically record review findings or backlog content without clear user confirmation. <br>\nMitigation: Confirm where deferred findings are written before use, disable or constrain capture where possible, and avoid running the skill on repositories with sensitive content unless capture behavior is understood. <br>\nRisk: The workflow may run local review or test commands as part of repository analysis. <br>\nMitigation: Run it in a controlled workspace, review commands before execution when possible, and prefer focused review modes for narrower scope. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-pensive-unified-review) <br>\n- [Publisher profile](https://clawhub.ai/user/athola) <br>\n- [Project homepage](https://github.com/athola/claude-night-market/tree/master/plugins/pensive) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, guidance] <br>\n**Output Format:** [Markdown with structured review findings, action items, evidence appendices, and inline shell commands] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May automatically save deferred backlog findings according to the skill workflow.] <br>\n\n## Skill Version(s): <br>\n1.9.14 (source: server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.9.13: 6 files, 10318 bytes\n\nFiles: modules/output-format-templates.md (3699b), modules/quality-checklist-patterns.md (3503b), modules/review-workflow-core.md (3203b), skill-card.md (2698b), SKILL.md (9230b), _meta.json (145b)\n\nFile v1.9.13:SKILL.md\n\n---\nname: unified-review\ndescription: Orchestrates multi-domain review (code, arch, tests, security) in a single pass\nversion: 1.9.8\ntriggers:\n  - review\n  - orchestration\n  - code-quality\n  - analysis\n  - multi-domain\n  - comprehensive pre-release review is needed\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/pensive\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.pensive:shared\", \"night-market.imbue:proof-of-work\", \"night-market.imbue:structured-output\"]}}}\nsource: claude-night-market\nsource_plugin: pensive\n---\n\n> **Night Market Skill** — ported from [claude-night-market/pensive](https://github.com/athola/claude-night-market/tree/master/plugins/pensive). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n## Table of Contents\n\n- [Quick Start](#quick-start)\n- [When to Use](#when-to-use)\n- [Review Skill Selection Matrix](#review-skill-selection-matrix)\n- [Workflow](#workflow)\n- [1. Analyze Repository Context](#1-analyze-repository-context)\n- [2. Select Review Skills](#2-select-review-skills)\n- [3. Execute Reviews](#3-execute-reviews)\n- [4. Integrate Findings](#4-integrate-findings)\n- [Review Modes](#review-modes)\n- [Auto-Detect (default)](#auto-detect-(default))\n- [Focused Mode](#focused-mode)\n- [Full Review Mode](#full-review-mode)\n- [Quality Gates](#quality-gates)\n- [Deliverables](#deliverables)\n- [Executive Summary](#executive-summary)\n- [Domain-Specific Reports](#domain-specific-reports)\n- [Integrated Action Plan](#integrated-action-plan)\n- [Modular Architecture](#modular-architecture)\n- [Exit Criteria](#exit-criteria)\n\n\n# Unified Review Orchestration\n\nIntelligently selects and executes appropriate review skills based on codebase analysis and context.\n\n## Quick Start\n\n```bash\n# Auto-detect and run appropriate reviews\n/full-review\n\n# Focus on specific areas\n/full-review api          # API surface review\n/full-review architecture # Architecture review\n/full-review bugs         # Bug hunting\n/full-review tests        # Test suite review\n/full-review all          # Run all applicable skills\n```\n**Verification:** Run `pytest -v` to verify tests pass.\n\n## When To Use\n\n- Starting a full code review\n- Reviewing changes across multiple domains\n- Need intelligent selection of review skills\n- Want integrated reporting from multiple review types\n- Before merging major feature branches\n\n## When NOT To Use\n\n- Specific review type known\n  - use bug-review\n- Test-review\n- Architecture-only focus - use\n  architecture-review\n- Specific review type known\n  - use bug-review\n\n## Review Skill Selection Matrix\n\n| Codebase Pattern | Review Skills | Triggers |\n|-----------------|---------------|----------|\n| Rust files (`*.rs`, `Cargo.toml`) | rust-review, bug-review, api-review | Rust project detected |\n| API changes (`openapi.yaml`, `routes/`) | api-review, architecture-review | Public API surfaces |\n| Test files (`test_*.py`, `*_test.go`) | test-review, bug-review | Test infrastructure |\n| Makefile/build system | makefile-review, architecture-review | Build complexity |\n| Mathematical algorithms | math-review, bug-review | Numerical computation |\n| Architecture docs/ADRs | architecture-review, api-review | System design |\n| General code quality | bug-review, test-review | Default review |\n| Post-implementation audit | imbue:justify | High add/delete ratio, test changes, new abstractions |\n\n## Workflow\n\n### 1. Analyze Repository Context\n- Detect primary languages from extensions and manifests\n- Analyze git status and diffs for change scope\n- Identify project structure (monorepo, microservices, library)\n- Detect build systems, testing frameworks, documentation\n\n### 2. Select Review Skills\n```python\n# Detection logic\nif has_rust_files():\n    schedule_skill(\"rust-review\")\nif has_api_changes():\n    schedule_skill(\"api-review\")\nif has_test_files():\n    schedule_skill(\"test-review\")\nif has_makefiles():\n    schedule_skill(\"makefile-review\")\nif has_math_code():\n    schedule_skill(\"math-review\")\nif has_architecture_changes():\n    schedule_skill(\"architecture-review\")\n# Default\nschedule_skill(\"bug-review\")\n```\n**Verification:** Run `pytest -v` to verify tests pass.\n\n### 3. Execute Reviews\n\nDispatch selected skills concurrently via the Agent tool.\nUse this mapping to resolve skill names to agent types:\n\n| Skill Name | Agent Type | Notes |\n|---|---|---|\n| bug-review | `pensive:code-reviewer` | Covers bugs, API, tests |\n| api-review | `pensive:code-reviewer` | Same agent, API focus |\n| test-review | `pensive:code-reviewer` | Same agent, test focus |\n| architecture-review | `pensive:architecture-reviewer` | ADR compliance |\n| rust-review | `pensive:rust-auditor` | Rust-specific |\n| code-refinement | `pensive:code-refiner` | Duplication, quality |\n| math-review | `general-purpose` | Prompt: invoke `Skill(pensive:math-review)` |\n| makefile-review | `general-purpose` | Prompt: invoke `Skill(pensive:makefile-review)` |\n| shell-review | `general-purpose` | Prompt: invoke `Skill(pensive:shell-review)` |\n\n**Sub-agent isolation (required):**\n\nDispatch ALL selected agents in a SINGLE parallel Agent tool\ncall. Do not read or process any agent's output until ALL agents\nhave returned their results. Reading the first result before the\nothers are in anchors synthesis toward that perspective — each\nsubsequent result gets evaluated against the first rather than\nindependently. Collect all results, then synthesize once.\n\n**Rules:**\n- Never use skill names as agent types (e.g., `pensive:math-review` is NOT an agent)\n- When `pensive:code-reviewer` covers multiple domains, dispatch once with combined scope\n- For skills without dedicated agents, use `general-purpose` and instruct it to invoke the Skill tool\n- Maintain consistent evidence logging across all agents\n- Track progress via TodoWrite\n\n### 4. Integrate Findings\n\n- Consolidate findings across domains\n- Identify cross-domain patterns\n- Prioritize by impact and effort\n- Generate unified action plan\n\n**Deferred capture for backlog findings:**\nFindings that are triaged to the backlog (out-of-scope for\nthe current review or deferred by the team) should be\npreserved so they are not lost between review cycles.\nFor each finding assigned to the backlog, run:\n\n```bash\npython3 scripts/deferred_capture.py \\\n  --title \"<finding title>\" \\\n  --source review \\\n  --context \"Review dimension: <dimension>. <finding description>\"\n```\n\nThe `<dimension>` value should match the review skill that\nsurfaced the finding (e.g. `bug-review`, `api-review`,\n`architecture-review`).\nThis runs automatically after the action plan is finalised,\nwithout prompting the user.\n\n## Review Modes\n\n### Auto-Detect (default)\nAutomatically selects skills based on codebase analysis.\n\n### Focused Mode\nRun specific review domains:\n- `/full-review api` → api-review only\n- `/full-review architecture` → architecture-review only\n- `/full-review bugs` → bug-review only\n- `/full-review tests` → test-review only\n\n### Full Review Mode\nRun all applicable review skills:\n- `/full-review all` → Execute all detected skills\n\n## Quality Gates\n\nEach review must:\n1. Establish proper context\n2. Execute all selected skills successfully\n3. Document findings with evidence\n4. Prioritize recommendations by impact\n5. Create action plan with owners\n\n## Deliverables\n\n### Executive Summary\n- Overall codebase health assessment\n- Critical issues requiring immediate attention\n- Review frequency recommendations\n\n### Domain-Specific Reports\n- API surface analysis and consistency\n- Architecture alignment with ADRs\n- Test coverage gaps and improvements\n- Bug analysis and security findings\n- Performance and maintainability recommendations\n\n### Integrated Action Plan\n- Prioritized remediation tasks\n- Cross-domain dependencies\n- Assigned owners and target dates\n- Follow-up review schedule\n\n## Modular Architecture\n\nAll review skills use a hub-and-spoke architecture with progressive loading:\n\n- **`pensive:shared`**: Common workflow, output templates, quality checklists\n- **Each skill has `modules/`**: Domain-specific details loaded on demand\n- **Cross-plugin deps**: `imbue:proof-of-work`, `imbue:diff-analysis/modules/risk-assessment-framework`\n\nThis reduces token usage by 50-70% for focused reviews while maintaining full capabilities.\n\n## Exit Criteria\n\n- All selected review skills executed\n- Findings consolidated and prioritized\n- Action plan created with ownership\n- Evidence logged per structured output format\n## Supporting Modules\n\n- [Review workflow core](modules/review-workflow-core.md) - standard 5-step workflow pattern for all pensive reviews\n- [Output format templates](modules/output-format-templates.md) - finding entry, severity, action item templates\n- [Quality checklist patterns](modules/quality-checklist-patterns.md) - pre-review, analysis, evidence, deliverable checklists\n\n## Troubleshooting\n\n### Common Issues\n\nIf the auto-detection fails to identify the correct review skills, explicitly specify the mode (e.g., `/full-review rust` instead of just `/full-review`). If integration fails, check that `TodoWrite` logs are accessible and that evidence files were correctly written by the individual skills.\n\nFile v1.9.13:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-pensive-unified-review\",\n  \"version\": \"1.9.13\",\n  \"publishedAt\": 1782577365285\n}\n\nFile v1.9.13:modules/output-format-templates.md\n\n---\nname: output-format-templates\ndescription: Standard output format templates for pensive review deliverables\nparent_skill: pensive:shared\ncategory: review-infrastructure\ntags: [templates, output, formatting, structure]\nreusable_by: [pensive:bug-review, pensive:api-review, pensive:architecture-review, pensive:test-review, pensive:rust-review, pensive:makefile-review, pensive:math-review, pensive:unified-review]\nestimated_tokens: 350\n---\n\n# Output Format Templates\n\nStandard templates for consistent review deliverables.\n\n## Top-Level Structure\n\n```markdown\n# [Review Type] Review: [Subject]\n\n## Executive Summary\n[High-level overview, key findings count, overall assessment]\n\n## Findings Summary\n[Count by severity: Critical, High, Medium, Low]\n\n## Detailed Findings\n[Organized by category or severity]\n\n## Action Items\n[Prioritized recommendations with owner and next step]\n\n## Evidence Appendix\n[Supporting code snippets, references, measurements]\n```\n\n## Finding Entry Template\n\n```markdown\n### [Category]: [Short Title]\n\n**Severity**: [Critical|High|Medium|Low]\n**Location**: [File path:line numbers or component name]\n**Category**: [Specific category from domain]\n\n**Issue**:\n[Clear description of what's wrong]\n\n**Evidence**:\n[Code snippet, measurement, or observation]\n\n**Why This Matters**:\n[The underlying principle or rule being violated.\nExplain the concept, not just the symptom.]\n\n**Proof**:\n[Link to authoritative best-practice documentation.\nPrefer: language docs, OWASP, PEPs, style guides,\nRFCs. Summarize what the link teaches.]\n\n**Teachable Moment**:\n[How this lesson generalizes beyond this specific\nfinding. When else would this principle apply?]\n\n**Recommendation**:\n[Specific steps to resolve, with concrete next action]\n\n**References**: [Evidence appendix section or external docs]\n```\n\n### Educational Depth by Severity\n\n| Severity | Why | Proof Link | Teachable Moment |\n|----------|-----|------------|------------------|\n| Critical | Required | Required | Required |\n| High | Required | Required | Required |\n| Medium | Required | If available | Optional |\n| Low | Brief | Optional | Optional |\n\n## Severity Definitions\n\n**Critical**: Security vulnerability, data loss risk, system failure potential\n**High**: Significant functionality issues, major violations, substantial technical debt\n**Medium**: Moderate violations, code quality issues, maintainability concerns\n**Low**: Minor style issues, optimization opportunities, documentation gaps\n\n## Action Items Template\n\n```markdown\n## Action Items\n\n### Immediate (Critical/High Severity)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n\n### Short-term (Medium Severity)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n\n### Long-term (Low Severity / Improvements)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n```\n\n## Evidence Appendix Template\n\n```markdown\n## Evidence Appendix\n\n### E1: [Short Reference Name]\n**Related to**: Finding [X]\n**File**: `/path/to/file.ext:lines`\n\n```[language]\n[code snippet or measurement]\n```\n\n**Context**: [Why this evidence matters]\n\n---\n\n### E2: [Next Reference]\n...\n```\n\n## Summary Statistics Template\n\n```markdown\n## Review Statistics\n\n- **Total Items Reviewed**: [count]\n- **Findings by Severity**:\n  - Critical: [count]\n  - High: [count]\n  - Medium: [count]\n  - Low: [count]\n- **Categories Analyzed**: [list]\n- **Recommendations**: [count]\n```\n\n## Usage Notes\n\n1. Adapt section headings to domain (e.g., \"Endpoints\" for API, \"Components\" for architecture)\n2. Always link findings to evidence\n3. Keep Executive Summary under 5 sentences\n4. validate every finding has a concrete next step\n5. Use consistent severity assessment across entire review\n\nFile v1.9.13:modules/quality-checklist-patterns.md\n\n---\nname: quality-checklist-patterns\ndescription: Reusable quality checklist patterns for review validation\nparent_skill: pensive:shared\ncategory: review-infrastructure\ntags: [quality, checklist, validation, completeness]\nreusable_by: [pensive:bug-review, pensive:api-review, pensive:architecture-review, pensive:test-review, pensive:rust-review, pensive:makefile-review, pensive:math-review, pensive:unified-review]\nestimated_tokens: 300\n---\n\n# Quality Checklist Patterns\n\nStandard quality assurance checklists for review deliverables.\n\n## Pre-Review Checklist\n\nExecute before starting analysis:\n\n- [ ] Scope clearly defined and documented\n- [ ] Review criteria identified (use domain-specific patterns)\n- [ ] Success criteria established\n- [ ] Evidence logging strategy prepared\n- [ ] Output template selected and customized\n\n## Analysis Quality Checklist\n\nExecute during deep analysis phase:\n\n- [ ] All scope items examined\n- [ ] Domain-specific criteria applied consistently\n- [ ] Severity assessed using standard definitions\n- [ ] Patterns and anti-patterns identified\n- [ ] Cross-references validated\n- [ ] Edge cases considered\n\n## Evidence Quality Checklist\n\nExecute during evidence capture:\n\n- [ ] Every finding has supporting evidence\n- [ ] File paths and line numbers included\n- [ ] Code snippets are minimal and focused\n- [ ] Context preserved for each evidence item\n- [ ] Evidence appendix organized and referenced\n- [ ] Reasoning chains documented\n\n## Deliverable Completeness Checklist\n\nExecute before finalizing output:\n\n- [ ] Executive summary present and concise\n- [ ] All findings documented with required fields:\n  - [ ] Severity assigned\n  - [ ] Location specified\n  - [ ] Category identified\n  - [ ] Issue described\n  - [ ] Evidence provided\n  - [ ] Impact explained\n  - [ ] Recommendation actionable\n- [ ] Action items prioritized by severity\n- [ ] Evidence appendix complete\n- [ ] Summary statistics included\n- [ ] Output follows template structure\n\n## Recommendation Quality Checklist\n\nExecute for each recommendation:\n\n- [ ] Specific and actionable\n- [ ] Addresses root cause, not just symptoms\n- [ ] Feasible within project constraints\n- [ ] Prioritized appropriately\n- [ ] Linked to finding\n- [ ] Includes rationale\n\n## Review Consistency Checklist\n\nExecute before final delivery:\n\n- [ ] Severity levels applied consistently\n- [ ] Terminology used consistently\n- [ ] Categories align with domain standards\n- [ ] Similar issues grouped appropriately\n- [ ] No contradictory recommendations\n- [ ] Style and tone professional throughout\n\n## Exit Criteria Validation\n\nFinal check before completion:\n\n- [ ] All TodoWrite items marked complete\n- [ ] Workflow steps executed in sequence\n- [ ] Quality checklists satisfied\n- [ ] Output validated against template\n- [ ] Evidence complete and linked\n- [ ] Deliverable ready for stakeholder review\n\n## Usage Pattern\n\nIntegrate into Step 5 (Deliverable Assembly) of review workflow:\n\n```python\n# Before marking final todo as complete\nprint(\"Validating deliverable quality...\")\n# Run through Deliverable Completeness Checklist\n# Run through Review Consistency Checklist\n# Run through Exit Criteria Validation\n# Only then mark todo complete\n```\n\n## Customization\n\nDomain-specific reviews may extend these checklists with:\n- Additional domain criteria (e.g., security-specific checks)\n- Tool-specific validation (e.g., linter results)\n- Compliance requirements (e.g., regulatory standards)\n\nExtend, don't replace, these baseline checklists.\n\nFile v1.9.13:modules/review-workflow-core.md\n\n---\nname: review-workflow-core\ndescription: Core workflow patterns for all pensive review skills\nparent_skill: pensive:shared\ncategory: review-infrastructure\ntags: [workflow, core, review, patterns]\nreusable_by: [pensive:bug-review, pensive:api-review, pensive:architecture-review, pensive:test-review, pensive:rust-review, pensive:makefile-review, pensive:math-review, pensive:unified-review]\nestimated_tokens: 400\n---\n\n# Review Workflow Core\n\nStandard 5-step workflow pattern for all pensive review skills.\n\n## Workflow Structure\n\n### Step 1: Context Establishment\n**TodoWrite Item**: \"Establishing review context\"\n\nActions:\n1. Identify review scope and boundaries\n2. Gather relevant files and documentation\n3. Establish success criteria\n4. Load domain-specific patterns (if applicable)\n\n**Output**: Context summary with scope definition\n\n### Step 2: Scope Inventory\n**TodoWrite Item**: \"Creating scope inventory\"\n\nActions:\n1. Catalog all items to review (files, components, endpoints, etc.)\n2. Categorize by type, complexity, or domain area\n3. Prioritize based on risk, complexity, or impact\n4. Create initial structure for findings\n\n**Output**: Structured inventory with categories\n\n### Step 3: Deep Analysis\n**TodoWrite Item**: \"Performing deep analysis\"\n\nActions:\n1. Apply domain-specific review criteria\n2. Identify patterns, anti-patterns, violations\n3. Assess severity (Critical, High, Medium, Low)\n4. Cross-reference with best practices\n5. Capture evidence for each finding\n\n**Output**: Detailed findings with evidence\n\n### Step 4: Evidence Capture\n**TodoWrite Item**: \"Capturing evidence\"\n\nIntegration with `imbue:proof-of-work`:\n1. Document code snippets with file paths and line numbers\n2. Record reasoning chains for conclusions\n3. Link findings to specific violations or patterns\n4. Preserve context for future reference\n\n**Output**: Evidence appendix linked to findings\n\n### Step 5: Deliverable Assembly\n**TodoWrite Item**: \"Assembling final deliverable\"\n\nActions:\n1. Structure findings by severity and category\n2. Format recommendations with actionable steps\n3. Create prioritized action items\n4. Validate completeness against exit criteria\n5. Generate final output using templates\n\n**Output**: Complete review deliverable\n\n## TodoWrite Integration\n\nCreate tasks at workflow start:\n\n```python\nTodoWrite({\n    \"todos\": [\n        {\"content\": \"Establish review context\", \"status\": \"pending\", \"activeForm\": \"Establishing review context\"},\n        {\"content\": \"Create scope inventory\", \"status\": \"pending\", \"activeForm\": \"Creating scope inventory\"},\n        {\"content\": \"Perform deep analysis\", \"status\": \"pending\", \"activeForm\": \"Performing deep analysis\"},\n        {\"content\": \"Capture evidence\", \"status\": \"pending\", \"activeForm\": \"Capturing evidence\"},\n        {\"content\": \"Assemble final deliverable\", \"status\": \"pending\", \"activeForm\": \"Assembling final deliverable\"}\n    ]\n})\n```\n\nMark each as `in_progress` when starting, `completed` when finished.\n\n## Exit Criteria\n\nBefore marking workflow complete:\n- [ ] All scope items analyzed\n- [ ] Evidence captured for each finding\n- [ ] Recommendations are actionable\n- [ ] Output follows format templates\n- [ ] Quality checklist satisfied\n\nFile v1.9.13:skill-card.md\n\n## Description: <br>\nOrchestrates multi-domain review across code, architecture, tests, and security in a single pass. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[athola](https://clawhub.ai/user/athola) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and engineering teams use this skill before merging major feature branches or broad changes to coordinate code, architecture, test, security, and quality reviews into one consolidated action plan. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The review workflow may automatically persist backlog findings through a local deferred-capture command. <br>\nMitigation: Review or disable the deferred-capture step before use on private, regulated, or security-sensitive code, and confirm where any backlog data is stored. <br>\nRisk: Broad review-related prompts may activate multi-domain review and dispatch multiple review agents. <br>\nMitigation: Confirm the intended review scope, selected review mode, and agent set before relying on results or applying follow-up changes. <br>\nRisk: Integrated review output can combine findings from multiple reviewers before each finding is independently verified. <br>\nMitigation: Require evidence-linked findings and human verification before changing code or promoting recommendations into release blockers. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/athola/skills/nm-pensive-unified-review) <br>\n- [Pensive plugin homepage](https://github.com/athola/claude-night-market/tree/master/plugins/pensive) <br>\n- [Review workflow core](modules/review-workflow-core.md) <br>\n- [Output format templates](modules/output-format-templates.md) <br>\n- [Quality checklist patterns](modules/quality-checklist-patterns.md) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, guidance] <br>\n**Output Format:** [Markdown review report with an executive summary, findings, action items, and evidence appendix; may include shell commands for deferred finding capture.] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Integrates selected domain-review results into prioritized recommendations and backlog capture guidance.] <br>\n\n## Skill Version(s): <br>\n1.9.13 (source: server release evidence; artifact frontmatter lists 1.9.8) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.9.12: 6 files, 10048 bytes\n\nFiles: modules/output-format-templates.md (3699b), modules/quality-checklist-patterns.md (3503b), modules/review-workflow-core.md (3203b), skill-card.md (1980b), SKILL.md (9230b), _meta.json (145b)\n\nFile v1.9.12:SKILL.md\n\n---\nname: unified-review\ndescription: Orchestrates multi-domain review (code, arch, tests, security) in a single pass\nversion: 1.9.8\ntriggers:\n  - review\n  - orchestration\n  - code-quality\n  - analysis\n  - multi-domain\n  - comprehensive pre-release review is needed\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/pensive\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.pensive:shared\", \"night-market.imbue:proof-of-work\", \"night-market.imbue:structured-output\"]}}}\nsource: claude-night-market\nsource_plugin: pensive\n---\n\n> **Night Market Skill** — ported from [claude-night-market/pensive](https://github.com/athola/claude-night-market/tree/master/plugins/pensive). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n## Table of Contents\n\n- [Quick Start](#quick-start)\n- [When to Use](#when-to-use)\n- [Review Skill Selection Matrix](#review-skill-selection-matrix)\n- [Workflow](#workflow)\n- [1. Analyze Repository Context](#1-analyze-repository-context)\n- [2. Select Review Skills](#2-select-review-skills)\n- [3. Execute Reviews](#3-execute-reviews)\n- [4. Integrate Findings](#4-integrate-findings)\n- [Review Modes](#review-modes)\n- [Auto-Detect (default)](#auto-detect-(default))\n- [Focused Mode](#focused-mode)\n- [Full Review Mode](#full-review-mode)\n- [Quality Gates](#quality-gates)\n- [Deliverables](#deliverables)\n- [Executive Summary](#executive-summary)\n- [Domain-Specific Reports](#domain-specific-reports)\n- [Integrated Action Plan](#integrated-action-plan)\n- [Modular Architecture](#modular-architecture)\n- [Exit Criteria](#exit-criteria)\n\n\n# Unified Review Orchestration\n\nIntelligently selects and executes appropriate review skills based on codebase analysis and context.\n\n## Quick Start\n\n```bash\n# Auto-detect and run appropriate reviews\n/full-review\n\n# Focus on specific areas\n/full-review api          # API surface review\n/full-review architecture # Architecture review\n/full-review bugs         # Bug hunting\n/full-review tests        # Test suite review\n/full-review all          # Run all applicable skills\n```\n**Verification:** Run `pytest -v` to verify tests pass.\n\n## When To Use\n\n- Starting a full code review\n- Reviewing changes across multiple domains\n- Need intelligent selection of review skills\n- Want integrated reporting from multiple review types\n- Before merging major feature branches\n\n## When NOT To Use\n\n- Specific review type known\n  - use bug-review\n- Test-review\n- Architecture-only focus - use\n  architecture-review\n- Specific review type known\n  - use bug-review\n\n## Review Skill Selection Matrix\n\n| Codebase Pattern | Review Skills | Triggers |\n|-----------------|---------------|----------|\n| Rust files (`*.rs`, `Cargo.toml`) | rust-review, bug-review, api-review | Rust project detected |\n| API changes (`openapi.yaml`, `routes/`) | api-review, architecture-review | Public API surfaces |\n| Test files (`test_*.py`, `*_test.go`) | test-review, bug-review | Test infrastructure |\n| Makefile/build system | makefile-review, architecture-review | Build complexity |\n| Mathematical algorithms | math-review, bug-review | Numerical computation |\n| Architecture docs/ADRs | architecture-review, api-review | System design |\n| General code quality | bug-review, test-review | Default review |\n| Post-implementation audit | imbue:justify | High add/delete ratio, test changes, new abstractions |\n\n## Workflow\n\n### 1. Analyze Repository Context\n- Detect primary languages from extensions and manifests\n- Analyze git status and diffs for change scope\n- Identify project structure (monorepo, microservices, library)\n- Detect build systems, testing frameworks, documentation\n\n### 2. Select Review Skills\n```python\n# Detection logic\nif has_rust_files():\n    schedule_skill(\"rust-review\")\nif has_api_changes():\n    schedule_skill(\"api-review\")\nif has_test_files():\n    schedule_skill(\"test-review\")\nif has_makefiles():\n    schedule_skill(\"makefile-review\")\nif has_math_code():\n    schedule_skill(\"math-review\")\nif has_architecture_changes():\n    schedule_skill(\"architecture-review\")\n# Default\nschedule_skill(\"bug-review\")\n```\n**Verification:** Run `pytest -v` to verify tests pass.\n\n### 3. Execute Reviews\n\nDispatch selected skills concurrently via the Agent tool.\nUse this mapping to resolve skill names to agent types:\n\n| Skill Name | Agent Type | Notes |\n|---|---|---|\n| bug-review | `pensive:code-reviewer` | Covers bugs, API, tests |\n| api-review | `pensive:code-reviewer` | Same agent, API focus |\n| test-review | `pensive:code-reviewer` | Same agent, test focus |\n| architecture-review | `pensive:architecture-reviewer` | ADR compliance |\n| rust-review | `pensive:rust-auditor` | Rust-specific |\n| code-refinement | `pensive:code-refiner` | Duplication, quality |\n| math-review | `general-purpose` | Prompt: invoke `Skill(pensive:math-review)` |\n| makefile-review | `general-purpose` | Prompt: invoke `Skill(pensive:makefile-review)` |\n| shell-review | `general-purpose` | Prompt: invoke `Skill(pensive:shell-review)` |\n\n**Sub-agent isolation (required):**\n\nDispatch ALL selected agents in a SINGLE parallel Agent tool\ncall. Do not read or process any agent's output until ALL agents\nhave returned their results. Reading the first result before the\nothers are in anchors synthesis toward that perspective — each\nsubsequent result gets evaluated against the first rather than\nindependently. Collect all results, then synthesize once.\n\n**Rules:**\n- Never use skill names as agent types (e.g., `pensive:math-review` is NOT an agent)\n- When `pensive:code-reviewer` covers multiple domains, dispatch once with combined scope\n- For skills without dedicated agents, use `general-purpose` and instruct it to invoke the Skill tool\n- Maintain consistent evidence logging across all agents\n- Track progress via TodoWrite\n\n### 4. Integrate Findings\n\n- Consolidate findings across domains\n- Identify cross-domain patterns\n- Prioritize by impact and effort\n- Generate unified action plan\n\n**Deferred capture for backlog findings:**\nFindings that are triaged to the backlog (out-of-scope for\nthe current review or deferred by the team) should be\npreserved so they are not lost between review cycles.\nFor each finding assigned to the backlog, run:\n\n```bash\npython3 scripts/deferred_capture.py \\\n  --title \"<finding title>\" \\\n  --source review \\\n  --context \"Review dimension: <dimension>. <finding description>\"\n```\n\nThe `<dimension>` value should match the review skill that\nsurfaced the finding (e.g. `bug-review`, `api-review`,\n`architecture-review`).\nThis runs automatically after the action plan is finalised,\nwithout prompting the user.\n\n## Review Modes\n\n### Auto-Detect (default)\nAutomatically selects skills based on codebase analysis.\n\n### Focused Mode\nRun specific review domains:\n- `/full-review api` → api-review only\n- `/full-review architecture` → architecture-review only\n- `/full-review bugs` → bug-review only\n- `/full-review tests` → test-review only\n\n### Full Review Mode\nRun all applicable review skills:\n- `/full-review all` → Execute all detected skills\n\n## Quality Gates\n\nEach review must:\n1. Establish proper context\n2. Execute all selected skills successfully\n3. Document findings with evidence\n4. Prioritize recommendations by impact\n5. Create action plan with owners\n\n## Deliverables\n\n### Executive Summary\n- Overall codebase health assessment\n- Critical issues requiring immediate attention\n- Review frequency recommendations\n\n### Domain-Specific Reports\n- API surface analysis and consistency\n- Architecture alignment with ADRs\n- Test coverage gaps and improvements\n- Bug analysis and security findings\n- Performance and maintainability recommendations\n\n### Integrated Action Plan\n- Prioritized remediation tasks\n- Cross-domain dependencies\n- Assigned owners and target dates\n- Follow-up review schedule\n\n## Modular Architecture\n\nAll review skills use a hub-and-spoke architecture with progressive loading:\n\n- **`pensive:shared`**: Common workflow, output templates, quality checklists\n- **Each skill has `modules/`**: Domain-specific details loaded on demand\n- **Cross-plugin deps**: `imbue:proof-of-work`, `imbue:diff-analysis/modules/risk-assessment-framework`\n\nThis reduces token usage by 50-70% for focused reviews while maintaining full capabilities.\n\n## Exit Criteria\n\n- All selected review skills executed\n- Findings consolidated and prioritized\n- Action plan created with ownership\n- Evidence logged per structured output format\n## Supporting Modules\n\n- [Review workflow core](modules/review-workflow-core.md) - standard 5-step workflow pattern for all pensive reviews\n- [Output format templates](modules/output-format-templates.md) - finding entry, severity, action item templates\n- [Quality checklist patterns](modules/quality-checklist-patterns.md) - pre-review, analysis, evidence, deliverable checklists\n\n## Troubleshooting\n\n### Common Issues\n\nIf the auto-detection fails to identify the correct review skills, explicitly specify the mode (e.g., `/full-review rust` instead of just `/full-review`). If integration fails, check that `TodoWrite` logs are accessible and that evidence files were correctly written by the individual skills.\n\nFile v1.9.12:_meta.json\n\n{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-pensive-unified-review\",\n  \"version\": \"1.9.12\",\n  \"publishedAt\": 1781839083335\n}\n\nFile v1.9.12:modules/output-format-templates.md\n\n---\nname: output-format-templates\ndescription: Standard output format templates for pensive review deliverables\nparent_skill: pensive:shared\ncategory: review-infrastructure\ntags: [templates, output, formatting, structure]\nreusable_by: [pensive:bug-review, pensive:api-review, pensive:architecture-review, pensive:test-review, pensive:rust-review, pensive:makefile-review, pensive:math-review, pensive:unified-review]\nestimated_tokens: 350\n---\n\n# Output Format Templates\n\nStandard templates for consistent review deliverables.\n\n## Top-Level Structure\n\n```markdown\n# [Review Type] Review: [Subject]\n\n## Executive Summary\n[High-level overview, key findings count, overall assessment]\n\n## Findings Summary\n[Count by severity: Critical, High, Medium, Low]\n\n## Detailed Findings\n[Organized by category or severity]\n\n## Action Items\n[Prioritized recommendations with owner and next step]\n\n## Evidence Appendix\n[Supporting code snippets, references, measurements]\n```\n\n## Finding Entry Template\n\n```markdown\n### [Category]: [Short Title]\n\n**Severity**: [Critical|High|Medium|Low]\n**Location**: [File path:line numbers or component name]\n**Category**: [Specific category from domain]\n\n**Issue**:\n[Clear description of what's wrong]\n\n**Evidence**:\n[Code snippet, measurement, or observation]\n\n**Why This Matters**:\n[The underlying principle or rule being violated.\nExplain the concept, not just the symptom.]\n\n**Proof**:\n[Link to authoritative best-practice documentation.\nPrefer: language docs, OWASP, PEPs, style guides,\nRFCs. Summarize what the link teaches.]\n\n**Teachable Moment**:\n[How this lesson generalizes beyond this specific\nfinding. When else would this principle apply?]\n\n**Recommendation**:\n[Specific steps to resolve, with concrete next action]\n\n**References**: [Evidence appendix section or external docs]\n```\n\n### Educational Depth by Severity\n\n| Severity | Why | Proof Link | Teachable Moment |\n|----------|-----|------------|------------------|\n| Critical | Required | Required | Required |\n| High | Required | Required | Required |\n| Medium | Required | If available | Optional |\n| Low | Brief | Optional | Optional |\n\n## Severity Definitions\n\n**Critical**: Security vulnerability, data loss risk, system failure potential\n**High**: Significant functionality issues, major violations, substantial technical debt\n**Medium**: Moderate violations, code quality issues, maintainability concerns\n**Low**: Minor style issues, optimization opportunities, documentation gaps\n\n## Action Items Template\n\n```markdown\n## Action Items\n\n### Immediate (Critical/High Severity)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n\n### Short-term (Medium Severity)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n\n### Long-term (Low Severity / Improvements)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n```\n\n## Evidence Appendix Template\n\n```markdown\n## Evidence Appendix\n\n### E1: [Short Reference Name]\n**Related to**: Finding [X]\n**File**: `/path/to/file.ext:lines`\n\n```[language]\n[code snippet or measurement]\n```\n\n**Context**: [Why this evidence matters]\n\n---\n\n### E2: [Next Reference]\n...\n```\n\n## Summary Statistics Template\n\n```markdown\n## Review Statistics\n\n- **Total Items Reviewed**: [count]\n- **Findings by Severity**:\n  - Critical: [count]\n  - High: [count]\n  - Medium: [count]\n  - Low: [count]\n- **Categories Analyzed**: [list]\n- **Recommendations**: [count]\n```\n\n## Usage Notes\n\n1. Adapt section headings to domain (e.g., \"Endpoints\" for API, \"Components\" for architecture)\n2. Always link findings to evidence\n3. Keep Executive Summary under 5 sentences\n4. validate every finding has a concrete next step\n5. Use consistent severity assessment across entire review\n\nFile v1.9.12:modules/quality-checklist-patterns.md\n\n---\nname: quality-checklist-patterns\ndescription: Reusable quality checklist patterns for review validation\nparent_skill: pensive:shared\ncategory: review-infrastructure\ntags: [quality, checklist, validation, completeness]\nreusable_by: [pensive:bug-review, pensive:api-review, pensive:architecture-review, pensive:test-review, pensive:rust-review, pensive:makefile-review, pensive:math-review, pensive:unified-review]\nestimated_tokens: 300\n---\n\n# Quality Checklist Patterns\n\nStandard quality assurance checklists for review deliverables.\n\n## Pre-Review Checklist\n\nExecute before starting analysis:\n\n- [ ] Scope clearly defined and documented\n- [ ] Review criteria identified (use domain-specific patterns)\n- [ ] Success criteria established\n- [ ] Evidence logging strategy prepared\n- [ ] Output template selected and customized\n\n## Analysis Quality Checklist\n\nExecute during deep analysis phase:\n\n- [ ] All scope items examined\n- [ ] Domain-specific criteria applied consistently\n- [ ] Severity assessed using standard definitions\n- [ ] Patterns and anti-patterns identified\n- [ ] Cross-references validated\n- [ ] Edge cases considered\n\n## Evidence Quality Checklist\n\nExecute during evidence capture:\n\n- [ ] Every finding has supporting evidence\n- [ ] File paths and line numbers included\n- [ ] Code snippets are minimal and focused\n- [ ] Context preserved for each evidence item\n- [ ] Evidence appendix organized and referenced\n- [ ] Reasoning chains documented\n\n## Deliverable Completeness Checklist\n\nExecute before finalizing output:\n\n- [ ] Executive summary present and concise\n- [ ] All findings documented with required fields:\n  - [ ] Severity assigned\n  - [ ] Location specified\n  - [ ] Category identified\n  - [ ] Issue described\n  - [ ] Evidence provided\n  - [ ] Impact explained\n  - [ ] Recommendation actionable\n- [ ] Action items prioritized by severity\n- [ ] Evidence appendix complete\n- [ ] Summary statistics included\n- [ ] Output follows template structure\n\n## Recommendation Quality Checklist\n\nExecute for each recommendation:\n\n- [ ] Specific and actionable\n- [ ] Addresses root cause, not just symptoms\n- [ ] Feasible within project constraints\n- [ ] Prioritized appropriately\n- [ ] Linked to finding\n- [ ] Includes rationale\n\n## Review Consistency Checklist\n\nExecute before final delivery:\n\n- [ ] Severity levels applied consistently\n- [ ] Terminology used consistently\n- [ ] Categories align with domain standards\n- [ ] Similar issues grouped appropriately\n- [ ] No contradictory recommendations\n- [ ] Style and tone professional throughout\n\n## Exit Criteria Validation\n\nFinal check before completion:\n\n- [ ] All TodoWrite items marked complete\n- [ ] Workflow steps executed in sequence\n- [ ] Quality checklists satisfied\n- [ ] Output validated against template\n- [ ] Evidence complete and linked\n- [ ] Deliverable ready for stakeholder review\n\n## Usage Pattern\n\nIntegrate into Step 5 (Deliverable Assembly) of review workflow:\n\n```python\n# Before marking final todo as complete\nprint(\"Validating deliverable quality...\")\n# Run through Deliverable Completeness Checklist\n# Run through Review Consistency Checklist\n# Run through Exit Criteria Validation\n# Only then mark todo complete\n```\n\n## Customization\n\nDomain-specific reviews may extend these checklists with:\n- Additional domain criteria (e.g., security-specific checks)\n- Tool-specific validation (e.g., linter results)\n- Compliance requirements (e.g., regulatory standards)\n\nExtend, don't replace, these baseline checklists.\n\nFile v1.9.12:modules/review-workflow-core.md\n\n---\nname: review-workflow-core\ndescription: Core workflow patterns for all pensive review skills\nparent_skill: pensive:shared\ncategory: review-infrastructure\ntags: [workflow, core, review, patterns]\nreusable_by: [pensive:bug-review, pensive:api-review, pensive:architecture-review, pensive:test-review, pensive:rust-review, pensive:makefile-review, pensive:math-review, pensive:unified-review]\nestimated_tokens: 400\n---\n\n# Review Workflow Core\n\nStandard 5-step workflow pattern for all pensive review skills.\n\n## Workflow Structure\n\n### Step 1: Context Establishment\n**TodoWrite Item**: \"Establishing review context\"\n\nActions:\n1. Identify review scope and boundaries\n2. Gather relevant files and documentation\n3. Establish success criteria\n4. Load domain-specific patterns (if applicable)\n\n**Output**: Context summary with scope definition\n\n### Step 2: Scope Inventory\n**TodoWrite Item**: \"Creating scope inventory\"\n\nActions:\n1. Catalog all items to review (files, components, endpoints, etc.)\n2. Categorize by type, complexity, or domain area\n3. Prioritize based on risk, complexity, or impact\n4. Create initial structure for findings\n\n**Output**: Structured inventory with categories\n\n### Step 3: Deep Analysis\n**TodoWrite Item**: \"Performing deep analysis\"\n\nActions:\n1. Apply domain-specific review criteria\n2. Identify patterns, anti-patterns, violations\n3. Assess severity (Critical, High, Medium, Low)\n4. Cross-reference with best practices\n5. Capture evidence for each finding\n\n**Output**: Detailed findings with evidence\n\n### Step 4: Evidence Capture\n**TodoWrite Item**: \"Capturing evidence\"\n\nIntegration with `imbue:proof-of-work`:\n1. Document code snippets with file paths and line numbers\n2. Record reasoning chains for conclusions\n3. Link findings to specific violations or patterns\n4. Preserve context for future reference\n\n**Output**: Evidence appendix linked to findings\n\n### Step 5: Deliverable Assembly\n**TodoWrite Item**: \"Assembling final deliverable\"\n\nActions:\n1. Structure findings by severity and category\n2. Format recommendations with actionable steps\n3. Create prioritized action items\n4. Validate completeness against exit criteria\n5. Generate final output using templates\n\n**Output**: Complete review deliverable\n\n## TodoWrite Integration\n\nCreate tasks at workflow start:\n\n```python\nTodoWrite({\n    \"todos\": [\n        {\"content\": \"Establish review context\", \"status\": \"pending\", \"activeForm\": \"Establishing review context\"},\n        {\"content\": \"Create scope inventory\", \"status\": \"pending\", \"activeForm\": \"Creating scope inventory\"},\n        {\"content\": \"Perform deep analysis\", \"status\": \"pending\", \"activeForm\": \"Performing deep analysis\"},\n        {\"content\": \"Capture evidence\", \"status\": \"pending\", \"activeForm\": \"Capturing evidence\"},\n        {\"content\": \"Assemble final deliverable\", \"status\": \"pending\", \"activeForm\": \"Assembling final deliverable\"}\n    ]\n})\n```\n\nMark each as `in_progress` when starting, `completed` when finished.\n\n## Exit Criteria\n\nBefore marking workflow complete:\n- [ ] All scope items analyzed\n- [ ] Evidence captured for each finding\n- [ ] Recommendations are actionable\n- [ ] Output follows format templates\n- [ ] Quality checklist satisfied\n\nFile v1.9.12:skill-card.md\n\n## Description: <br>\nOrchestrates multi-domain review (code, architecture, tests, security) in a single pass. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[athola](https://clawhub.ai/user/athola) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and maintainers use this skill to run a unified review across code, architecture, tests, security, and related domains, then consolidate findings into summaries, domain reports, and prioritized action plans. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill may automatically run a local deferred-capture script that stores review-derived details from the reviewed workspace. <br>\nMitigation: Inspect or disable that script path before use, invoke the skill explicitly, and avoid using it on repositories with secrets or sensitive internal findings unless backlog storage is controlled. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/athola/nm-pensive-unified-review) <br>\n- [Pensive plugin homepage](https://github.com/athola/claude-night-market/tree/master/plugins/pensive) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, Markdown, Shell commands, Guidance] <br>\n**Output Format:** [Markdown review reports with findings, evidence, summaries, and prioritized action items.] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May coordinate multiple review domains and include evidence appendices; backlog capture behavior should be reviewed before use.] <br>\n\n## Skill Version(s): <br>\n1.9.12 (source: server release evidence; artifact frontmatter says 1.9.8) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.3: 6 files, 10106 bytes\n\nFiles: modules/output-format-templates.md (3699b), modules/quality-checklist-patterns.md (3503b), modules/review-workflow-core.md (3203b), skill-card.md (2112b), SKILL.md (9230b), _meta.json (144b)\n\nFile v1.0.3:SKILL.md\n\n---\nname: unified-review\ndescription: Orchestrates multi-domain review (code, arch, tests, security) in a single pass\nversion: 1.9.8\ntriggers:\n  - review\n  - orchestration\n  - code-quality\n  - analysis\n  - multi-domain\n  - comprehensive pre-release review is needed\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/pensive\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.pensive:shared\", \"night-market.imbue:proof-of-work\", \"night-market.imbue:structured-output\"]}}}\nsource: claude-night-market\nsource_plugin: pensive\n---\n\n> **Night Market Skill** — ported from [claude-night-market/pensive](https://github.com/athola/claude-night-market/tree/master/plugins/pensive). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n## Table of Contents\n\n- [Quick Start](#quick-start)\n- [When to Use](#when-to-use)\n- [Review Skill Selection Matrix](#review-skill-selection-matrix)\n- [Workflow](#workflow)\n- [1. Analyze Repository Context](#1-analyze-repository-context)\n- [2. Select Review Skills](#2-select-review-skills)\n- [3. Execute Reviews](#3-execute-reviews)\n- [4. Integrate Findings](#4-integrate-findings)\n- [Review Modes](#review-modes)\n- [Auto-Detect (default)](#auto-detect-(default))\n- [Focused Mode](#focused-mode)\n- [Full Review Mode](#full-review-mode)\n- [Quality Gates](#quality-gates)\n- [Deliverables](#deliverables)\n- [Executive Summary](#executive-summary)\n- [Domain-Specific Reports](#domain-specific-reports)\n- [Integrated Action Plan](#integrated-action-plan)\n- [Modular Architecture](#modular-architecture)\n- [Exit Criteria](#exit-criteria)\n\n\n# Unified Review Orchestration\n\nIntelligently selects and executes appropriate review skills based on codebase analysis and context.\n\n## Quick Start\n\n```bash\n# Auto-detect and run appropriate reviews\n/full-review\n\n# Focus on specific areas\n/full-review api          # API surface review\n/full-review architecture # Architecture review\n/full-review bugs         # Bug hunting\n/full-review tests        # Test suite review\n/full-review all          # Run all applicable skills\n```\n**Verification:** Run `pytest -v` to verify tests pass.\n\n## When To Use\n\n- Starting a full code review\n- Reviewing changes across multiple domains\n- Need intelligent selection of review skills\n- Want integrated reporting from multiple review types\n- Before merging major feature branches\n\n## When NOT To Use\n\n- Specific review type known\n  - use bug-review\n- Test-review\n- Architecture-only focus - use\n  architecture-review\n- Specific review type known\n  - use bug-review\n\n## Review Skill Selection Matrix\n\n| Codebase Pattern | Review Skills | Triggers |\n|-----------------|---------------|----------|\n| Rust files (`*.rs`, `Cargo.toml`) | rust-review, bug-review, api-review | Rust project detected |\n| API changes (`openapi.yaml`, `routes/`) | api-review, architecture-review | Public API surfaces |\n| Test files (`test_*.py`, `*_test.go`) | test-review, bug-review | Test infrastructure |\n| Makefile/build system | makefile-review, architecture-review | Build complexity |\n| Mathematical algorithms | math-review, bug-review | Numerical computation |\n| Architecture docs/ADRs | architecture-review, api-review | System design |\n| General code quality | bug-review, test-review | Default review |\n| Post-implementation audit | imbue:justify | High add/delete ratio, test changes, new abstractions |\n\n## Workflow\n\n### 1. Analyze Repository Context\n- Detect primary languages from extensions and manifests\n- Analyze git status and diffs for change scope\n- Identify project structure (monorepo, microservices, library)\n- Detect build systems, testing frameworks, documentation\n\n### 2. Select Review Skills\n```python\n# Detection logic\nif has_rust_files():\n    schedule_skill(\"rust-review\")\nif has_api_changes():\n    schedule_skill(\"api-review\")\nif has_test_files():\n    schedule_skill(\"test-review\")\nif has_makefiles():\n    schedule_skill(\"makefile-review\")\nif has_math_code():\n    schedule_skill(\"math-review\")\nif has_architecture_changes():\n    schedule_skill(\"architecture-review\")\n# Default\nschedule_skill(\"bug-review\")\n```\n**Verification:** Run `pytest -v` to verify tests pass.\n\n### 3. Execute Reviews\n\nDispatch selected skills concurrently via the Agent tool.\nUse this mapping to resolve skill names to agent types:\n\n| Skill Name | Agent Type | Notes |\n|---|---|---|\n| bug-review | `pensive:code-reviewer` | Covers bugs, API, tests |\n| api-review | `pensive:code-reviewer` | Same agent, API focus |\n| test-review | `pensive:code-reviewer` | Same agent, test focus |\n| architecture-review | `pensive:architecture-reviewer` | ADR compliance |\n| rust-review | `pensive:rust-auditor` | Rust-specific |\n| code-refinement | `pensive:code-refiner` | Duplication, quality |\n| math-review | `general-purpose` | Prompt: invoke `Skill(pensive:math-review)` |\n| makefile-review | `general-purpose` | Prompt: invoke `Skill(pensive:makefile-review)` |\n| shell-review | `general-purpose` | Prompt: invoke `Skill(pensive:shell-review)` |\n\n**Sub-agent isolation (required):**\n\nDispatch ALL selected agents in a SINGLE parallel Agent tool\ncall. Do not read or process any agent's output until ALL agents\nhave returned their results. Reading the first result before the\nothers are in anchors synthesis toward that perspective — each\nsubsequent result gets evaluated against the first rather than\nindependently. Collect all results, then synthesize once.\n\n**Rules:**\n- Never use skill names as agent types (e.g., `pensive:math-review` is NOT an agent)\n- When `pensive:code-reviewer` covers multiple domains, dispatch once with combined scope\n- For skills without dedicated agents, use `general-purpose` and instruct it to invoke the Skill tool\n- Maintain consistent evidence logging across all agents\n- Track progress via TodoWrite\n\n### 4. Integrate Findings\n\n- Consolidate findings across domains\n- Identify cross-domain patterns\n- Prioritize by impact and effort\n- Generate unified action plan\n\n**Deferred capture for backlog findings:**\nFindings that are triaged to the backlog (out-of-scope for\nthe current review or deferred by the team) should be\npreserved so they are not lost between review cycles.\nFor each finding assigned to the backlog, run:\n\n```bash\npython3 scripts/deferred_capture.py \\\n  --title \"<finding title>\" \\\n  --source review \\\n  --context \"Review dimension: <dimension>. <finding description>\"\n```\n\nThe `<dimension>` value should match the review skill that\nsurfaced the finding (e.g. `bug-review`, `api-review`,\n`architecture-review`).\nThis runs automatically after the action plan is finalised,\nwithout prompting the user.\n\n## Review Modes\n\n### Auto-Detect (default)\nAutomatically selects skills based on codebase analysis.\n\n### Focused Mode\nRun specific review domains:\n- `/full-review api` → api-review only\n- `/full-review architecture` → architecture-review only\n- `/full-review bugs` → bug-review only\n- `/full-review tests` → test-review only\n\n### Full Review Mode\nRun all applicable review skills:\n- `/full-review all` → Execute all detected skills\n\n## Quality Gates\n\nEach review must:\n1. Establish proper context\n2. Execute all selected skills successfully\n3. Document findings with evidence\n4. Prioritize recommendations by impact\n5. Create action plan with owners\n\n## Deliverables\n\n### Executive Summary\n- Overall codebase health assessment\n- Critical issues requiring immediate attention\n- Review frequency recommendations\n\n### Domain-Specific Reports\n- API surface analysis and consistency\n- Architecture alignment with ADRs\n- Test coverage gaps and improvements\n- Bug analysis and security findings\n- Performance and maintainability recommendations\n\n### Integrated Action Plan\n- Prioritized remediation tasks\n- Cross-domain dependencies\n- Assigned owners and target dates\n- Follow-up review schedule\n\n## Modular Architecture\n\nAll review skills use a hub-and-spoke architecture with progressive loading:\n\n- **`pensive:shared`**: Common workflow, output templates, quality checklists\n- **Each skill has `modules/`**: Domain-specific details loaded on demand\n- **Cross-plugin deps**: `imbue:proof\n\nArchive v1.0.2: 6 files, 9746 bytes\n\nFiles: modules/output-format-templates.md (3676b), modules/quality-checklist-patterns.md (3503b), modules/review-workflow-core.md (3203b), skill-card.md (2006b), SKILL.md (8684b), _meta.json (144b)\n\nArchive v1.0.1: 5 files, 8616 bytes\n\nFiles: modules/output-format-templates.md (3676b), modules/quality-checklist-patterns.md (3503b), modules/review-workflow-core.md (3203b), SKILL.md (8684b), _meta.json (144b)\n\nArchive v1.0.0: 5 files, 8616 bytes\n\nFiles: modules/output-format-templates.md (3676b), modules/quality-checklist-patterns.md (3503b), modules/review-workflow-core.md (3203b), SKILL.md (8684b), _meta.json (144b)","readmeExcerpt":"Skill: unified-review Owner: athola Summary: Orchestrates multi-domain review (code, arch, tests, security) in a single pass Tags: latest:1.9.19 Version history: v1.9.19 | 2026-08-26T13:19:45.599Z | user Release v1.9.19 v1.9.17 | 2026-07-30T05:39:54.341Z | user Release v1.9.17 v1.9.16 | 2026-07-14T19:56:41.998Z | user Release v1.9.16 v1.9.14 | 2026-06-30T18:04:50.733Z | user Release v1.9.14 v1.9.13 | 2026-06-27T16:22","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"# Auto-detect and run appropriate reviews\n/full-review\n\n# Focus on specific areas\n/full-review api          # API surface review\n/full-review architecture # Architecture review\n/full-review bugs         # Bug hunting\n/full-review tests        # Test suite review\n/full-review all          # Run all applicable skills"},{"language":"python","snippet":"# Detection logic\nif has_rust_files():\n    schedule_skill(\"rust-review\")\nif has_api_changes():\n    schedule_skill(\"api-review\")\nif has_test_files():\n    schedule_skill(\"test-review\")\nif has_makefiles():\n    schedule_skill(\"makefile-review\")\nif has_math_code():\n    schedule_skill(\"math-review\")\nif has_architecture_changes():\n    schedule_skill(\"architecture-review\")\n# Default\nschedule_skill(\"bug-review\")"},{"language":"bash","snippet":"python3 scripts/deferred_capture.py \\\n  --title \"<finding title>\" \\\n  --source review \\\n  --context \"Review dimension: <dimension>. <finding description>\""},{"language":"markdown","snippet":"# [Review Type] Review: [Subject]\n\n## Executive Summary\n[High-level overview, key findings count, overall assessment]\n\n## Findings Summary\n[Count by severity: Critical, High, Medium, Low]\n\n## Detailed Findings\n[Organized by category or severity]\n\n## Action Items\n[Prioritized recommendations with owner and next step]\n\n## Evidence Appendix\n[Supporting code snippets, references, measurements]"},{"language":"markdown","snippet":"### [Category]: [Short Title]\n\n**Severity**: [Critical|High|Medium|Low]\n**Location**: [File path:line numbers or component name]\n**Category**: [Specific category from domain]\n\n**Issue**:\n[Clear description of what's wrong]\n\n**Evidence**:\n[Code snippet, measurement, or observation]\n\n**Why This Matters**:\n[The underlying principle or rule being violated.\nExplain the concept, not just the symptom.]\n\n**Proof**:\n[Link to authoritative best-practice documentation.\nPrefer: language docs, OWASP, PEPs, style guides,\nRFCs. Summarize what the link teaches.]\n\n**Teachable Moment**:\n[How this lesson generalizes beyond this specific\nfinding. When else would this principle apply?]\n\n**Recommendation**:\n[Specific steps to resolve, with concrete next action]\n\n**References**: [Evidence appendix section or external docs]"},{"language":"markdown","snippet":"## Action Items\n\n### Immediate (Critical/High Severity)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n\n### Short-term (Medium Severity)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n\n### Long-term (Low Severity / Improvements)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ..."}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: unified-review\ndescription: Orchestrates multi-domain review (code, arch, tests, security) in a single pass\nversion: 1.9.8\ntriggers:\n  - review\n  - orchestration\n  - code-quality\n  - analysis\n  - multi-domain\n  - comprehensive pre-release review is needed\nmetadata: {\"openclaw\": {\"homepage\": \"https://github.com/athola/claude-night-market/tree/master/plugins/pensive\", \"emoji\": \"\\ud83e\\udd9e\", \"requires\": {\"config\": [\"night-market.pensive:shared\", \"night-market.imbue:proof-of-work\", \"night-market.imbue:structured-output\"]}}}\nsource: claude-night-market\nsource_plugin: pensive\n---\n\n> **Night Market Skill** — ported from [claude-night-market/pensive](https://github.com/athola/claude-night-market/tree/master/plugins/pensive). For the full experience with agents, hooks, and commands, install the Claude Code plugin.\n\n\n## Table of Contents\n\n- [Quick Start](#quick-start)\n- [When to Use](#when-to-use)\n- [Review Skill Selection Matrix](#review-skill-selection-matrix)\n- [Workflow](#workflow)\n- [1. Analyze Repository Context](#1-analyze-repository-context)\n- [2. Select Review Skills](#2-select-review-skills)\n- [3. Execute Reviews](#3-execute-reviews)\n- [4. Integrate Findings](#4-integrate-findings)\n- [Review Modes](#review-modes)\n- [Auto-Detect (default)](#auto-detect-(default))\n- [Focused Mode](#focused-mode)\n- [Full Review Mode](#full-review-mode)\n- [Quality Gates](#quality-gates)\n- [Deliverables](#deliverables)\n- [Executive Summary](#executive-summary)\n- [Domain-Specific Reports](#domain-specific-reports)\n- [Integrated Action Plan](#integrated-action-plan)\n- [Modular Architecture](#modular-architecture)\n- [Exit Criteria](#exit-criteria)\n\n\n# Unified Review Orchestration\n\nIntelligently selects and executes appropriate review skills based on codebase analysis and context.\n\n## Quick Start\n\n```bash\n# Auto-detect and run appropriate reviews\n/full-review\n\n# Focus on specific areas\n/full-review api          # API surface review\n/full-review architecture # Architecture review\n/full-review bugs         # Bug hunting\n/full-review tests        # Test suite review\n/full-review all          # Run all applicable skills\n```\n**Verification:** Run `pytest -v` to verify tests pass.\n\n## When To Use\n\n- Starting a full code review\n- Reviewing changes across multiple domains\n- Need intelligent selection of review skills\n- Want integrated reporting from multiple review types\n- Before merging major feature branches\n\n## When NOT To Use\n\n- Specific review type known\n  - use bug-review\n- Test-review\n- Architecture-only focus - use\n  architecture-review\n- Specific review type known\n  - use bug-review\n\n## Review Skill Selection Matrix\n\n| Codebase Pattern | Review Skills | Triggers |\n|-----------------|---------------|----------|\n| Rust files (`*.rs`, `Cargo.toml`) | rust-review, bug-review, api-review | Rust project detected |\n| API changes (`openapi.yaml`, `routes/`) | api-review, architecture-review | Public API surfaces |\n| Test files (`test_*.py`, `*_test.go`) | test-review"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7d107jg9jv602h9ytsegydq184a42s\",\n  \"slug\": \"nm-pensive-unified-review\",\n  \"version\": \"1.9.19\",\n  \"publishedAt\": 1787750385599\n}"},{"path":"modules/output-format-templates.md","content":"---\nname: output-format-templates\ndescription: Standard output format templates for pensive review deliverables\nparent_skill: pensive:shared\ncategory: review-infrastructure\ntags: [templates, output, formatting, structure]\nreusable_by: [pensive:bug-review, pensive:api-review, pensive:architecture-review, pensive:test-review, pensive:rust-review, pensive:makefile-review, pensive:math-review, pensive:unified-review]\nestimated_tokens: 350\n---\n\n# Output Format Templates\n\nStandard templates for consistent review deliverables.\n\n## Top-Level Structure\n\n```markdown\n# [Review Type] Review: [Subject]\n\n## Executive Summary\n[High-level overview, key findings count, overall assessment]\n\n## Findings Summary\n[Count by severity: Critical, High, Medium, Low]\n\n## Detailed Findings\n[Organized by category or severity]\n\n## Action Items\n[Prioritized recommendations with owner and next step]\n\n## Evidence Appendix\n[Supporting code snippets, references, measurements]\n```\n\n## Finding Entry Template\n\n```markdown\n### [Category]: [Short Title]\n\n**Severity**: [Critical|High|Medium|Low]\n**Location**: [File path:line numbers or component name]\n**Category**: [Specific category from domain]\n\n**Issue**:\n[Clear description of what's wrong]\n\n**Evidence**:\n[Code snippet, measurement, or observation]\n\n**Why This Matters**:\n[The underlying principle or rule being violated.\nExplain the concept, not just the symptom.]\n\n**Proof**:\n[Link to authoritative best-practice documentation.\nPrefer: language docs, OWASP, PEPs, style guides,\nRFCs. Summarize what the link teaches.]\n\n**Teachable Moment**:\n[How this lesson generalizes beyond this specific\nfinding. When else would this principle apply?]\n\n**Recommendation**:\n[Specific steps to resolve, with concrete next action]\n\n**References**: [Evidence appendix section or external docs]\n```\n\n### Educational Depth by Severity\n\n| Severity | Why | Proof Link | Teachable Moment |\n|----------|-----|------------|------------------|\n| Critical | Required | Required | Required |\n| High | Required | Required | Required |\n| Medium | Required | If available | Optional |\n| Low | Brief | Optional | Optional |\n\n## Severity Definitions\n\n**Critical**: Security vulnerability, data loss risk, system failure potential\n**High**: Significant functionality issues, major violations, substantial technical debt\n**Medium**: Moderate violations, code quality issues, maintainability concerns\n**Low**: Minor style issues, optimization opportunities, documentation gaps\n\n## Action Items Template\n\n```markdown\n## Action Items\n\n### Immediate (Critical/High Severity)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n\n### Short-term (Medium Severity)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n\n### Long-term (Low Severity / Improvements)\n1. [Action] - [Rationale] - [Reference to finding]\n2. ...\n```\n\n## Evidence Appendix Template\n\n```markdown\n## Evidence Appendix\n\n### E1: [Short Reference Name]\n**Related to**: Finding [X]\n**File**: `/path/to/file.ext:lines`\n\n```[langu"},{"path":"modules/quality-checklist-patterns.md","content":"---\nname: quality-checklist-patterns\ndescription: Reusable quality checklist patterns for review validation\nparent_skill: pensive:shared\ncategory: review-infrastructure\ntags: [quality, checklist, validation, completeness]\nreusable_by: [pensive:bug-review, pensive:api-review, pensive:architecture-review, pensive:test-review, pensive:rust-review, pensive:makefile-review, pensive:math-review, pensive:unified-review]\nestimated_tokens: 300\n---\n\n# Quality Checklist Patterns\n\nStandard quality assurance checklists for review deliverables.\n\n## Pre-Review Checklist\n\nExecute before starting analysis:\n\n- [ ] Scope clearly defined and documented\n- [ ] Review criteria identified (use domain-specific patterns)\n- [ ] Success criteria established\n- [ ] Evidence logging strategy prepared\n- [ ] Output template selected and customized\n\n## Analysis Quality Checklist\n\nExecute during deep analysis phase:\n\n- [ ] All scope items examined\n- [ ] Domain-specific criteria applied consistently\n- [ ] Severity assessed using standard definitions\n- [ ] Patterns and anti-patterns identified\n- [ ] Cross-references validated\n- [ ] Edge cases considered\n\n## Evidence Quality Checklist\n\nExecute during evidence capture:\n\n- [ ] Every finding has supporting evidence\n- [ ] File paths and line numbers included\n- [ ] Code snippets are minimal and focused\n- [ ] Context preserved for each evidence item\n- [ ] Evidence appendix organized and referenced\n- [ ] Reasoning chains documented\n\n## Deliverable Completeness Checklist\n\nExecute before finalizing output:\n\n- [ ] Executive summary present and concise\n- [ ] All findings documented with required fields:\n  - [ ] Severity assigned\n  - [ ] Location specified\n  - [ ] Category identified\n  - [ ] Issue described\n  - [ ] Evidence provided\n  - [ ] Impact explained\n  - [ ] Recommendation actionable\n- [ ] Action items prioritized by severity\n- [ ] Evidence appendix complete\n- [ ] Summary statistics included\n- [ ] Output follows template structure\n\n## Recommendation Quality Checklist\n\nExecute for each recommendation:\n\n- [ ] Specific and actionable\n- [ ] Addresses root cause, not just symptoms\n- [ ] Feasible within project constraints\n- [ ] Prioritized appropriately\n- [ ] Linked to finding\n- [ ] Includes rationale\n\n## Review Consistency Checklist\n\nExecute before final delivery:\n\n- [ ] Severity levels applied consistently\n- [ ] Terminology used consistently\n- [ ] Categories align with domain standards\n- [ ] Similar issues grouped appropriately\n- [ ] No contradictory recommendations\n- [ ] Style and tone professional throughout\n\n## Exit Criteria Validation\n\nFinal check before completion:\n\n- [ ] All TodoWrite items marked complete\n- [ ] Workflow steps executed in sequence\n- [ ] Quality checklists satisfied\n- [ ] Output validated against template\n- [ ] Evidence complete and linked\n- [ ] Deliverable ready for stakeholder review\n\n## Usage Pattern\n\nIntegrate into Step 5 (Deliverable Assembly) of review workflow:\n\n```python\n# Before marking final todo as complete\np"},{"path":"modules/review-workflow-core.md","content":"---\nname: review-workflow-core\ndescription: Core workflow patterns for all pensive review skills\nparent_skill: pensive:shared\ncategory: review-infrastructure\ntags: [workflow, core, review, patterns]\nreusable_by: [pensive:bug-review, pensive:api-review, pensive:architecture-review, pensive:test-review, pensive:rust-review, pensive:makefile-review, pensive:math-review, pensive:unified-review]\nestimated_tokens: 400\n---\n\n# Review Workflow Core\n\nStandard 5-step workflow pattern for all pensive review skills.\n\n## Workflow Structure\n\n### Step 1: Context Establishment\n**TodoWrite Item**: \"Establishing review context\"\n\nActions:\n1. Identify review scope and boundaries\n2. Gather relevant files and documentation\n3. Establish success criteria\n4. Load domain-specific patterns (if applicable)\n\n**Output**: Context summary with scope definition\n\n### Step 2: Scope Inventory\n**TodoWrite Item**: \"Creating scope inventory\"\n\nActions:\n1. Catalog all items to review (files, components, endpoints, etc.)\n2. Categorize by type, complexity, or domain area\n3. Prioritize based on risk, complexity, or impact\n4. Create initial structure for findings\n\n**Output**: Structured inventory with categories\n\n### Step 3: Deep Analysis\n**TodoWrite Item**: \"Performing deep analysis\"\n\nActions:\n1. Apply domain-specific review criteria\n2. Identify patterns, anti-patterns, violations\n3. Assess severity (Critical, High, Medium, Low)\n4. Cross-reference with best practices\n5. Capture evidence for each finding\n\n**Output**: Detailed findings with evidence\n\n### Step 4: Evidence Capture\n**TodoWrite Item**: \"Capturing evidence\"\n\nIntegration with `imbue:proof-of-work`:\n1. Document code snippets with file paths and line numbers\n2. Record reasoning chains for conclusions\n3. Link findings to specific violations or patterns\n4. Preserve context for future reference\n\n**Output**: Evidence appendix linked to findings\n\n### Step 5: Deliverable Assembly\n**TodoWrite Item**: \"Assembling final deliverable\"\n\nActions:\n1. Structure findings by severity and category\n2. Format recommendations with actionable steps\n3. Create prioritized action items\n4. Validate completeness against exit criteria\n5. Generate final output using templates\n\n**Output**: Complete review deliverable\n\n## TodoWrite Integration\n\nCreate tasks at workflow start:\n\n```python\nTodoWrite({\n    \"todos\": [\n        {\"content\": \"Establish review context\", \"status\": \"pending\", \"activeForm\": \"Establishing review context\"},\n        {\"content\": \"Create scope inventory\", \"status\": \"pending\", \"activeForm\": \"Creating scope inventory\"},\n        {\"content\": \"Perform deep analysis\", \"status\": \"pending\", \"activeForm\": \"Performing deep analysis\"},\n        {\"content\": \"Capture evidence\", \"status\": \"pending\", \"activeForm\": \"Capturing evidence\"},\n        {\"content\": \"Assemble final deliverable\", \"status\": \"pending\", \"activeForm\": \"Assembling final deliverable\"}\n    ]\n})\n```\n\nMark each as `in_progress` when starting, `completed` when finished.\n\n## Exit Criteria\n\nBefore marki"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Orchestrates multi-domain review (code, arch, tests, security) in a single pass Skill: unified-review Owner: athola Summary: Orchestrates multi-domain review (code, arch, tests, security) in a single pass Tags: latest:1.9.19 Version history: v1.9.19 | 2026-08-26T13:19:45.599Z | user Release v1.9.19 v1.9.17 | 2026-07-30T05:39:54.341Z | user Release v1.9.17 v1.9.16 | 2026-07-14T19:56:41.998Z | user Release v1.9.16 v1.9.14 | 2026-06-30T18:04:50.733Z | user Release v1.9.14 v1.9.13 | 2026-06-27T16:22","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1222,"uniquenessScore":52,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T12:13:00.818Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-10T12:13:00.818Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-10T14:47:57.613Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}