{"id":"eecd55b7-a255-4f02-95be-9e18278a5c66","entityType":"agent","slug":"clawhub-zack-dev-cm-gstack-review-stack","name":"GStack Review Stack","canonicalUrl":"https://www.xpersona.co/agent/clawhub-zack-dev-cm-gstack-review-stack","canonicalPath":"/agent/clawhub-zack-dev-cm-gstack-review-stack","generatedAt":"2026-10-09T12:31:53.246Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T08:32:40.440Z","emptyReason":null},"description":"Use this skill when Codex needs gstack-style CEO/product, engineering, design, QA, release, or portfolio-shelf-space review. Trigger for requests like \"use g... Skill: GStack Review Stack Owner: zack-dev-cm Summary: Use this skill when Codex needs gstack-style CEO/product, engineering, design, QA, release, or portfolio-shelf-space review. Trigger for requests like \"use g... Tags: latest:0.1.2 Version history: v0.1.2 | 2026-05-22T20:44:28.344Z | user Call the local discovery helper through python3 so fresh ClawHub installs do not require executable file permissions. v0.1.1 |","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 3.4K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s170hyv1nagjajq3y5c6kpzx3s84jp29:gstack-review-stack","sourceUrl":"https://clawhub.ai/zack-dev-cm/gstack-review-stack","homepage":"https://clawhub.ai/zack-dev-cm/skills/gstack-review-stack","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/zack-dev-cm/gstack-review-stack","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/zack-dev-cm/skills/gstack-review-stack","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":71,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Use this skill when Codex needs gstack-style CEO/product, engineering, design, QA, release, or portfolio-shelf-space review. Trigger for requests like \"use g..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T08:32:40.440Z","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":"2026-10-09T08:32:40.440Z","emptyReason":null},"stars":null,"forks":null,"downloads":3363,"packageName":null,"latestVersion":"0.1.2","tractionLabel":"3.4K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T08:32:40.439Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T08:32:40.440Z","lastCrawledAt":"2026-10-09T08:32:40.439Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T08:32:40.439Z","lastVerifiedAt":null,"highlights":[{"version":"0.1.2","createdAt":"2026-05-22T20:44:28.344Z","changelog":"Call the local discovery helper through python3 so fresh ClawHub installs do not require executable file permissions.","fileCount":8,"zipByteSize":7285},{"version":"0.1.1","createdAt":"2026-05-22T20:42:12.689Z","changelog":"Declare python3 runtime metadata for the local gstack discovery helper.","fileCount":7,"zipByteSize":5985},{"version":"0.1.0","createdAt":"2026-05-22T20:38:50.138Z","changelog":"Initial Codex and ClawHub adapter for gstack-style CEO, engineering, design, QA, and ship reviews.","fileCount":7,"zipByteSize":5951}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s170hyv1nagjajq3y5c6kpzx3s84jp29:gstack-review-stack","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","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-zack-dev-cm-gstack-review-stack/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zack-dev-cm-gstack-review-stack/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zack-dev-cm-gstack-review-stack/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-zack-dev-cm-gstack-review-stack/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-zack-dev-cm-gstack-review-stack/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-zack-dev-cm-gstack-review-stack/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T12:31:53.246Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zack-dev-cm-gstack-review-stack/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zack-dev-cm-gstack-review-stack/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zack-dev-cm-gstack-review-stack/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zack-dev-cm-gstack-review-stack/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":"2026-10-09T08:32:40.440Z","emptyReason":null},"readme":"Skill: GStack Review Stack\n\nOwner: zack-dev-cm\n\nSummary: Use this skill when Codex needs gstack-style CEO/product, engineering, design, QA, release, or portfolio-shelf-space review. Trigger for requests like \"use g...\n\nTags: latest:0.1.2\n\nVersion history:\n\nv0.1.2 | 2026-05-22T20:44:28.344Z | user\n\nCall the local discovery helper through python3 so fresh ClawHub installs do not require executable file permissions.\n\nv0.1.1 | 2026-05-22T20:42:12.689Z | user\n\nDeclare python3 runtime metadata for the local gstack discovery helper.\n\nv0.1.0 | 2026-05-22T20:38:50.138Z | user\n\nInitial Codex and ClawHub adapter for gstack-style CEO, engineering, design, QA, and ship reviews.\n\nArchive index:\n\nArchive v0.1.2: 8 files, 7285 bytes\n\nFiles: references/design-review.md (919b), references/review-rubric.md (1428b), references/ship-and-qa.md (1034b), references/upstream.md (781b), scripts/find_gstack.py (1593b), skill-card.md (2354b), SKILL.md (3628b), _meta.json (138b)\n\nFile v0.1.2:SKILL.md\n\n---\nname: gstack-review-stack\ndescription: Use this skill when Codex needs gstack-style CEO/product, engineering, design, QA, release, or portfolio-shelf-space review. Trigger for requests like \"use gstack\", \"CEO review\", \"engineering plan review\", \"design critique\", \"QA gate\", \"ship gate\", \"which products should we keep\", or \"decide what to publish/unpublish\".\nmetadata:\n  openclaw:\n    requires:\n      bins:\n        - python3\n---\n\n# GStack Review Stack\n\nUse this skill to bring gstack-style review discipline into Codex and ClawHub workflows without copying the full upstream gstack playbooks into context.\n\nThis adapter is original guidance inspired by the public MIT-licensed `garrytan/gstack` project. When exact upstream behavior matters, inspect the local or upstream gstack clone and cite the specific file used.\n\n## Start\n\n1. Run `python3 scripts/find_gstack.py --summary` from the skill folder to locate the local gstack clone and list available upstream skill files.\n2. Choose the narrowest review mode that matches the user's request.\n3. Load only the reference file needed for that mode:\n   - Product, portfolio, scope, or slot decisions: `references/review-rubric.md`\n   - Release, QA, or \"is this ready to ship\": `references/ship-and-qa.md`\n   - UI/UX plans or visual quality: `references/design-review.md`\n4. If the task involves live publishing, store actions, or irreversible changes, make the recommendation first and only execute after explicit user approval.\n\n## Modes\n\n### CEO/Product Review\n\nUse for strategy, portfolio, scope expansion/reduction, product line focus, and \"what should we build/keep/kill?\"\n\nDefault stance: selective expansion with reduction discipline.\n\nOutput:\n- Current facts and missing facts\n- What is not in scope\n- Candidate options\n- Green/yellow/red classification\n- Named tradeoffs\n- Recommended decision and explicit next action\n\n### Engineering Review\n\nUse before implementation or release when architecture, data flow, edge cases, permissions, or maintainability are the risk.\n\nOutput:\n- Critical paths\n- Failure modes\n- Test coverage map\n- Security/privacy risk\n- Performance and maintenance risks\n- Blocking fixes before release\n\n### Design Review\n\nUse for UI/UX, landing pages, extension side panels, listing assets, screenshots, and flows.\n\nOutput:\n- 0-10 rating by dimension\n- What would make it a 10\n- Specific edits, not taste adjectives\n- Mobile/responsive and empty/error/loading states\n- \"AI-slop\" flags: generic layouts, vague copy, ornamental visuals, overcomplicated text\n\n### QA And Ship Gate\n\nUse when the user asks to test, publish, deploy, submit, or release.\n\nOutput:\n- Tests run and results\n- User-flow evidence\n- Remaining blockers\n- Rollback or recovery path\n- Clear ship/no-ship recommendation\n\n## Decision Rules\n\n- Prefer real demand over technical novelty.\n- Prefer recurring use over one-time curiosity.\n- Prefer narrow permissions and simple privacy disclosures.\n- Keep scarce slots only for products that beat a named alternative.\n- Do not treat total installs as active use; weigh retained weekly users, uninstall rate, impressions, page views, and conversion.\n- When evidence is weak, run a bounded test instead of declaring certainty.\n\n## Upstream Use\n\nIf `/home/z/Github/gstack` exists, use it as source material for deeper review. Read only the specific upstream `SKILL.md` needed for the current mode.\n\nIf it is missing and the user asked to use upstream gstack, fetch or inspect `https://github.com/garrytan/gstack` before proceeding.\n\nDo not paste large upstream sections into outputs. Summarize and cite local file paths or public links.\n\nFile v0.1.2:_meta.json\n\n{\n  \"ownerId\": \"kn7dhjt1k1f111whp13fmrqwnh81tn1v\",\n  \"slug\": \"gstack-review-stack\",\n  \"version\": \"0.1.2\",\n  \"publishedAt\": 1779482668344\n}\n\nFile v0.1.2:references/design-review.md\n\n# Design Review\n\nUse this for UI/UX plans, landing pages, store listings, extension popups, side panels, and screenshots.\n\n## Score 0-10\n\nRate:\n- First-screen clarity\n- User job clarity\n- Trust and permission comfort\n- Visual originality\n- Interaction completeness\n- Mobile/responsive behavior\n- Copy simplicity\n- Empty/error/loading states\n\nFor each score below 8, write the exact change that would raise it.\n\n## AI-Slop Flags\n\nFlag:\n- Generic centered hero with vague claims\n- Overdecorated cards with no workflow density\n- Text that a nontechnical user cannot understand\n- Screenshots that do not show the actual product\n- Permission-heavy UX without trust explanation\n- Missing empty/error states\n- Unclear call to action\n\n## Required Output\n\nGive concrete edits:\n- Replace this phrase with that phrase\n- Move this control here\n- Add/remove this state\n- Change screenshot composition\n- Simplify the listing promise\n\nFile v0.1.2:references/review-rubric.md\n\n# Review Rubric\n\nUse this for CEO/product, portfolio, and publish/unpublish decisions.\n\n## Shelf-Space Rule\n\nTreat scarce release slots as shelf space. A new candidate must beat a named incumbent or it stays draft.\n\nScore each candidate 0-5, weighted to 100:\n\n| Weight | Category | Question |\n|---:|---|---|\n| 30 | Demand reality | Does current usage, growth, retention, or user pull exist? |\n| 20 | Strategic coherence | Does this compound the product line and audience? |\n| 15 | Distribution efficiency | Does search/listing/channel fit make acquisition plausible? |\n| 15 | Quality and trust | Are permissions, privacy, reviews, and policy risk acceptable? |\n| 10 | Focus cost | Does it fragment attention or duplicate another product? |\n| 10 | Option value | Is the test reversible and likely to teach something useful? |\n\n## Gates\n\nGreen:\n- Real demand or a strong specific wedge\n- Clear user and job\n- Low policy and trust risk\n- Measurable 30-day success test\n\nYellow:\n- Plausible but evidence-light\n- Needs clearer positioning\n- Overlaps another candidate\n- Keep as draft until it beats a live item\n\nRed:\n- Near-zero users and no growth signal\n- High policy/trust risk\n- Novelty-only or time-bound\n- Exists because it was easy to ship\n\n## Required Output\n\nInclude:\n- Ranked keep list\n- Ranked cut list\n- Hold-as-draft list\n- The exact evidence behind each cut\n- The first irreversible action that needs explicit approval\n\nFile v0.1.2:references/ship-and-qa.md\n\n# Ship And QA Gate\n\nUse this for release, publish, deploy, submit-for-review, and \"is it ready?\" work.\n\n## Ship Gate\n\nBefore release:\n- Confirm package/version identity.\n- Confirm permission and privacy disclosures match actual behavior.\n- Run local unit and e2e checks appropriate to the blast radius.\n- Test the main user flow as a real user, not only with mocked internals.\n- Inspect logs/network errors for hidden failures.\n- Confirm listing screenshots, icons, URLs, support links, and privacy pages.\n- Identify store-side or account-side blockers separately from code blockers.\n\n## QA Output\n\nReport:\n- Tests run\n- User flows verified\n- Critical failures found/fixed\n- Remaining blockers\n- Ship/no-ship recommendation\n- Rollback or recovery path\n\n## Stop Conditions\n\nStop before destructive actions unless the user explicitly approved:\n- Unpublish/delete/hide a live listing\n- Submit a store listing with inaccurate claims\n- Publish with known broken core flow\n- Ship a privacy disclosure that omits data sharing or permissions\n\nFile v0.1.2:references/upstream.md\n\n# Upstream\n\nThis skill is an original concise adapter for using gstack-style review patterns inside Codex and ClawHub workflows.\n\nUpstream project:\n- Repository: `https://github.com/garrytan/gstack`\n- Local default clone: `/home/z/Github/gstack`\n- License observed locally: MIT License, Copyright (c) 2026 Garry Tan\n\nDo not copy large upstream skill bodies into generated ClawHub packages. ClawHub publishes skills as MIT-0, so this adapter should stay original and only reference upstream gstack when deeper source behavior is required.\n\nSuggested upstream files to inspect by task:\n- CEO/product review: `plan-ceo-review/SKILL.md`\n- Engineering review: `plan-eng-review/SKILL.md`\n- Design review: `plan-design-review/SKILL.md`\n- QA: `qa/SKILL.md`\n- Ship/release: `ship/SKILL.md`\n\nFile v0.1.2:skill-card.md\n\n## Description:\n\nUse this skill when Codex needs gstack-style CEO/product, engineering, design, QA, release, or portfolio-shelf-space review.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[zack-dev-cm](https://clawhub.ai/user/zack-dev-cm)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers, product owners, designers, QA reviewers, and release reviewers use this skill to apply gstack-style review discipline to Codex and ClawHub decisions. It supports product and portfolio triage, engineering risk review, UI/UX critique, QA gates, and ship/no-ship recommendations.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill can influence review outcomes and ship/no-ship recommendations, which could lead to publish, unpublish, delete, submit, or similar actions if treated as automatic approval.\n\nMitigation: Review recommendations before execution and require explicit user approval before any publishing, unpublishing, deletion, submission, or other irreversible action.\n\nRisk: When upstream behavior matters, the skill may read a local gstack clone or inspect the public gstack repository.\n\nMitigation: Load only task-relevant upstream files, cite the source used, and avoid copying large upstream sections into outputs.\n\n## Reference(s):\n\n- [Design Review](references/design-review.md)\n- [Review Rubric](references/review-rubric.md)\n- [Ship And QA Gate](references/ship-and-qa.md)\n- [Upstream](references/upstream.md)\n- [Upstream gstack project](https://github.com/garrytan/gstack)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with structured review sections, recommendations, and occasional inline shell commands or code references]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include green/yellow/red classifications, 0-10 design scores, QA evidence, blocker lists, rollback notes, and ship/no-ship recommendations.]\n\n## Skill Version(s):\n\n0.1.2 (source: server release evidence)\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 v0.1.1: 7 files, 5985 bytes\n\nFiles: references/design-review.md (919b), references/review-rubric.md (1428b), references/ship-and-qa.md (1034b), references/upstream.md (781b), scripts/find_gstack.py (1593b), SKILL.md (3598b), _meta.json (138b)\n\nFile v0.1.1:SKILL.md\n\n---\nname: gstack-review-stack\ndescription: Use this skill when Codex needs gstack-style CEO/product, engineering, design, QA, release, or portfolio-shelf-space review. Trigger for requests like \"use gstack\", \"CEO review\", \"engineering plan review\", \"design critique\", \"QA gate\", \"ship gate\", \"which products should we keep\", or \"decide what to publish/unpublish\".\nmetadata:\n  openclaw:\n    requires:\n      bins:\n        - python3\n---\n\n# GStack Review Stack\n\nUse this skill to bring gstack-style review discipline into Codex and ClawHub workflows without copying the full upstream gstack playbooks into context.\n\nThis adapter is original guidance inspired by the public MIT-licensed `garrytan/gstack` project. When exact upstream behavior matters, inspect the local or upstream gstack clone and cite the specific file used.\n\n## Start\n\n1. Run `scripts/find_gstack.py --summary` to locate the local gstack clone and list available upstream skill files.\n2. Choose the narrowest review mode that matches the user's request.\n3. Load only the reference file needed for that mode:\n   - Product, portfolio, scope, or slot decisions: `references/review-rubric.md`\n   - Release, QA, or \"is this ready to ship\": `references/ship-and-qa.md`\n   - UI/UX plans or visual quality: `references/design-review.md`\n4. If the task involves live publishing, store actions, or irreversible changes, make the recommendation first and only execute after explicit user approval.\n\n## Modes\n\n### CEO/Product Review\n\nUse for strategy, portfolio, scope expansion/reduction, product line focus, and \"what should we build/keep/kill?\"\n\nDefault stance: selective expansion with reduction discipline.\n\nOutput:\n- Current facts and missing facts\n- What is not in scope\n- Candidate options\n- Green/yellow/red classification\n- Named tradeoffs\n- Recommended decision and explicit next action\n\n### Engineering Review\n\nUse before implementation or release when architecture, data flow, edge cases, permissions, or maintainability are the risk.\n\nOutput:\n- Critical paths\n- Failure modes\n- Test coverage map\n- Security/privacy risk\n- Performance and maintenance risks\n- Blocking fixes before release\n\n### Design Review\n\nUse for UI/UX, landing pages, extension side panels, listing assets, screenshots, and flows.\n\nOutput:\n- 0-10 rating by dimension\n- What would make it a 10\n- Specific edits, not taste adjectives\n- Mobile/responsive and empty/error/loading states\n- \"AI-slop\" flags: generic layouts, vague copy, ornamental visuals, overcomplicated text\n\n### QA And Ship Gate\n\nUse when the user asks to test, publish, deploy, submit, or release.\n\nOutput:\n- Tests run and results\n- User-flow evidence\n- Remaining blockers\n- Rollback or recovery path\n- Clear ship/no-ship recommendation\n\n## Decision Rules\n\n- Prefer real demand over technical novelty.\n- Prefer recurring use over one-time curiosity.\n- Prefer narrow permissions and simple privacy disclosures.\n- Keep scarce slots only for products that beat a named alternative.\n- Do not treat total installs as active use; weigh retained weekly users, uninstall rate, impressions, page views, and conversion.\n- When evidence is weak, run a bounded test instead of declaring certainty.\n\n## Upstream Use\n\nIf `/home/z/Github/gstack` exists, use it as source material for deeper review. Read only the specific upstream `SKILL.md` needed for the current mode.\n\nIf it is missing and the user asked to use upstream gstack, fetch or inspect `https://github.com/garrytan/gstack` before proceeding.\n\nDo not paste large upstream sections into outputs. Summarize and cite local file paths or public links.\n\nFile v0.1.1:_meta.json\n\n{\n  \"ownerId\": \"kn7dhjt1k1f111whp13fmrqwnh81tn1v\",\n  \"slug\": \"gstack-review-stack\",\n  \"version\": \"0.1.1\",\n  \"publishedAt\": 1779482532689\n}\n\nFile v0.1.1:references/design-review.md\n\n# Design Review\n\nUse this for UI/UX plans, landing pages, store listings, extension popups, side panels, and screenshots.\n\n## Score 0-10\n\nRate:\n- First-screen clarity\n- User job clarity\n- Trust and permission comfort\n- Visual originality\n- Interaction completeness\n- Mobile/responsive behavior\n- Copy simplicity\n- Empty/error/loading states\n\nFor each score below 8, write the exact change that would raise it.\n\n## AI-Slop Flags\n\nFlag:\n- Generic centered hero with vague claims\n- Overdecorated cards with no workflow density\n- Text that a nontechnical user cannot understand\n- Screenshots that do not show the actual product\n- Permission-heavy UX without trust explanation\n- Missing empty/error states\n- Unclear call to action\n\n## Required Output\n\nGive concrete edits:\n- Replace this phrase with that phrase\n- Move this control here\n- Add/remove this state\n- Change screenshot composition\n- Simplify the listing promise\n\nFile v0.1.1:references/review-rubric.md\n\n# Review Rubric\n\nUse this for CEO/product, portfolio, and publish/unpublish decisions.\n\n## Shelf-Space Rule\n\nTreat scarce release slots as shelf space. A new candidate must beat a named incumbent or it stays draft.\n\nScore each candidate 0-5, weighted to 100:\n\n| Weight | Category | Question |\n|---:|---|---|\n| 30 | Demand reality | Does current usage, growth, retention, or user pull exist? |\n| 20 | Strategic coherence | Does this compound the product line and audience? |\n| 15 | Distribution efficiency | Does search/listing/channel fit make acquisition plausible? |\n| 15 | Quality and trust | Are permissions, privacy, reviews, and policy risk acceptable? |\n| 10 | Focus cost | Does it fragment attention or duplicate another product? |\n| 10 | Option value | Is the test reversible and likely to teach something useful? |\n\n## Gates\n\nGreen:\n- Real demand or a strong specific wedge\n- Clear user and job\n- Low policy and trust risk\n- Measurable 30-day success test\n\nYellow:\n- Plausible but evidence-light\n- Needs clearer positioning\n- Overlaps another candidate\n- Keep as draft until it beats a live item\n\nRed:\n- Near-zero users and no growth signal\n- High policy/trust risk\n- Novelty-only or time-bound\n- Exists because it was easy to ship\n\n## Required Output\n\nInclude:\n- Ranked keep list\n- Ranked cut list\n- Hold-as-draft list\n- The exact evidence behind each cut\n- The first irreversible action that needs explicit approval\n\nFile v0.1.1:references/ship-and-qa.md\n\n# Ship And QA Gate\n\nUse this for release, publish, deploy, submit-for-review, and \"is it ready?\" work.\n\n## Ship Gate\n\nBefore release:\n- Confirm package/version identity.\n- Confirm permission and privacy disclosures match actual behavior.\n- Run local unit and e2e checks appropriate to the blast radius.\n- Test the main user flow as a real user, not only with mocked internals.\n- Inspect logs/network errors for hidden failures.\n- Confirm listing screenshots, icons, URLs, support links, and privacy pages.\n- Identify store-side or account-side blockers separately from code blockers.\n\n## QA Output\n\nReport:\n- Tests run\n- User flows verified\n- Critical failures found/fixed\n- Remaining blockers\n- Ship/no-ship recommendation\n- Rollback or recovery path\n\n## Stop Conditions\n\nStop before destructive actions unless the user explicitly approved:\n- Unpublish/delete/hide a live listing\n- Submit a store listing with inaccurate claims\n- Publish with known broken core flow\n- Ship a privacy disclosure that omits data sharing or permissions\n\nFile v0.1.1:references/upstream.md\n\n# Upstream\n\nThis skill is an original concise adapter for using gstack-style review patterns inside Codex and ClawHub workflows.\n\nUpstream project:\n- Repository: `https://github.com/garrytan/gstack`\n- Local default clone: `/home/z/Github/gstack`\n- License observed locally: MIT License, Copyright (c) 2026 Garry Tan\n\nDo not copy large upstream skill bodies into generated ClawHub packages. ClawHub publishes skills as MIT-0, so this adapter should stay original and only reference upstream gstack when deeper source behavior is required.\n\nSuggested upstream files to inspect by task:\n- CEO/product review: `plan-ceo-review/SKILL.md`\n- Engineering review: `plan-eng-review/SKILL.md`\n- Design review: `plan-design-review/SKILL.md`\n- QA: `qa/SKILL.md`\n- Ship/release: `ship/SKILL.md`\n\nArchive v0.1.0: 7 files, 5951 bytes\n\nFiles: references/design-review.md (919b), references/review-rubric.md (1428b), references/ship-and-qa.md (1034b), references/upstream.md (781b), scripts/find_gstack.py (1593b), SKILL.md (3532b), _meta.json (138b)\n\nFile v0.1.0:SKILL.md\n\n---\nname: gstack-review-stack\ndescription: Use this skill when Codex needs gstack-style CEO/product, engineering, design, QA, release, or portfolio-shelf-space review. Trigger for requests like \"use gstack\", \"CEO review\", \"engineering plan review\", \"design critique\", \"QA gate\", \"ship gate\", \"which products should we keep\", or \"decide what to publish/unpublish\".\n---\n\n# GStack Review Stack\n\nUse this skill to bring gstack-style review discipline into Codex and ClawHub workflows without copying the full upstream gstack playbooks into context.\n\nThis adapter is original guidance inspired by the public MIT-licensed `garrytan/gstack` project. When exact upstream behavior matters, inspect the local or upstream gstack clone and cite the specific file used.\n\n## Start\n\n1. Run `scripts/find_gstack.py --summary` to locate the local gstack clone and list available upstream skill files.\n2. Choose the narrowest review mode that matches the user's request.\n3. Load only the reference file needed for that mode:\n   - Product, portfolio, scope, or slot decisions: `references/review-rubric.md`\n   - Release, QA, or \"is this ready to ship\": `references/ship-and-qa.md`\n   - UI/UX plans or visual quality: `references/design-review.md`\n4. If the task involves live publishing, store actions, or irreversible changes, make the recommendation first and only execute after explicit user approval.\n\n## Modes\n\n### CEO/Product Review\n\nUse for strategy, portfolio, scope expansion/reduction, product line focus, and \"what should we build/keep/kill?\"\n\nDefault stance: selective expansion with reduction discipline.\n\nOutput:\n- Current facts and missing facts\n- What is not in scope\n- Candidate options\n- Green/yellow/red classification\n- Named tradeoffs\n- Recommended decision and explicit next action\n\n### Engineering Review\n\nUse before implementation or release when architecture, data flow, edge cases, permissions, or maintainability are the risk.\n\nOutput:\n- Critical paths\n- Failure modes\n- Test coverage map\n- Security/privacy risk\n- Performance and maintenance risks\n- Blocking fixes before release\n\n### Design Review\n\nUse for UI/UX, landing pages, extension side panels, listing assets, screenshots, and flows.\n\nOutput:\n- 0-10 rating by dimension\n- What would make it a 10\n- Specific edits, not taste adjectives\n- Mobile/responsive and empty/error/loading states\n- \"AI-slop\" flags: generic layouts, vague copy, ornamental visuals, overcomplicated text\n\n### QA And Ship Gate\n\nUse when the user asks to test, publish, deploy, submit, or release.\n\nOutput:\n- Tests run and results\n- User-flow evidence\n- Remaining blockers\n- Rollback or recovery path\n- Clear ship/no-ship recommendation\n\n## Decision Rules\n\n- Prefer real demand over technical novelty.\n- Prefer recurring use over one-time curiosity.\n- Prefer narrow permissions and simple privacy disclosures.\n- Keep scarce slots only for products that beat a named alternative.\n- Do not treat total installs as active use; weigh retained weekly users, uninstall rate, impressions, page views, and conversion.\n- When evidence is weak, run a bounded test instead of declaring certainty.\n\n## Upstream Use\n\nIf `/home/z/Github/gstack` exists, use it as source material for deeper review. Read only the specific upstream `SKILL.md` needed for the current mode.\n\nIf it is missing and the user asked to use upstream gstack, fetch or inspect `https://github.com/garrytan/gstack` before proceeding.\n\nDo not paste large upstream sections into outputs. Summarize and cite local file paths or public links.\n\nFile v0.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn7dhjt1k1f111whp13fmrqwnh81tn1v\",\n  \"slug\": \"gstack-review-stack\",\n  \"version\": \"0.1.0\",\n  \"publishedAt\": 1779482330138\n}\n\nFile v0.1.0:references/design-review.md\n\n# Design Review\n\nUse this for UI/UX plans, landing pages, store listings, extension popups, side panels, and screenshots.\n\n## Score 0-10\n\nRate:\n- First-screen clarity\n- User job clarity\n- Trust and permission comfort\n- Visual originality\n- Interaction completeness\n- Mobile/responsive behavior\n- Copy simplicity\n- Empty/error/loading states\n\nFor each score below 8, write the exact change that would raise it.\n\n## AI-Slop Flags\n\nFlag:\n- Generic centered hero with vague claims\n- Overdecorated cards with no workflow density\n- Text that a nontechnical user cannot understand\n- Screenshots that do not show the actual product\n- Permission-heavy UX without trust explanation\n- Missing empty/error states\n- Unclear call to action\n\n## Required Output\n\nGive concrete edits:\n- Replace this phrase with that phrase\n- Move this control here\n- Add/remove this state\n- Change screenshot composition\n- Simplify the listing promise\n\nFile v0.1.0:references/review-rubric.md\n\n# Review Rubric\n\nUse this for CEO/product, portfolio, and publish/unpublish decisions.\n\n## Shelf-Space Rule\n\nTreat scarce release slots as shelf space. A new candidate must beat a named incumbent or it stays draft.\n\nScore each candidate 0-5, weighted to 100:\n\n| Weight | Category | Question |\n|---:|---|---|\n| 30 | Demand reality | Does current usage, growth, retention, or user pull exist? |\n| 20 | Strategic coherence | Does this compound the product line and audience? |\n| 15 | Distribution efficiency | Does search/listing/channel fit make acquisition plausible? |\n| 15 | Quality and trust | Are permissions, privacy, reviews, and policy risk acceptable? |\n| 10 | Focus cost | Does it fragment attention or duplicate another product? |\n| 10 | Option value | Is the test reversible and likely to teach something useful? |\n\n## Gates\n\nGreen:\n- Real demand or a strong specific wedge\n- Clear user and job\n- Low policy and trust risk\n- Measurable 30-day success test\n\nYellow:\n- Plausible but evidence-light\n- Needs clearer positioning\n- Overlaps another candidate\n- Keep as draft until it beats a live item\n\nRed:\n- Near-zero users and no growth signal\n- High policy/trust risk\n- Novelty-only or time-bound\n- Exists because it was easy to ship\n\n## Required Output\n\nInclude:\n- Ranked keep list\n- Ranked cut list\n- Hold-as-draft list\n- The exact evidence behind each cut\n- The first irreversible action that needs explicit approval\n\nFile v0.1.0:references/ship-and-qa.md\n\n# Ship And QA Gate\n\nUse this for release, publish, deploy, submit-for-review, and \"is it ready?\" work.\n\n## Ship Gate\n\nBefore release:\n- Confirm package/version identity.\n- Confirm permission and privacy disclosures match actual behavior.\n- Run local unit and e2e checks appropriate to the blast radius.\n- Test the main user flow as a real user, not only with mocked internals.\n- Inspect logs/network errors for hidden failures.\n- Confirm listing screenshots, icons, URLs, support links, and privacy pages.\n- Identify store-side or account-side blockers separately from code blockers.\n\n## QA Output\n\nReport:\n- Tests run\n- User flows verified\n- Critical failures found/fixed\n- Remaining blockers\n- Ship/no-ship recommendation\n- Rollback or recovery path\n\n## Stop Conditions\n\nStop before destructive actions unless the user explicitly approved:\n- Unpublish/delete/hide a live listing\n- Submit a store listing with inaccurate claims\n- Publish with known broken core flow\n- Ship a privacy disclosure that omits data sharing or permissions\n\nFile v0.1.0:references/upstream.md\n\n# Upstream\n\nThis skill is an original concise adapter for using gstack-style review patterns inside Codex and ClawHub workflows.\n\nUpstream project:\n- Repository: `https://github.com/garrytan/gstack`\n- Local default clone: `/home/z/Github/gstack`\n- License observed locally: MIT License, Copyright (c) 2026 Garry Tan\n\nDo not copy large upstream skill bodies into generated ClawHub packages. ClawHub publishes skills as MIT-0, so this adapter should stay original and only reference upstream gstack when deeper source behavior is required.\n\nSuggested upstream files to inspect by task:\n- CEO/product review: `plan-ceo-review/SKILL.md`\n- Engineering review: `plan-eng-review/SKILL.md`\n- Design review: `plan-design-review/SKILL.md`\n- QA: `qa/SKILL.md`\n- Ship/release: `ship/SKILL.md`","readmeExcerpt":"Skill: GStack Review Stack Owner: zack-dev-cm Summary: Use this skill when Codex needs gstack-style CEO/product, engineering, design, QA, release, or portfolio-shelf-space review. Trigger for requests like \"use g... Tags: latest:0.1.2 Version history: v0.1.2 | 2026-05-22T20:44:28.344Z | user Call the local discovery helper through python3 so fresh ClawHub installs do not require executable file permissions. v0.1.1 | ","codeSnippets":[],"executableExamples":[],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: gstack-review-stack\ndescription: Use this skill when Codex needs gstack-style CEO/product, engineering, design, QA, release, or portfolio-shelf-space review. Trigger for requests like \"use gstack\", \"CEO review\", \"engineering plan review\", \"design critique\", \"QA gate\", \"ship gate\", \"which products should we keep\", or \"decide what to publish/unpublish\".\nmetadata:\n  openclaw:\n    requires:\n      bins:\n        - python3\n---\n\n# GStack Review Stack\n\nUse this skill to bring gstack-style review discipline into Codex and ClawHub workflows without copying the full upstream gstack playbooks into context.\n\nThis adapter is original guidance inspired by the public MIT-licensed `garrytan/gstack` project. When exact upstream behavior matters, inspect the local or upstream gstack clone and cite the specific file used.\n\n## Start\n\n1. Run `python3 scripts/find_gstack.py --summary` from the skill folder to locate the local gstack clone and list available upstream skill files.\n2. Choose the narrowest review mode that matches the user's request.\n3. Load only the reference file needed for that mode:\n   - Product, portfolio, scope, or slot decisions: `references/review-rubric.md`\n   - Release, QA, or \"is this ready to ship\": `references/ship-and-qa.md`\n   - UI/UX plans or visual quality: `references/design-review.md`\n4. If the task involves live publishing, store actions, or irreversible changes, make the recommendation first and only execute after explicit user approval.\n\n## Modes\n\n### CEO/Product Review\n\nUse for strategy, portfolio, scope expansion/reduction, product line focus, and \"what should we build/keep/kill?\"\n\nDefault stance: selective expansion with reduction discipline.\n\nOutput:\n- Current facts and missing facts\n- What is not in scope\n- Candidate options\n- Green/yellow/red classification\n- Named tradeoffs\n- Recommended decision and explicit next action\n\n### Engineering Review\n\nUse before implementation or release when architecture, data flow, edge cases, permissions, or maintainability are the risk.\n\nOutput:\n- Critical paths\n- Failure modes\n- Test coverage map\n- Security/privacy risk\n- Performance and maintenance risks\n- Blocking fixes before release\n\n### Design Review\n\nUse for UI/UX, landing pages, extension side panels, listing assets, screenshots, and flows.\n\nOutput:\n- 0-10 rating by dimension\n- What would make it a 10\n- Specific edits, not taste adjectives\n- Mobile/responsive and empty/error/loading states\n- \"AI-slop\" flags: generic layouts, vague copy, ornamental visuals, overcomplicated text\n\n### QA And Ship Gate\n\nUse when the user asks to test, publish, deploy, submit, or release.\n\nOutput:\n- Tests run and results\n- User-flow evidence\n- Remaining blockers\n- Rollback or recovery path\n- Clear ship/no-ship recommendation\n\n## Decision Rules\n\n- Prefer real demand over technical novelty.\n- Prefer recurring use over one-time curiosity.\n- Prefer narrow permissions and simple privacy disclosures.\n- Keep scarce slots only for products that beat a named a"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7dhjt1k1f111whp13fmrqwnh81tn1v\",\n  \"slug\": \"gstack-review-stack\",\n  \"version\": \"0.1.2\",\n  \"publishedAt\": 1779482668344\n}"},{"path":"references/design-review.md","content":"# Design Review\n\nUse this for UI/UX plans, landing pages, store listings, extension popups, side panels, and screenshots.\n\n## Score 0-10\n\nRate:\n- First-screen clarity\n- User job clarity\n- Trust and permission comfort\n- Visual originality\n- Interaction completeness\n- Mobile/responsive behavior\n- Copy simplicity\n- Empty/error/loading states\n\nFor each score below 8, write the exact change that would raise it.\n\n## AI-Slop Flags\n\nFlag:\n- Generic centered hero with vague claims\n- Overdecorated cards with no workflow density\n- Text that a nontechnical user cannot understand\n- Screenshots that do not show the actual product\n- Permission-heavy UX without trust explanation\n- Missing empty/error states\n- Unclear call to action\n\n## Required Output\n\nGive concrete edits:\n- Replace this phrase with that phrase\n- Move this control here\n- Add/remove this state\n- Change screenshot composition\n- Simplify the listing promise"},{"path":"references/review-rubric.md","content":"# Review Rubric\n\nUse this for CEO/product, portfolio, and publish/unpublish decisions.\n\n## Shelf-Space Rule\n\nTreat scarce release slots as shelf space. A new candidate must beat a named incumbent or it stays draft.\n\nScore each candidate 0-5, weighted to 100:\n\n| Weight | Category | Question |\n|---:|---|---|\n| 30 | Demand reality | Does current usage, growth, retention, or user pull exist? |\n| 20 | Strategic coherence | Does this compound the product line and audience? |\n| 15 | Distribution efficiency | Does search/listing/channel fit make acquisition plausible? |\n| 15 | Quality and trust | Are permissions, privacy, reviews, and policy risk acceptable? |\n| 10 | Focus cost | Does it fragment attention or duplicate another product? |\n| 10 | Option value | Is the test reversible and likely to teach something useful? |\n\n## Gates\n\nGreen:\n- Real demand or a strong specific wedge\n- Clear user and job\n- Low policy and trust risk\n- Measurable 30-day success test\n\nYellow:\n- Plausible but evidence-light\n- Needs clearer positioning\n- Overlaps another candidate\n- Keep as draft until it beats a live item\n\nRed:\n- Near-zero users and no growth signal\n- High policy/trust risk\n- Novelty-only or time-bound\n- Exists because it was easy to ship\n\n## Required Output\n\nInclude:\n- Ranked keep list\n- Ranked cut list\n- Hold-as-draft list\n- The exact evidence behind each cut\n- The first irreversible action that needs explicit approval"},{"path":"references/ship-and-qa.md","content":"# Ship And QA Gate\n\nUse this for release, publish, deploy, submit-for-review, and \"is it ready?\" work.\n\n## Ship Gate\n\nBefore release:\n- Confirm package/version identity.\n- Confirm permission and privacy disclosures match actual behavior.\n- Run local unit and e2e checks appropriate to the blast radius.\n- Test the main user flow as a real user, not only with mocked internals.\n- Inspect logs/network errors for hidden failures.\n- Confirm listing screenshots, icons, URLs, support links, and privacy pages.\n- Identify store-side or account-side blockers separately from code blockers.\n\n## QA Output\n\nReport:\n- Tests run\n- User flows verified\n- Critical failures found/fixed\n- Remaining blockers\n- Ship/no-ship recommendation\n- Rollback or recovery path\n\n## Stop Conditions\n\nStop before destructive actions unless the user explicitly approved:\n- Unpublish/delete/hide a live listing\n- Submit a store listing with inaccurate claims\n- Publish with known broken core flow\n- Ship a privacy disclosure that omits data sharing or permissions"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Use this skill when Codex needs gstack-style CEO/product, engineering, design, QA, release, or portfolio-shelf-space review. Trigger for requests like \"use g... Skill: GStack Review Stack Owner: zack-dev-cm Summary: Use this skill when Codex needs gstack-style CEO/product, engineering, design, QA, release, or portfolio-shelf-space review. Trigger for requests like \"use g... Tags: latest:0.1.2 Version history: v0.1.2 | 2026-05-22T20:44:28.344Z | user Call the local discovery helper through python3 so fresh ClawHub installs do not require executable file permissions. v0.1.1 |","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1346,"uniquenessScore":51,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T08:32:40.440Z","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":"2026-10-09T08:32:40.440Z","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":"2026-10-09T12:31:53.246Z","emptyReason":null},"items":[{"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":"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":"2026-04-10T18:48:31.762Z","createdAt":"2026-02-25T03:38:16.584Z","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"}]}}}