{"id":"f8fc9468-81b8-4f31-a583-c39b4116d941","entityType":"agent","slug":"clawhub-clarezoe-refactor-agents-md","name":"Refactor Agents Md","canonicalUrl":"https://www.xpersona.co/agent/clawhub-clarezoe-refactor-agents-md","canonicalPath":"/agent/clawhub-clarezoe-refactor-agents-md","generatedAt":"2026-10-11T21:50:44.278Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T18:42:22.770Z","emptyReason":null},"description":"Refactors AGENTS.md files into a minimal root file plus topic-specific follow-up docs using progressive disclosure. Use when cleaning up, splitting, or revie...","descriptionLabel":"Source description","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s178sk484g47vwcbvvfcjpftfx8461fz:refactor-agents-md","sourceUrl":"https://clawhub.ai/clarezoe/refactor-agents-md","homepage":"https://clawhub.ai/clarezoe/skills/refactor-agents-md","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/clarezoe/refactor-agents-md","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/clarezoe/skills/refactor-agents-md","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Refactor Agents Md technical dossier on Xpersona with agent coverage, OPENCLEW support, and live trust metadata."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T18:42:22.770Z","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":"2026-10-11T18:42:22.770Z","emptyReason":null},"stars":null,"forks":null,"downloads":1008,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.0.2","tractionLabel":"1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T18:42:22.693Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T18:42:22.770Z","lastCrawledAt":"2026-10-11T18:42:22.693Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T18:42:22.693Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.2","createdAt":"2026-06-09T13:21:48.782Z","changelog":"Add OpenCode, Kiro, Devin, Codex, Cursor, and Windsurf skill compatibility","fileCount":7,"zipByteSize":6108},{"version":"1.0.1","createdAt":"2026-06-09T13:10:03.642Z","changelog":"Normalize SKILL.md frontmatter for OpenClaw, Hermes, and Claude compatibility","fileCount":7,"zipByteSize":6246},{"version":"1.0.0","createdAt":"2026-05-12T22:51:32.084Z","changelog":"Initial release: audit and refactor AGENTS.md files using progressive disclosure — identify contradictions, extract essentials, group bloat into topic docs, flag stale instructions.","fileCount":6,"zipByteSize":5322}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s178sk484g47vwcbvvfcjpftfx8461fz:refactor-agents-md","setupComplexity":"low","setupSteps":["Install using `clawhub skill install s178sk484g47vwcbvvfcjpftfx8461fz:refactor-agents-md` in an isolated environment before connecting it to live workloads.","No published capability contract is available yet, so validate auth and request/response behavior manually.","Review the upstream CLAWHUB listing at https://clawhub.ai/clarezoe/refactor-agents-md before using production credentials."],"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-clarezoe-refactor-agents-md/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-refactor-agents-md/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-refactor-agents-md/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-refactor-agents-md/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-refactor-agents-md/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-refactor-agents-md/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T21:50:44.276Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-refactor-agents-md/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-refactor-agents-md/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-refactor-agents-md/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-refactor-agents-md/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":"medium","updatedAt":"2026-10-11T18:42:22.770Z","emptyReason":null},"readme":"Skill: Refactor Agents Md\n\nOwner: clarezoe\n\nSummary: Refactors AGENTS.md files into a minimal root file plus topic-specific follow-up docs using progressive disclosure. Use when cleaning up, splitting, or revie...\n\nTags: agents-md:1.0.2, ai-config:1.0.2, claude-md:1.0.2, developer-tools:1.0.0, latest:1.0.2, progressive-disclosure:1.0.2, refactoring:1.0.2\n\nVersion history:\n\nv1.0.2 | 2026-06-09T13:21:48.782Z | user\n\nAdd OpenCode, Kiro, Devin, Codex, Cursor, and Windsurf skill compatibility\n\nv1.0.1 | 2026-06-09T13:10:03.642Z | user\n\nNormalize SKILL.md frontmatter for OpenClaw, Hermes, and Claude compatibility\n\nv1.0.0 | 2026-05-12T22:51:32.084Z | user\n\nInitial release: audit and refactor AGENTS.md files using progressive disclosure — identify contradictions, extract essentials, group bloat into topic docs, flag stale instructions.\n\nArchive index:\n\nArchive v1.0.2: 7 files, 6108 bytes\n\nFiles: README.md (1131b), references/principles.md (1587b), skill-card.md (1956b), SKILL.md (3702b), workflows/audit-agents-md.md (859b), workflows/refactor-agents-md.md (1102b), _meta.json (137b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: \"refactor-agents-md\"\ndescription: \"Refactors AGENTS.md files into a minimal root file plus topic-specific follow-up docs using progressive disclosure. Use when cleaning up, splitting, or reviewing AGENTS.md / CLAUDE.md guidance — or when the file has grown into a \\\"ball of mud\\\" with contradictions, bloat, and stale instructions.\"\nlicense: \"MIT-0\"\nmetadata: {\"openclaw\":{\"emoji\":\"🧹\",\"homepage\":\"https://github.com/Fei2-Labs/skill-genie\"},\"category\":\"developer-tools\",\"author\":\"Skill Genie\",\"tags\":[\"agents-md\",\"claude-md\",\"refactoring\",\"progressive-disclosure\",\"ai-config\"],\"version\":\"1.0.2\",\"license\":\"MIT-0\",\"hermes\":{\"tags\":[\"agents-md\",\"claude-md\",\"refactoring\",\"progressive-disclosure\",\"ai-config\"]}}\n---\n\n<objective>\nRefactor AGENTS.md files so the root file stays small, stable, and broadly useful while detailed guidance moves into focused follow-up docs. The skill helps identify contradictions, separate essentials from bloat, and produce a clearer instruction hierarchy that is easier for agents to follow.\n</objective>\n\n<quick_start>\n1. Identify whether the user wants a review, a rewrite proposal, or an in-repo refactor.\n2. Read the current AGENTS.md content and classify each instruction as root-essential, topic-specific, conflicting, redundant, vague, or stale.\n3. Keep only universal instructions in the root file, move the rest into topic docs, and surface any contradictions before editing.\n</quick_start>\n\n<essential_principles>\n<principle name=\"keep-root-minimal\">\nThe root AGENTS.md should contain only what applies to every task: a one-line project description, package manager expectations if non-default, non-standard build or typecheck commands, and truly universal constraints.\n</principle>\n\n<principle name=\"resolve-conflicts-first\">\nIf two instructions disagree, do not silently merge them. Surface the conflict, explain the tradeoff briefly, and ask the user which version to keep before rewriting.\n</principle>\n\n<principle name=\"group-by-purpose\">\nMove remaining guidance into separate files grouped by topic or behavior, not by author, chronology, or file location.\n</principle>\n\n<principle name=\"delete-bloat\">\nFlag redundant, vague, self-evident, or outdated instructions for deletion instead of preserving them in a new location.\n</principle>\n\n<principle name=\"prefer_progressive_disclosure\">\nKeep the root file as a router into narrower guidance. Detail belongs in follow-up docs that are only read when relevant.\n</principle>\n</essential_principles>\n\n<intake>\nAsk the user which mode they want:\n1. Review only\n2. Propose a rewrite\n3. Apply the refactor in the repo\n\nIf the user already gave enough context, skip extra questions and go straight to the matching workflow.\n</intake>\n\n<routing>\n<mode name=\"review-only\">workflows/audit-agents-md.md</mode>\n<mode name=\"propose-rewrite\">workflows/audit-agents-md.md</mode>\n<mode name=\"apply-refactor\">workflows/refactor-agents-md.md</mode>\n</routing>\n\n<reference_index>\nAll shared guidance lives in references/:\n\n**Principles and heuristics:** references/principles.md\n</reference_index>\n\n<workflows_index>\n<workflow name=\"audit-agents-md.md\">Review an AGENTS.md file, classify instructions, and propose a minimal split.</workflow>\n<workflow name=\"refactor-agents-md.md\">Inspect the repo and rewrite AGENTS.md files in place.</workflow>\n</workflows_index>\n\n<success_criteria>\nThe skill is complete when it can consistently:\n- identify contradictions before rewriting\n- keep root AGENTS.md content minimal\n- split topic-specific guidance into separate docs\n- flag redundant, vague, and stale instructions for deletion\n- produce a clear proposed file structure or apply it in the repo\n</success_criteria>\n\nFile v1.0.2:README.md\n\n# refactor-agents-md\n\nRefactor bloated AGENTS.md / CLAUDE.md into clean, topic-specific docs.\n\n## What it does\n\n`refactor-agents-md` takes a monolithic agent guidance file that has grown into a \"ball of mud\" and splits it into a minimal root file plus topic-specific follow-up documents using progressive disclosure.\n\n## When to use\n\n- Your AGENTS.md or CLAUDE.md has grown too large with contradictions and stale instructions\n- User asks to clean up, split, or review agent guidance files\n\n## How it works\n\n1. Analyze the existing file for sections, contradictions, and bloat\n2. Extract topic-specific content into separate focused documents\n3. Create a minimal root file that routes to topic docs on demand\n4. Remove contradictions and stale instructions\n\n## Key features\n\n- Progressive disclosure: agents only load what they need\n- Detects contradictions and redundancy\n- Preserves important rules while removing noise\n- Works with any agent config format (AGENTS.md, CLAUDE.md, etc.)\n\n---\n\n**Source**: [github.com/Fei2-Labs/skill-genie](https://github.com/Fei2-Labs/skill-genie)\n**Author**: [@clarezoe](https://x.com/clarezoe)\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn71ntcwxg33gv53ryabqt0vw981g9my\",\n  \"slug\": \"refactor-agents-md\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1781011308782\n}\n\nFile v1.0.2:references/principles.md\n\n<principles>\n<rule name=\"root_scope\">\nTreat the root AGENTS.md as a universal contract, not a knowledge dump. Keep only instructions that should apply to every task in the repository.\n</rule>\n\n<rule name=\"universal_content\">\nGood root content is usually limited to:\n- a one-sentence project description\n- package manager or workspace expectations if non-default\n- non-standard build, test, or typecheck commands\n- repository-wide safety constraints that matter for every task\n</rule>\n\n<rule name=\"split_triggers\">\nMove content out of the root file when it is specific to one domain, one workflow, or one tool. If only some tasks need it, it belongs elsewhere.\n</rule>\n\n<rule name=\"contradiction_handling\">\nWhen instructions conflict, preserve neither by default. Identify the exact conflict, explain the consequence of each option, and ask the user to choose.\n</rule>\n\n<rule name=\"bloat_signals\">\nTreat these as deletion candidates unless there is a strong reason to keep them:\n- obvious advice the agent already knows\n- duplicated instructions with slightly different wording\n- vague slogans that do not change behavior\n- stale references to paths, commands, or project state\n</rule>\n\n<rule name=\"file_organization\">\nPrefer a small root file with direct links to topic-specific docs. Name follow-up files by purpose, such as testing, formatting, release, or platform-specific guidance.\n</rule>\n\n<rule name=\"output_goal\">\nA good refactor leaves the root file shorter, clearer, and easier to scan, while the total guidance stays available in focused follow-up docs.\n</rule>\n</principles>\n\nFile v1.0.2:skill-card.md\n\n## Description:\n\nRefactors AGENTS.md files into a minimal root file plus topic-specific follow-up docs using progressive disclosure.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[clarezoe](https://clawhub.ai/user/clarezoe)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineers use this skill to review, split, or refactor oversized AGENTS.md or CLAUDE.md guidance into a minimal root file and focused topic documents.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Apply mode can intentionally change repository guidance files that future agents may read.\n\nMitigation: Use review or proposal mode first when instructions may conflict, and inspect proposed changes before applying them.\n\nRisk: Conflicting AGENTS.md or CLAUDE.md instructions can lead to incorrect refactoring decisions.\n\nMitigation: Pause on conflicts, present the exact disagreement, and require the user to choose which instruction to keep before rewriting.\n\n## Reference(s):\n\n- [Skill Genie repository](https://github.com/Fei2-Labs/skill-genie)\n- [Principles and heuristics](references/principles.md)\n- [ClawHub skill page](https://clawhub.ai/clarezoe/skills/refactor-agents-md)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Code, Configuration, Guidance]\n\n**Output Format:** [Markdown guidance, proposed file structures, and repository file edits when apply mode is requested]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May change AGENTS.md, CLAUDE.md, or related topic guidance files in apply mode.]\n\n## Skill Version(s):\n\n1.0.2 (source: SKILL.md frontmatter metadata and server release metadata)\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\nFile v1.0.2:workflows/audit-agents-md.md\n\n<required_reading>\nRead references/principles.md before starting.\n</required_reading>\n\n<process>\n1. Read the current AGENTS.md content and any nearby AGENTS.md files that merge into scope.\n2. Split each instruction into one of four buckets:\n   - root-essential\n   - topic-specific\n   - conflicting\n   - delete\n3. If you find conflicts, stop and present the exact conflict to the user before rewriting anything.\n4. If there are no blockers, draft a minimal root AGENTS.md structure and list the follow-up docs that should hold the removed guidance.\n5. Call out redundant, vague, or stale lines explicitly so the user can decide whether to delete them.\n</process>\n\n<success_criteria>\nThis workflow is complete when the user has either:\n- a clear audit of what to keep, move, and delete, or\n- a concise proposed file structure for a rewrite.\n</success_criteria>\n\nFile v1.0.2:workflows/refactor-agents-md.md\n\n<required_reading>\nRead references/principles.md before starting.\n</required_reading>\n\n<process>\n1. Inspect the repository to find all AGENTS.md files and determine which ones apply to the target area.\n2. Read the current root AGENTS.md and any inherited or nested instructions that affect it.\n3. Classify each line or section into:\n   - keep in root\n   - move to a topic doc\n   - delete\n   - ask the user about because it conflicts or depends on a choice\n4. If any conflicts exist, pause and ask the user which instruction to keep.\n5. Draft the new root AGENTS.md so it stays minimal and points to the topic docs.\n6. Create or update the topic docs with the moved guidance, keeping each file narrowly scoped.\n7. Verify the result by checking that the root file reads cleanly on its own and that no important guidance was lost.\n</process>\n\n<success_criteria>\nThis workflow is complete when the repo has either:\n- a rewritten AGENTS.md structure with the important guidance preserved and the root file minimized, or\n- a precise blocker list for the user to resolve before rewriting.\n</success_criteria>\n\nArchive v1.0.1: 7 files, 6246 bytes\n\nFiles: README.md (1131b), references/principles.md (1587b), skill-card.md (2386b), SKILL.md (3702b), workflows/audit-agents-md.md (859b), workflows/refactor-agents-md.md (1102b), _meta.json (137b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: \"refactor-agents-md\"\ndescription: \"Refactors AGENTS.md files into a minimal root file plus topic-specific follow-up docs using progressive disclosure. Use when cleaning up, splitting, or reviewing AGENTS.md / CLAUDE.md guidance — or when the file has grown into a \\\"ball of mud\\\" with contradictions, bloat, and stale instructions.\"\nlicense: \"MIT-0\"\nmetadata: {\"openclaw\":{\"emoji\":\"🧹\",\"homepage\":\"https://github.com/Fei2-Labs/skill-genie\"},\"category\":\"developer-tools\",\"author\":\"Skill Genie\",\"tags\":[\"agents-md\",\"claude-md\",\"refactoring\",\"progressive-disclosure\",\"ai-config\"],\"version\":\"1.0.1\",\"license\":\"MIT-0\",\"hermes\":{\"tags\":[\"agents-md\",\"claude-md\",\"refactoring\",\"progressive-disclosure\",\"ai-config\"]}}\n---\n\n<objective>\nRefactor AGENTS.md files so the root file stays small, stable, and broadly useful while detailed guidance moves into focused follow-up docs. The skill helps identify contradictions, separate essentials from bloat, and produce a clearer instruction hierarchy that is easier for agents to follow.\n</objective>\n\n<quick_start>\n1. Identify whether the user wants a review, a rewrite proposal, or an in-repo refactor.\n2. Read the current AGENTS.md content and classify each instruction as root-essential, topic-specific, conflicting, redundant, vague, or stale.\n3. Keep only universal instructions in the root file, move the rest into topic docs, and surface any contradictions before editing.\n</quick_start>\n\n<essential_principles>\n<principle name=\"keep-root-minimal\">\nThe root AGENTS.md should contain only what applies to every task: a one-line project description, package manager expectations if non-default, non-standard build or typecheck commands, and truly universal constraints.\n</principle>\n\n<principle name=\"resolve-conflicts-first\">\nIf two instructions disagree, do not silently merge them. Surface the conflict, explain the tradeoff briefly, and ask the user which version to keep before rewriting.\n</principle>\n\n<principle name=\"group-by-purpose\">\nMove remaining guidance into separate files grouped by topic or behavior, not by author, chronology, or file location.\n</principle>\n\n<principle name=\"delete-bloat\">\nFlag redundant, vague, self-evident, or outdated instructions for deletion instead of preserving them in a new location.\n</principle>\n\n<principle name=\"prefer_progressive_disclosure\">\nKeep the root file as a router into narrower guidance. Detail belongs in follow-up docs that are only read when relevant.\n</principle>\n</essential_principles>\n\n<intake>\nAsk the user which mode they want:\n1. Review only\n2. Propose a rewrite\n3. Apply the refactor in the repo\n\nIf the user already gave enough context, skip extra questions and go straight to the matching workflow.\n</intake>\n\n<routing>\n<mode name=\"review-only\">workflows/audit-agents-md.md</mode>\n<mode name=\"propose-rewrite\">workflows/audit-agents-md.md</mode>\n<mode name=\"apply-refactor\">workflows/refactor-agents-md.md</mode>\n</routing>\n\n<reference_index>\nAll shared guidance lives in references/:\n\n**Principles and heuristics:** references/principles.md\n</reference_index>\n\n<workflows_index>\n<workflow name=\"audit-agents-md.md\">Review an AGENTS.md file, classify instructions, and propose a minimal split.</workflow>\n<workflow name=\"refactor-agents-md.md\">Inspect the repo and rewrite AGENTS.md files in place.</workflow>\n</workflows_index>\n\n<success_criteria>\nThe skill is complete when it can consistently:\n- identify contradictions before rewriting\n- keep root AGENTS.md content minimal\n- split topic-specific guidance into separate docs\n- flag redundant, vague, and stale instructions for deletion\n- produce a clear proposed file structure or apply it in the repo\n</success_criteria>\n\nFile v1.0.1:README.md\n\n# refactor-agents-md\n\nRefactor bloated AGENTS.md / CLAUDE.md into clean, topic-specific docs.\n\n## What it does\n\n`refactor-agents-md` takes a monolithic agent guidance file that has grown into a \"ball of mud\" and splits it into a minimal root file plus topic-specific follow-up documents using progressive disclosure.\n\n## When to use\n\n- Your AGENTS.md or CLAUDE.md has grown too large with contradictions and stale instructions\n- User asks to clean up, split, or review agent guidance files\n\n## How it works\n\n1. Analyze the existing file for sections, contradictions, and bloat\n2. Extract topic-specific content into separate focused documents\n3. Create a minimal root file that routes to topic docs on demand\n4. Remove contradictions and stale instructions\n\n## Key features\n\n- Progressive disclosure: agents only load what they need\n- Detects contradictions and redundancy\n- Preserves important rules while removing noise\n- Works with any agent config format (AGENTS.md, CLAUDE.md, etc.)\n\n---\n\n**Source**: [github.com/Fei2-Labs/skill-genie](https://github.com/Fei2-Labs/skill-genie)\n**Author**: [@clarezoe](https://x.com/clarezoe)\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn71ntcwxg33gv53ryabqt0vw981g9my\",\n  \"slug\": \"refactor-agents-md\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1781010603642\n}\n\nFile v1.0.1:references/principles.md\n\n<principles>\n<rule name=\"root_scope\">\nTreat the root AGENTS.md as a universal contract, not a knowledge dump. Keep only instructions that should apply to every task in the repository.\n</rule>\n\n<rule name=\"universal_content\">\nGood root content is usually limited to:\n- a one-sentence project description\n- package manager or workspace expectations if non-default\n- non-standard build, test, or typecheck commands\n- repository-wide safety constraints that matter for every task\n</rule>\n\n<rule name=\"split_triggers\">\nMove content out of the root file when it is specific to one domain, one workflow, or one tool. If only some tasks need it, it belongs elsewhere.\n</rule>\n\n<rule name=\"contradiction_handling\">\nWhen instructions conflict, preserve neither by default. Identify the exact conflict, explain the consequence of each option, and ask the user to choose.\n</rule>\n\n<rule name=\"bloat_signals\">\nTreat these as deletion candidates unless there is a strong reason to keep them:\n- obvious advice the agent already knows\n- duplicated instructions with slightly different wording\n- vague slogans that do not change behavior\n- stale references to paths, commands, or project state\n</rule>\n\n<rule name=\"file_organization\">\nPrefer a small root file with direct links to topic-specific docs. Name follow-up files by purpose, such as testing, formatting, release, or platform-specific guidance.\n</rule>\n\n<rule name=\"output_goal\">\nA good refactor leaves the root file shorter, clearer, and easier to scan, while the total guidance stays available in focused follow-up docs.\n</rule>\n</principles>\n\nFile v1.0.1:skill-card.md\n\n## Description: <br>\nRefactors AGENTS.md files into a minimal root file plus topic-specific follow-up docs using progressive disclosure. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[clarezoe](https://clawhub.ai/user/clarezoe) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and maintainers use this skill to review, split, and refactor bloated AGENTS.md or CLAUDE.md guidance into a small root file plus focused topic documents. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Applied refactors can remove or change repository-wide agent guidance, affecting future agent behavior. <br>\nMitigation: Review the keep, move, delete, and conflict classifications and inspect diffs before accepting file changes. <br>\nRisk: Conflicting instructions can lead to ambiguous or incorrect guidance if merged without a decision. <br>\nMitigation: Pause on conflicts and require an explicit user choice before rewriting. <br>\nRisk: Using the skill in a privileged maintainer context can affect repository instructions and downstream automation. <br>\nMitigation: Install and run it only in an appropriate maintainer context, and review generated changes before deployment. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/clarezoe/refactor-agents-md) <br>\n- [Project homepage](https://github.com/Fei2-Labs/skill-genie) <br>\n- [Principles and heuristics](references/principles.md) <br>\n- [Audit workflow](workflows/audit-agents-md.md) <br>\n- [Refactor workflow](workflows/refactor-agents-md.md) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, configuration, guidance] <br>\n**Output Format:** [Markdown guidance and repository file edits when refactoring is applied] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May produce a review, a rewrite proposal, or in-repository AGENTS.md and topic-document updates depending on the selected mode.] <br>\n\n## Skill Version(s): <br>\n1.0.1 (source: frontmatter and 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\nFile v1.0.1:workflows/audit-agents-md.md\n\n<required_reading>\nRead references/principles.md before starting.\n</required_reading>\n\n<process>\n1. Read the current AGENTS.md content and any nearby AGENTS.md files that merge into scope.\n2. Split each instruction into one of four buckets:\n   - root-essential\n   - topic-specific\n   - conflicting\n   - delete\n3. If you find conflicts, stop and present the exact conflict to the user before rewriting anything.\n4. If there are no blockers, draft a minimal root AGENTS.md structure and list the follow-up docs that should hold the removed guidance.\n5. Call out redundant, vague, or stale lines explicitly so the user can decide whether to delete them.\n</process>\n\n<success_criteria>\nThis workflow is complete when the user has either:\n- a clear audit of what to keep, move, and delete, or\n- a concise proposed file structure for a rewrite.\n</success_criteria>\n\nFile v1.0.1:workflows/refactor-agents-md.md\n\n<required_reading>\nRead references/principles.md before starting.\n</required_reading>\n\n<process>\n1. Inspect the repository to find all AGENTS.md files and determine which ones apply to the target area.\n2. Read the current root AGENTS.md and any inherited or nested instructions that affect it.\n3. Classify each line or section into:\n   - keep in root\n   - move to a topic doc\n   - delete\n   - ask the user about because it conflicts or depends on a choice\n4. If any conflicts exist, pause and ask the user which instruction to keep.\n5. Draft the new root AGENTS.md so it stays minimal and points to the topic docs.\n6. Create or update the topic docs with the moved guidance, keeping each file narrowly scoped.\n7. Verify the result by checking that the root file reads cleanly on its own and that no important guidance was lost.\n</process>\n\n<success_criteria>\nThis workflow is complete when the repo has either:\n- a rewritten AGENTS.md structure with the important guidance preserved and the root file minimized, or\n- a precise blocker list for the user to resolve before rewriting.\n</success_criteria>\n\nArchive v1.0.0: 6 files, 5322 bytes\n\nFiles: references/principles.md (1587b), skill-card.md (1886b), SKILL.md (3602b), workflows/audit-agents-md.md (859b), workflows/refactor-agents-md.md (1102b), _meta.json (137b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: refactor-agents-md\ndescription: Refactors AGENTS.md files into a minimal root file plus topic-specific follow-up docs using progressive disclosure. Use when cleaning up, splitting, or reviewing AGENTS.md / CLAUDE.md guidance — or when the file has grown into a \"ball of mud\" with contradictions, bloat, and stale instructions.\nversion: 1.0.0\nlicense: MIT-0\nmetadata:\n  openclaw:\n    emoji: \"🧹\"\n    homepage: \"https://github.com/Fei2-Labs/skill-genie\"\n  category: \"developer-tools\"\n  author: \"Skill Genie\"\n  tags:\n    - agents-md\n    - claude-md\n    - refactoring\n    - progressive-disclosure\n    - ai-config\n---\n\n<objective>\nRefactor AGENTS.md files so the root file stays small, stable, and broadly useful while detailed guidance moves into focused follow-up docs. The skill helps identify contradictions, separate essentials from bloat, and produce a clearer instruction hierarchy that is easier for agents to follow.\n</objective>\n\n<quick_start>\n1. Identify whether the user wants a review, a rewrite proposal, or an in-repo refactor.\n2. Read the current AGENTS.md content and classify each instruction as root-essential, topic-specific, conflicting, redundant, vague, or stale.\n3. Keep only universal instructions in the root file, move the rest into topic docs, and surface any contradictions before editing.\n</quick_start>\n\n<essential_principles>\n<principle name=\"keep-root-minimal\">\nThe root AGENTS.md should contain only what applies to every task: a one-line project description, package manager expectations if non-default, non-standard build or typecheck commands, and truly universal constraints.\n</principle>\n\n<principle name=\"resolve-conflicts-first\">\nIf two instructions disagree, do not silently merge them. Surface the conflict, explain the tradeoff briefly, and ask the user which version to keep before rewriting.\n</principle>\n\n<principle name=\"group-by-purpose\">\nMove remaining guidance into separate files grouped by topic or behavior, not by author, chronology, or file location.\n</principle>\n\n<principle name=\"delete-bloat\">\nFlag redundant, vague, self-evident, or outdated instructions for deletion instead of preserving them in a new location.\n</principle>\n\n<principle name=\"prefer_progressive_disclosure\">\nKeep the root file as a router into narrower guidance. Detail belongs in follow-up docs that are only read when relevant.\n</principle>\n</essential_principles>\n\n<intake>\nAsk the user which mode they want:\n1. Review only\n2. Propose a rewrite\n3. Apply the refactor in the repo\n\nIf the user already gave enough context, skip extra questions and go straight to the matching workflow.\n</intake>\n\n<routing>\n<mode name=\"review-only\">workflows/audit-agents-md.md</mode>\n<mode name=\"propose-rewrite\">workflows/audit-agents-md.md</mode>\n<mode name=\"apply-refactor\">workflows/refactor-agents-md.md</mode>\n</routing>\n\n<reference_index>\nAll shared guidance lives in references/:\n\n**Principles and heuristics:** references/principles.md\n</reference_index>\n\n<workflows_index>\n<workflow name=\"audit-agents-md.md\">Review an AGENTS.md file, classify instructions, and propose a minimal split.</workflow>\n<workflow name=\"refactor-agents-md.md\">Inspect the repo and rewrite AGENTS.md files in place.</workflow>\n</workflows_index>\n\n<success_criteria>\nThe skill is complete when it can consistently:\n- identify contradictions before rewriting\n- keep root AGENTS.md content minimal\n- split topic-specific guidance into separate docs\n- flag redundant, vague, and stale instructions for deletion\n- produce a clear proposed file structure or apply it in the repo\n</success_criteria>\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn71ntcwxg33gv53ryabqt0vw981g9my\",\n  \"slug\": \"refactor-agents-md\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1778626292084\n}\n\nFile v1.0.0:references/principles.md\n\n<principles>\n<rule name=\"root_scope\">\nTreat the root AGENTS.md as a universal contract, not a knowledge dump. Keep only instructions that should apply to every task in the repository.\n</rule>\n\n<rule name=\"universal_content\">\nGood root content is usually limited to:\n- a one-sentence project description\n- package manager or workspace expectations if non-default\n- non-standard build, test, or typecheck commands\n- repository-wide safety constraints that matter for every task\n</rule>\n\n<rule name=\"split_triggers\">\nMove content out of the root file when it is specific to one domain, one workflow, or one tool. If only some tasks need it, it belongs elsewhere.\n</rule>\n\n<rule name=\"contradiction_handling\">\nWhen instructions conflict, preserve neither by default. Identify the exact conflict, explain the consequence of each option, and ask the user to choose.\n</rule>\n\n<rule name=\"bloat_signals\">\nTreat these as deletion candidates unless there is a strong reason to keep them:\n- obvious advice the agent already knows\n- duplicated instructions with slightly different wording\n- vague slogans that do not change behavior\n- stale references to paths, commands, or project state\n</rule>\n\n<rule name=\"file_organization\">\nPrefer a small root file with direct links to topic-specific docs. Name follow-up files by purpose, such as testing, formatting, release, or platform-specific guidance.\n</rule>\n\n<rule name=\"output_goal\">\nA good refactor leaves the root file shorter, clearer, and easier to scan, while the total guidance stays available in focused follow-up docs.\n</rule>\n</principles>\n\nFile v1.0.0:skill-card.md\n\n## Description: <br>\nRefactors AGENTS.md files into a minimal root file plus topic-specific follow-up docs using progressive disclosure. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[clarezoe](https://clawhub.ai/user/clarezoe) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and engineers use this skill to audit, propose, or apply refactors to AGENTS.md and CLAUDE.md guidance so repository-wide instructions stay minimal while detailed guidance moves into focused follow-up docs. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill can change persistent agent instructions in a repository. <br>\nMitigation: Use review or propose mode first when possible, and inspect the resulting diff before accepting apply-refactor changes. <br>\n\n\n## Reference(s): <br>\n- [Refactor AGENTS.md on ClawHub](https://clawhub.ai/clarezoe/refactor-agents-md) <br>\n- [Project homepage](https://github.com/Fei2-Labs/skill-genie) <br>\n- [Principles and heuristics](references/principles.md) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance] <br>\n**Output Format:** [Markdown guidance, proposed file structures, and repository file edits when apply-refactor mode is selected] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May modify AGENTS.md or related guidance files when the user selects apply-refactor mode.] <br>\n\n## Skill Version(s): <br>\n1.0.0 (source: frontmatter and 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\nFile v1.0.0:workflows/audit-agents-md.md\n\n<required_reading>\nRead references/principles.md before starting.\n</required_reading>\n\n<process>\n1. Read the current AGENTS.md content and any nearby AGENTS.md files that merge into scope.\n2. Split each instruction into one of four buckets:\n   - root-essential\n   - topic-specific\n   - conflicting\n   - delete\n3. If you find conflicts, stop and present the exact conflict to the user before rewriting anything.\n4. If there are no blockers, draft a minimal root AGENTS.md structure and list the follow-up docs that should hold the removed guidance.\n5. Call out redundant, vague, or stale lines explicitly so the user can decide whether to delete them.\n</process>\n\n<success_criteria>\nThis workflow is complete when the user has either:\n- a clear audit of what to keep, move, and delete, or\n- a concise proposed file structure for a rewrite.\n</success_criteria>\n\nFile v1.0.0:workflows/refactor-agents-md.md\n\n<required_reading>\nRead references/principles.md before starting.\n</required_reading>\n\n<process>\n1. Inspect the repository to find all AGENTS.md files and determine which ones apply to the target area.\n2. Read the current root AGENTS.md and any inherited or nested instructions that affect it.\n3. Classify each line or section into:\n   - keep in root\n   - move to a topic doc\n   - delete\n   - ask the user about because it conflicts or depends on a choice\n4. If any conflicts exist, pause and ask the user which instruction to keep.\n5. Draft the new root AGENTS.md so it stays minimal and points to the topic docs.\n6. Create or update the topic docs with the moved guidance, keeping each file narrowly scoped.\n7. Verify the result by checking that the root file reads cleanly on its own and that no important guidance was lost.\n</process>\n\n<success_criteria>\nThis workflow is complete when the repo has either:\n- a rewritten AGENTS.md structure with the important guidance preserved and the root file minimized, or\n- a precise blocker list for the user to resolve before rewriting.\n</success_criteria>","readmeExcerpt":"Skill: Refactor Agents Md Owner: clarezoe Summary: Refactors AGENTS.md files into a minimal root file plus topic-specific follow-up docs using progressive disclosure. Use when cleaning up, splitting, or revie... Tags: agents-md:1.0.2, ai-config:1.0.2, claude-md:1.0.2, developer-tools:1.0.0, latest:1.0.2, progressive-disclosure:1.0.2, refactoring:1.0.2 Version history: v1.0.2 | 2026-06-09T13:21:48.782Z | user Add Open","codeSnippets":[],"executableExamples":[],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: \"refactor-agents-md\"\ndescription: \"Refactors AGENTS.md files into a minimal root file plus topic-specific follow-up docs using progressive disclosure. Use when cleaning up, splitting, or reviewing AGENTS.md / CLAUDE.md guidance — or when the file has grown into a \\\"ball of mud\\\" with contradictions, bloat, and stale instructions.\"\nlicense: \"MIT-0\"\nmetadata: {\"openclaw\":{\"emoji\":\"🧹\",\"homepage\":\"https://github.com/Fei2-Labs/skill-genie\"},\"category\":\"developer-tools\",\"author\":\"Skill Genie\",\"tags\":[\"agents-md\",\"claude-md\",\"refactoring\",\"progressive-disclosure\",\"ai-config\"],\"version\":\"1.0.2\",\"license\":\"MIT-0\",\"hermes\":{\"tags\":[\"agents-md\",\"claude-md\",\"refactoring\",\"progressive-disclosure\",\"ai-config\"]}}\n---\n\n<objective>\nRefactor AGENTS.md files so the root file stays small, stable, and broadly useful while detailed guidance moves into focused follow-up docs. The skill helps identify contradictions, separate essentials from bloat, and produce a clearer instruction hierarchy that is easier for agents to follow.\n</objective>\n\n<quick_start>\n1. Identify whether the user wants a review, a rewrite proposal, or an in-repo refactor.\n2. Read the current AGENTS.md content and classify each instruction as root-essential, topic-specific, conflicting, redundant, vague, or stale.\n3. Keep only universal instructions in the root file, move the rest into topic docs, and surface any contradictions before editing.\n</quick_start>\n\n<essential_principles>\n<principle name=\"keep-root-minimal\">\nThe root AGENTS.md should contain only what applies to every task: a one-line project description, package manager expectations if non-default, non-standard build or typecheck commands, and truly universal constraints.\n</principle>\n\n<principle name=\"resolve-conflicts-first\">\nIf two instructions disagree, do not silently merge them. Surface the conflict, explain the tradeoff briefly, and ask the user which version to keep before rewriting.\n</principle>\n\n<principle name=\"group-by-purpose\">\nMove remaining guidance into separate files grouped by topic or behavior, not by author, chronology, or file location.\n</principle>\n\n<principle name=\"delete-bloat\">\nFlag redundant, vague, self-evident, or outdated instructions for deletion instead of preserving them in a new location.\n</principle>\n\n<principle name=\"prefer_progressive_disclosure\">\nKeep the root file as a router into narrower guidance. Detail belongs in follow-up docs that are only read when relevant.\n</principle>\n</essential_principles>\n\n<intake>\nAsk the user which mode they want:\n1. Review only\n2. Propose a rewrite\n3. Apply the refactor in the repo\n\nIf the user already gave enough context, skip extra questions and go straight to the matching workflow.\n</intake>\n\n<routing>\n<mode name=\"review-only\">workflows/audit-agents-md.md</mode>\n<mode name=\"propose-rewrite\">workflows/audit-agents-md.md</mode>\n<mode name=\"apply-refactor\">workflows/refactor-agents-md.md</mode>\n</routing>\n\n<reference_index>\nAll shared guidance lives in refere"},{"path":"README.md","content":"# refactor-agents-md\n\nRefactor bloated AGENTS.md / CLAUDE.md into clean, topic-specific docs.\n\n## What it does\n\n`refactor-agents-md` takes a monolithic agent guidance file that has grown into a \"ball of mud\" and splits it into a minimal root file plus topic-specific follow-up documents using progressive disclosure.\n\n## When to use\n\n- Your AGENTS.md or CLAUDE.md has grown too large with contradictions and stale instructions\n- User asks to clean up, split, or review agent guidance files\n\n## How it works\n\n1. Analyze the existing file for sections, contradictions, and bloat\n2. Extract topic-specific content into separate focused documents\n3. Create a minimal root file that routes to topic docs on demand\n4. Remove contradictions and stale instructions\n\n## Key features\n\n- Progressive disclosure: agents only load what they need\n- Detects contradictions and redundancy\n- Preserves important rules while removing noise\n- Works with any agent config format (AGENTS.md, CLAUDE.md, etc.)\n\n---\n\n**Source**: [github.com/Fei2-Labs/skill-genie](https://github.com/Fei2-Labs/skill-genie)\n**Author**: [@clarezoe](https://x.com/clarezoe)"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn71ntcwxg33gv53ryabqt0vw981g9my\",\n  \"slug\": \"refactor-agents-md\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1781011308782\n}"},{"path":"references/principles.md","content":"<principles>\n<rule name=\"root_scope\">\nTreat the root AGENTS.md as a universal contract, not a knowledge dump. Keep only instructions that should apply to every task in the repository.\n</rule>\n\n<rule name=\"universal_content\">\nGood root content is usually limited to:\n- a one-sentence project description\n- package manager or workspace expectations if non-default\n- non-standard build, test, or typecheck commands\n- repository-wide safety constraints that matter for every task\n</rule>\n\n<rule name=\"split_triggers\">\nMove content out of the root file when it is specific to one domain, one workflow, or one tool. If only some tasks need it, it belongs elsewhere.\n</rule>\n\n<rule name=\"contradiction_handling\">\nWhen instructions conflict, preserve neither by default. Identify the exact conflict, explain the consequence of each option, and ask the user to choose.\n</rule>\n\n<rule name=\"bloat_signals\">\nTreat these as deletion candidates unless there is a strong reason to keep them:\n- obvious advice the agent already knows\n- duplicated instructions with slightly different wording\n- vague slogans that do not change behavior\n- stale references to paths, commands, or project state\n</rule>\n\n<rule name=\"file_organization\">\nPrefer a small root file with direct links to topic-specific docs. Name follow-up files by purpose, such as testing, formatting, release, or platform-specific guidance.\n</rule>\n\n<rule name=\"output_goal\">\nA good refactor leaves the root file shorter, clearer, and easier to scan, while the total guidance stays available in focused follow-up docs.\n</rule>\n</principles>"},{"path":"skill-card.md","content":"## Description:\n\nRefactors AGENTS.md files into a minimal root file plus topic-specific follow-up docs using progressive disclosure.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[clarezoe](https://clawhub.ai/user/clarezoe)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineers use this skill to review, split, or refactor oversized AGENTS.md or CLAUDE.md guidance into a minimal root file and focused topic documents.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Apply mode can intentionally change repository guidance files that future agents may read.\n\nMitigation: Use review or proposal mode first when instructions may conflict, and inspect proposed changes before applying them.\n\nRisk: Conflicting AGENTS.md or CLAUDE.md instructions can lead to incorrect refactoring decisions.\n\nMitigation: Pause on conflicts, present the exact disagreement, and require the user to choose which instruction to keep before rewriting.\n\n## Reference(s):\n\n- [Skill Genie repository](https://github.com/Fei2-Labs/skill-genie)\n- [Principles and heuristics](references/principles.md)\n- [ClawHub skill page](https://clawhub.ai/clarezoe/skills/refactor-agents-md)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Code, Configuration, Guidance]\n\n**Output Format:** [Markdown guidance, proposed file structures, and repository file edits when apply mode is requested]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May change AGENTS.md, CLAUDE.md, or related topic guidance files in apply mode.]\n\n## Skill Version(s):\n\n1.0.2 (source: SKILL.md frontmatter metadata and server release metadata)\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."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":null,"editorialQuality":{"score":100,"threshold":65,"status":"thin","wordCount":1493,"uniquenessScore":42,"reasons":["uniqueness-below-45"]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T18:42:22.770Z","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":"2026-10-11T18:42:22.770Z","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":"2026-10-11T21:50:44.278Z","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"}]}}}