[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CC2G4CB8CSD6KX01XANE3Z":3,"skill-same:01M6CC2G4CB8CSD6KX01XANE3Z":62},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":30,"linkOnly":31,"markdownContent":32,"markdownBody":33,"frontMatter":34,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":6,"ownerHtmlUrl":40,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":41,"install":42,"resources":55},"01M6CC2G4CB8CSD6KX01XANE3Z","review-skill-improver",null,"Analyzes feedback logs to identify patterns and suggest improvements to review skills. Use when you have accumulated feedback data and want to improve review accuracy.","ray-manaloto\u002Fmacos-development-environment","ray-manaloto","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F227192835?v=4","01M6CBR7J13ZA01X5YB1A1QRJP","01M6CBR7P0S3NS8ZV81JYNST14",1,"MIT","https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fskills\u002Freview-skill-improver\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29],"review","review skill improver","logs","data","improve","feedback","use","2026-11-10 10:12:30",false,"---\nname: review-skill-improver\ndescription: Analyzes feedback logs to identify patterns and suggest improvements to review skills. Use when you have accumulated feedback data and want to improve review accuracy.\n---\n\n# Review Skill Improver\n\n## Purpose\n\nAnalyzes structured feedback logs to:\n1. Identify rules that produce false positives (high REJECT rate)\n2. Identify missing rules (issues that should have been caught)\n3. Suggest specific skill modifications\n\n## Input\n\nFeedback log in enhanced schema format (see `review-feedback-schema` skill).\n\n## Analysis Process\n\n### Step 1: Aggregate by Rule Source\n\n```\nFor each unique rule_source:\n  - Count total issues flagged\n  - Count ACCEPT vs REJECT\n  - Calculate rejection rate\n  - Extract rejection rationales\n```\n\n### Step 2: Identify High-Rejection Rules\n\nRules with >30% rejection rate warrant investigation:\n- Read the rejection rationales\n- Identify common themes\n- Determine if rule needs refinement or exception\n\n### Step 3: Pattern Analysis\n\nGroup rejections by rationale theme:\n- \"Linter already handles this\" -> Add linter verification step\n- \"Framework supports this pattern\" -> Add exception to skill\n- \"Intentional design decision\" -> Add codebase context check\n- \"Wrong code path assumed\" -> Add code tracing step\n\n### Step 4: Generate Improvement Recommendations\n\nFor each identified issue, produce:\n\n```markdown\n## Recommendation: [SHORT_TITLE]\n\n**Affected Skill:** `skill-name\u002FSKILL.md` or `skill-name\u002Freferences\u002Ffile.md`\n\n**Problem:** [What's causing false positives]\n\n**Evidence:**\n- [X] rejections with rationale \"[common theme]\"\n- Example: [file:line] - [issue] - [rationale]\n\n**Proposed Fix:**\n```markdown\n[Exact text to add\u002Fmodify in the skill]\n```\n\n**Expected Impact:** Reduce false positive rate for [rule] from X% to Y%\n```\n\n## Output Format\n\n```markdown\n# Review Skill Improvement Report\n\n## Summary\n- Feedback entries analyzed: [N]\n- Unique rules triggered: [N]\n- High-rejection rules identified: [N]\n- Recommendations generated: [N]\n\n## High-Rejection Rules\n\n| Rule Source | Total | Rejected | Rate | Theme |\n|-------------|-------|----------|------|-------|\n| ... | ... | ... | ... | ... |\n\n## Recommendations\n\n[Numbered list of recommendations in format above]\n\n## Rules Performing Well\n\n[Rules with \u003C10% rejection rate - preserve these]\n```\n\n## Usage\n\n```bash\n# In a project with feedback log\n\u002Freview-skill-improver --log .feedback-log.csv --output improvement-report.md\n```\n\n## Example Analysis\n\nGiven this feedback data:\n\n```csv\nrule_source,verdict,rationale\npython-code-review:line-length,REJECT,ruff check passes\npython-code-review:line-length,REJECT,no E501 violation\npython-code-review:line-length,REJECT,linter config allows 120\npython-code-review:line-length,ACCEPT,fixed long line\npydantic-ai-common-pitfalls:tool-decorator,REJECT,docs support raw functions\npython-code-review:type-safety,ACCEPT,added type annotation\npython-code-review:type-safety,ACCEPT,fixed Any usage\n```\n\nAnalysis output:\n\n```markdown\n# Review Skill Improvement Report\n\n## Summary\n- Feedback entries analyzed: 7\n- Unique rules triggered: 3\n- High-rejection rules identified: 2\n- Recommendations generated: 2\n\n## High-Rejection Rules\n\n| Rule Source | Total | Rejected | Rate | Theme |\n|-------------|-------|----------|------|-------|\n| python-code-review:line-length | 4 | 3 | 75% | linter handles this |\n| pydantic-ai-common-pitfalls:tool-decorator | 1 | 1 | 100% | framework supports pattern |\n\n## Recommendations\n\n### 1. Add Linter Verification for Line Length\n\n**Affected Skill:** `commands\u002Freview-python.md`\n\n**Problem:** Flagging line length issues that linters confirm don't exist\n\n**Evidence:**\n- 3 rejections with rationale \"linter passes\u002Fhandles this\"\n- Example: amelia\u002Fdrivers\u002Fapi\u002Fopenai.py:102 - Line too long - ruff check passes\n\n**Proposed Fix:**\nAdd step to run `ruff check` before manual review. If linter passes for line length, do not flag manually.\n\n**Expected Impact:** Reduce false positive rate for line-length from 75% to \u003C10%\n\n### 2. Add Raw Function Tool Registration Exception\n\n**Affected Skill:** `skills\u002Fpydantic-ai-common-pitfalls\u002FSKILL.md`\n\n**Problem:** Flagging valid pydantic-ai pattern as error\n\n**Evidence:**\n- 1 rejection with rationale \"docs support raw functions\"\n\n**Proposed Fix:**\nAdd \"Valid Patterns\" section documenting that passing functions with RunContext to Agent(tools=[...]) is valid.\n\n**Expected Impact:** Eliminate false positives for this pattern\n\n## Rules Performing Well\n\n| Rule Source | Total | Accepted | Rate |\n|-------------|-------|----------|------|\n| python-code-review:type-safety | 2 | 2 | 100% |\n```\n\n## Future: Automated Skill Updates\n\nOnce confidence is high, this skill can:\n1. Generate PRs to beagle with skill improvements\n2. Track improvement impact over time\n3. A\u002FB test rule variations\n\n## Feedback Loop\n\n```\nReview Code -> Log Outcomes -> Analyze Patterns -> Improve Skills -> Better Reviews\n     ^                                                                    |\n     +--------------------------------------------------------------------+\n```\n\nThis creates a continuous improvement cycle where review quality improves based on empirical data rather than guesswork.\n","# Review Skill Improver\n\n## Purpose\n\nAnalyzes structured feedback logs to:\n1. Identify rules that produce false positives (high REJECT rate)\n2. Identify missing rules (issues that should have been caught)\n3. Suggest specific skill modifications\n\n## Input\n\nFeedback log in enhanced schema format (see `review-feedback-schema` skill).\n\n## Analysis Process\n\n### Step 1: Aggregate by Rule Source\n\n```\nFor each unique rule_source:\n  - Count total issues flagged\n  - Count ACCEPT vs REJECT\n  - Calculate rejection rate\n  - Extract rejection rationales\n```\n\n### Step 2: Identify High-Rejection Rules\n\nRules with >30% rejection rate warrant investigation:\n- Read the rejection rationales\n- Identify common themes\n- Determine if rule needs refinement or exception\n\n### Step 3: Pattern Analysis\n\nGroup rejections by rationale theme:\n- \"Linter already handles this\" -> Add linter verification step\n- \"Framework supports this pattern\" -> Add exception to skill\n- \"Intentional design decision\" -> Add codebase context check\n- \"Wrong code path assumed\" -> Add code tracing step\n\n### Step 4: Generate Improvement Recommendations\n\nFor each identified issue, produce:\n\n```markdown\n## Recommendation: [SHORT_TITLE]\n\n**Affected Skill:** `skill-name\u002FSKILL.md` or `skill-name\u002Freferences\u002Ffile.md`\n\n**Problem:** [What's causing false positives]\n\n**Evidence:**\n- [X] rejections with rationale \"[common theme]\"\n- Example: [file:line] - [issue] - [rationale]\n\n**Proposed Fix:**\n```markdown\n[Exact text to add\u002Fmodify in the skill]\n```\n\n**Expected Impact:** Reduce false positive rate for [rule] from X% to Y%\n```\n\n## Output Format\n\n```markdown\n# Review Skill Improvement Report\n\n## Summary\n- Feedback entries analyzed: [N]\n- Unique rules triggered: [N]\n- High-rejection rules identified: [N]\n- Recommendations generated: [N]\n\n## High-Rejection Rules\n\n| Rule Source | Total | Rejected | Rate | Theme |\n|-------------|-------|----------|------|-------|\n| ... | ... | ... | ... | ... |\n\n## Recommendations\n\n[Numbered list of recommendations in format above]\n\n## Rules Performing Well\n\n[Rules with \u003C10% rejection rate - preserve these]\n```\n\n## Usage\n\n```bash\n# In a project with feedback log\n\u002Freview-skill-improver --log .feedback-log.csv --output improvement-report.md\n```\n\n## Example Analysis\n\nGiven this feedback data:\n\n```csv\nrule_source,verdict,rationale\npython-code-review:line-length,REJECT,ruff check passes\npython-code-review:line-length,REJECT,no E501 violation\npython-code-review:line-length,REJECT,linter config allows 120\npython-code-review:line-length,ACCEPT,fixed long line\npydantic-ai-common-pitfalls:tool-decorator,REJECT,docs support raw functions\npython-code-review:type-safety,ACCEPT,added type annotation\npython-code-review:type-safety,ACCEPT,fixed Any usage\n```\n\nAnalysis output:\n\n```markdown\n# Review Skill Improvement Report\n\n## Summary\n- Feedback entries analyzed: 7\n- Unique rules triggered: 3\n- High-rejection rules identified: 2\n- Recommendations generated: 2\n\n## High-Rejection Rules\n\n| Rule Source | Total | Rejected | Rate | Theme |\n|-------------|-------|----------|------|-------|\n| python-code-review:line-length | 4 | 3 | 75% | linter handles this |\n| pydantic-ai-common-pitfalls:tool-decorator | 1 | 1 | 100% | framework supports pattern |\n\n## Recommendations\n\n### 1. Add Linter Verification for Line Length\n\n**Affected Skill:** `commands\u002Freview-python.md`\n\n**Problem:** Flagging line length issues that linters confirm don't exist\n\n**Evidence:**\n- 3 rejections with rationale \"linter passes\u002Fhandles this\"\n- Example: amelia\u002Fdrivers\u002Fapi\u002Fopenai.py:102 - Line too long - ruff check passes\n\n**Proposed Fix:**\nAdd step to run `ruff check` before manual review. If linter passes for line length, do not flag manually.\n\n**Expected Impact:** Reduce false positive rate for line-length from 75% to \u003C10%\n\n### 2. Add Raw Function Tool Registration Exception\n\n**Affected Skill:** `skills\u002Fpydantic-ai-common-pitfalls\u002FSKILL.md`\n\n**Problem:** Flagging valid pydantic-ai pattern as error\n\n**Evidence:**\n- 1 rejection with rationale \"docs support raw functions\"\n\n**Proposed Fix:**\nAdd \"Valid Patterns\" section documenting that passing functions with RunContext to Agent(tools=[...]) is valid.\n\n**Expected Impact:** Eliminate false positives for this pattern\n\n## Rules Performing Well\n\n| Rule Source | Total | Accepted | Rate |\n|-------------|-------|----------|------|\n| python-code-review:type-safety | 2 | 2 | 100% |\n```\n\n## Future: Automated Skill Updates\n\nOnce confidence is high, this skill can:\n1. Generate PRs to beagle with skill improvements\n2. Track improvement impact over time\n3. A\u002FB test rule variations\n\n## Feedback Loop\n\n```\nReview Code -> Log Outcomes -> Analyze Patterns -> Improve Skills -> Better Reviews\n     ^                                                                    |\n     +--------------------------------------------------------------------+\n```\n\nThis creates a continuous improvement cycle where review quality improves based on empirical data rather than guesswork.\n",{"name":5,"description":7},"main","716b17df3ef6719d88aeac180015008b7ddfff6f",".claude\u002Fskills\u002Fskills\u002Freview-skill-improver",0,"https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment","https:\u002F\u002Fgithub.com\u002Fray-manaloto","2026-08-03 16:55:50",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add ray-manaloto\u002Fmacos-development-environment --skill review-skill-improver",{"tool":48,"command":49},"bunx","bunx skills add ray-manaloto\u002Fmacos-development-environment --skill review-skill-improver",{"tool":51,"command":52},"pnpm","pnpm dlx skills add ray-manaloto\u002Fmacos-development-environment --skill review-skill-improver","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fskills\u002Freview-skill-improver\u002FSKILL.md",true,[56],{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"scripts\u002Frun.py","SCRIPT","脚本",15,"https:\u002F\u002Fgithub.com\u002Fjosephfung\u002Fcuria\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fimported-skills\u002Fwith-scripts\u002Fscripts\u002Frun.py",[63,81,99,116,136,150],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":70,"publishedAt":30},"01M6CC8DXNJ39YWERYTWCGGCGG","next-workflow-step","Use this skill when the user wants to transition to the next workflow step, wrap up a session cleanly, prepare a handoff, or says things like \"next step\", \"continue the workflow\", \"wrap up\", \"hand off\", \"move to the next phase\", \"what's next in embrace\", or \"prepare for \u002Fclear\". Also triggers when the current octo:embrace phase appears complete and no explicit next action is set.","https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002Frsm-subagents\u002Fplugins\u002Fworkflow-toolkit\u002Fskills\u002Fnext-workflow-step\u002FSKILL.md",[69],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[71,72,73,29,74,75,76,77,78,79,80],"next workflow step","workflow","up","session","user","wrap up","continue","handoff","prepare","SET",{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":30},"01M6CC8BRZBQHEBXGMKPDM422P","source-discovery","This skill should be used when the user asks to \"find sources\", \"discover URLs\", \"catalog a source\", \"classify a URL\", \"search for libraries\", \"check what exists\", or mentions source discovery, URL cataloging, source classification, or research source management.","https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002Frsm-subagents\u002Fplugins\u002Fresearch-review-toolkit\u002Fskills\u002Fsource-discovery\u002FSKILL.md",[],[88,89,90,91,92,93,94,95,96,75,97,98],"discovery","source discovery","research","libraries","search","classification","find","check","management","catalog","find sources",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":30},"01M6CC89CGJP69A0PS22G2H1FV","review-synthesis","This skill should be used when the user asks to \"summarize review findings\", \"prioritize fixes\", \"rank review issues\", \"combine reviewer feedback\", \"create action items from review\", or mentions review synthesis, finding prioritization, severity ranking, or review result summarization.","https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002Frsm-subagents\u002Fplugins\u002Fresearch-review-toolkit\u002Fskills\u002Freview-synthesis\u002FSKILL.md",[],[23,106,107,108,109,28,110,75,111,112,113,114,115],"review synthesis","Synthesis","prioritize","create action","reviewer","summarize","prioritization","create","issues","severity",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":125,"publishedAt":30},"01M6CC872EZ9GRJY0HRCG0RT2M","research-scoring","This skill should be used when the user asks to \"score research\", \"check research quality\", \"evaluate coverage\", \"measure improvement\", \"assess research completeness\", or mentions research scoring, quality metrics, coverage gaps, improvement baseline, or research pipeline status.","https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002Frsm-subagents\u002Fplugins\u002Fresearch-review-toolkit\u002Fskills\u002Fresearch-scoring\u002FSKILL.md",[122],{"categoryNo":123,"categoryName":124,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",[126,90,127,128,129,130,131,132,95,75,133,134,135],"research scoring","status","coverage gaps","metrics","pipeline","baseline","quality","coverage","pipeline status","research quality",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":30},"01M6CC852HSDS1FE4EJAT0RHGR","notebooklm-integration","This skill should be used when the user asks to \"ingest into NotebookLM\", \"query NotebookLM\", \"add sources to notebook\", \"cross-source synthesis\", \"check stale sources\", or mentions NotebookLM, notebook integration, source ingestion, or knowledge consolidation.","https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002Frsm-subagents\u002Fplugins\u002Fresearch-review-toolkit\u002Fskills\u002Fnotebooklm-integration\u002FSKILL.md",[],[143,144,145,146,95,75,147,148,149,107],"notebooklm integration","notebooklm","integration","knowledge","ingestion","ingest","stale",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":157,"publishedAt":30},"01M6CC82Z4V3205KCJWQZPS2VG","evidence-synthesis","This skill should be used when the user asks to \"synthesize findings\", \"combine research\", \"cross-reference sources\", \"summarize evidence\", \"write a deep review\", or mentions evidence synthesis, finding consolidation, cross-source analysis, or research summarization.","https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002Frsm-subagents\u002Fplugins\u002Fresearch-review-toolkit\u002Fskills\u002Fevidence-synthesis\u002FSKILL.md",[156],{"categoryNo":123,"categoryName":124,"taxonomyType":20,"taxonomyTypeDesc":21},[158,107,159,111,90,160,161,162,75,163,23],"evidence synthesis","evidence","deep review","analysis","write","reference"]