[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CBRS5MR2G2VAV07R0MNPMY":3,"skill-same:01M6CBRS5MR2G2VAV07R0MNPMY":76},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":52,"install":53,"resources":65},"01M6CBRS5MR2G2VAV07R0MNPMY","autonomous-fix-review",null,"Run autonomous multi-model code review on a finding. Invokes claude\u002Fcodex\u002Fgemini via reviewd, evaluates consensus, and auto-commits or escalates to human.","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.agents\u002Fskills\u002Fautonomous-fix-review\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"review","autonomous","fix","autonomous fix review","code review","gemini","codex","run","code","file","commits","model","consensus","auto","multi-model","2026-11-10 10:12:30",false,"---\nname: autonomous-fix-review\ndescription: Run autonomous multi-model code review on a finding. Invokes claude\u002Fcodex\u002Fgemini via reviewd, evaluates consensus, and auto-commits or escalates to human.\nuser-invocable: true\nargument-hint: \u003Cfinding-file-or-description>\ncontext: fork\n---\n\n# Autonomous Fix-Review Pipeline\n\nGive it a finding, walk away, come back to a committed fix that passed multi-model review.\n\n## Usage\n\n```\n\u002Fautonomous-fix-review \"Fix the null pointer in src\u002Fmain.py:42\"\n\u002Fautonomous-fix-review docs\u002Fresearch\u002Ftrail\u002Ffindings\u002Ffinding-001.yaml\n```\n\n## 7-Phase Pipeline\n\n| Phase | Action | Tool |\n|-------|--------|------|\n| 1. Research | Gather context (docs, code) | \u002Ffind-docs, \u002Fcontext7-mcp |\n| 2. Implement | Dispatch coder in worktree with TDD | subagent-driven-development |\n| 3. Review | Invoke claude + codex + gemini | reviewd.invoke_cli() |\n| 4. Consensus | Evaluate 75% threshold | mde.consensus.evaluate_consensus() |\n| 5. Decision | Apply autonomy mode | ConsensusGate.apply_autonomy() |\n| 6. Quality gate | Run lint + test + validate | uv run mde-py quality |\n| 7. Commit | Commit on feature branch or escalate | git commit |\n\n## Autonomy Modes\n\n- **supervised**: Human approves everything except unanimous approval\n- **semi-autonomous** (default): Auto-retry on warnings, escalate on disagreement\n- **autonomous**: Proceed on any non-abort consensus\n\n## Decision Matrix\n\n| Consensus | Supervised | Semi-Autonomous | Autonomous |\n|-----------|-----------|-----------------|------------|\n| >= 90% approve, no criticals | PROCEED | PROCEED | PROCEED |\n| >= 75% approve, no criticals | ESCALATE | RETRY | PROCEED |\n| Any critical findings | ESCALATE | ESCALATE | ESCALATE |\n| \u003C 75% approve | ESCALATE | ESCALATE | ESCALATE |\n| All reject | ABORT | ABORT | ABORT |\n\n## Workflow\n\n```bash\n# Step 1: Parse the finding\nfinding=$(echo \"$ARGUMENTS\")\n\n# Step 2: Research context\n# Invoke \u002Ffind-docs and \u002Fcontext7-mcp for the affected code area\n\n# Step 3: Implement fix (if not already done)\n# Dispatch coder subagent in worktree with TDD\n\n# Step 4-5: Run multi-model review + consensus\nuv run mde-py review \"$finding\" --autonomy semi-autonomous\n\n# Step 6: Quality gate (auto-runs unless --skip-quality)\nuv run mde-py quality\n\n# Step 7: Based on decision output:\n# PROCEED → commit on feature branch\n# ESCALATE → present findings to human for decision\n# RETRY → re-implement and re-review (up to max_retries)\n# ABORT → stop, finding may be invalid\n```\n\n## Constraints\n\n- Zero API keys — all LLM calls via subscription CLIs (claude, codex, gemini)\n- Worktree isolation for implementation phase\n- Human interview ONLY on consensus disagreement (ESCALATE)\n- Quality gate (6\u002F6) required before commit\n","# Autonomous Fix-Review Pipeline\n\nGive it a finding, walk away, come back to a committed fix that passed multi-model review.\n\n## Usage\n\n```\n\u002Fautonomous-fix-review \"Fix the null pointer in src\u002Fmain.py:42\"\n\u002Fautonomous-fix-review docs\u002Fresearch\u002Ftrail\u002Ffindings\u002Ffinding-001.yaml\n```\n\n## 7-Phase Pipeline\n\n| Phase | Action | Tool |\n|-------|--------|------|\n| 1. Research | Gather context (docs, code) | \u002Ffind-docs, \u002Fcontext7-mcp |\n| 2. Implement | Dispatch coder in worktree with TDD | subagent-driven-development |\n| 3. Review | Invoke claude + codex + gemini | reviewd.invoke_cli() |\n| 4. Consensus | Evaluate 75% threshold | mde.consensus.evaluate_consensus() |\n| 5. Decision | Apply autonomy mode | ConsensusGate.apply_autonomy() |\n| 6. Quality gate | Run lint + test + validate | uv run mde-py quality |\n| 7. Commit | Commit on feature branch or escalate | git commit |\n\n## Autonomy Modes\n\n- **supervised**: Human approves everything except unanimous approval\n- **semi-autonomous** (default): Auto-retry on warnings, escalate on disagreement\n- **autonomous**: Proceed on any non-abort consensus\n\n## Decision Matrix\n\n| Consensus | Supervised | Semi-Autonomous | Autonomous |\n|-----------|-----------|-----------------|------------|\n| >= 90% approve, no criticals | PROCEED | PROCEED | PROCEED |\n| >= 75% approve, no criticals | ESCALATE | RETRY | PROCEED |\n| Any critical findings | ESCALATE | ESCALATE | ESCALATE |\n| \u003C 75% approve | ESCALATE | ESCALATE | ESCALATE |\n| All reject | ABORT | ABORT | ABORT |\n\n## Workflow\n\n```bash\n# Step 1: Parse the finding\nfinding=$(echo \"$ARGUMENTS\")\n\n# Step 2: Research context\n# Invoke \u002Ffind-docs and \u002Fcontext7-mcp for the affected code area\n\n# Step 3: Implement fix (if not already done)\n# Dispatch coder subagent in worktree with TDD\n\n# Step 4-5: Run multi-model review + consensus\nuv run mde-py review \"$finding\" --autonomy semi-autonomous\n\n# Step 6: Quality gate (auto-runs unless --skip-quality)\nuv run mde-py quality\n\n# Step 7: Based on decision output:\n# PROCEED → commit on feature branch\n# ESCALATE → present findings to human for decision\n# RETRY → re-implement and re-review (up to max_retries)\n# ABORT → stop, finding may be invalid\n```\n\n## Constraints\n\n- Zero API keys — all LLM calls via subscription CLIs (claude, codex, gemini)\n- Worktree isolation for implementation phase\n- Human interview ONLY on consensus disagreement (ESCALATE)\n- Quality gate (6\u002F6) required before commit\n",{"name":5,"context":43,"description":7,"argument-hint":44,"user-invocable":45},"fork","\u003Cfinding-file-or-description>",true,"main","716b17df3ef6719d88aeac180015008b7ddfff6f",".agents\u002Fskills\u002Fautonomous-fix-review",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":54,"prompt":64,"zipAvailable":45},[55,58,61],{"tool":56,"command":57},"npx","npx skills add ray-manaloto\u002Fmacos-development-environment --skill autonomous-fix-review",{"tool":59,"command":60},"bunx","bunx skills add ray-manaloto\u002Fmacos-development-environment --skill autonomous-fix-review",{"tool":62,"command":63},"pnpm","pnpm dlx skills add ray-manaloto\u002Fmacos-development-environment --skill autonomous-fix-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fautonomous-fix-review\u002FSKILL.md",[66,72],{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"SOURCE.md","REFERENCE","参考文档",143,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fdefi\u002Fbridge-rates-mcp\u002FSOURCE.md",{"path":73,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":74,"sourceHtmlUrl":75},"TRUST.auto.yaml",2217,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fdefi\u002Fbridge-rates-mcp\u002FTRUST.auto.yaml",[77,98,116,134,154,168],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":86,"publishedAt":38},"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",[83],{"categoryNo":84,"categoryName":85,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[87,88,89,90,91,92,93,94,95,96,97],"next workflow step","workflow","up","use","session","user","wrap up","continue","handoff","prepare","SET",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":38},"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",[],[105,106,107,108,109,110,111,112,113,92,114,115],"discovery","source discovery","research","libraries","search","classification","find","check","management","catalog","find sources",{"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":122,"publishedAt":38},"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",[],[23,123,124,125,126,127,128,92,129,130,131,132,133],"review synthesis","Synthesis","prioritize","create action","feedback","reviewer","summarize","prioritization","create","issues","severity",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":143,"publishedAt":38},"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",[140],{"categoryNo":141,"categoryName":142,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",[144,107,145,146,147,148,149,150,112,92,151,152,153],"research scoring","status","coverage gaps","metrics","pipeline","baseline","quality","coverage","pipeline status","research quality",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":160,"publishedAt":38},"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",[],[161,162,163,164,112,92,165,166,167,124],"notebooklm integration","notebooklm","integration","knowledge","ingestion","ingest","stale",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":175,"publishedAt":38},"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",[174],{"categoryNo":141,"categoryName":142,"taxonomyType":20,"taxonomyTypeDesc":21},[176,124,177,129,107,178,179,180,92,181,23],"evidence synthesis","evidence","deep review","analysis","write","reference"]