[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C4TDH97KTYKYZP7S3QQWY3":3,"skill-same:01M6C4TDH97KTYKYZP7S3QQWY3":87},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":48,"linkOnly":49,"markdownContent":50,"markdownBody":51,"frontMatter":52,"refName":59,"commitSha":60,"skillDirectory":61,"forksCount":62,"repositoryHtmlUrl":63,"repositoryHomepageUrl":6,"ownerHtmlUrl":64,"ownerBlogUrl":65,"ownerDescription":66,"updatedAt":67,"install":68,"resources":80},"01M6C4TDH97KTYKYZP7S3QQWY3","failure-codifier",null,"Extract recurring failure patterns from breezing orchestration logs and Judgment Ledger, emit failure-rule.v1 proposals with confidence scores. SSOT promotion to patterns.md or decisions.md is proposal-only — human-approval-required. Use when user mentions failure codifier, failure patterns, self-learning loop, codify failures, or failure-rule proposals. Do NOT load for: direct SSOT edits, auto-promotion, or implementation unrelated to failure analysis.","Chachamaru127\u002Fclaude-code-harness","Chachamaru127","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F96473544?v=4","01M6C4N084DDDEK9SJPGFG9H9M","Chachamaru","01M6C4N0CCNFST9P8C7EJNVH42",3208,"MIT","https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fskills\u002Ffailure-codifier\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"failure codifier","use","when","for","v1","load","true","promotion","failure analysis","proposal","do","breezing","unrelated","only","auto","orchestration","recurring","proposals","read","decisions","grep","direct","explain","提案","loop","learning","Bash","analysis","logs","2026-11-10 10:12:30",false,"---\nname: failure-codifier\ndescription: \"Extract recurring failure patterns from breezing orchestration logs and Judgment Ledger, emit failure-rule.v1 proposals with confidence scores. SSOT promotion to patterns.md or decisions.md is proposal-only — human-approval-required. Use when user mentions failure codifier, failure patterns, self-learning loop, codify failures, or failure-rule proposals. Do NOT load for: direct SSOT edits, auto-promotion, or implementation unrelated to failure analysis.\"\ndescription-en: \"Extract recurring failure patterns from breezing orchestration logs and Judgment Ledger, emit failure-rule.v1 proposals with confidence scores. SSOT promotion to patterns.md or decisions.md is proposal-only — human-approval-required. Use when user mentions failure codifier, failure patterns, self-learning loop, codify failures, or failure-rule proposals. Do NOT load for: direct SSOT edits, auto-promotion, or implementation unrelated to failure analysis.\"\ndescription-ja: \"breezing ログと Judgment Ledger から再現失敗パターンを抽出し、confidence 付き failure-rule.v1 候補を提案する。patterns.md \u002F decisions.md への昇格は human-approval-required（自動昇格禁止）。Use when user mentions failure codifier, 失敗パターン, self-learning loop, codify failures. Do NOT load for: SSOT 直接編集, 自動昇格.\"\nallowed-tools: [\"Read\", \"Bash\", \"Grep\"]\nargument-hint: \"[propose|explain]\"\nuser-invocable: true\n---\n\n# Failure Codifier\n\nbreezing orchestration ledger + Judgment Ledger から再現失敗を **read-only** で抽出し、`failure-rule.v1` 候補を confidence score 付きで提案します。\n\n## 核心契約\n\n- **human-approval-required**: codifier は dry-run 提案のみ。`patterns.md` \u002F `decisions.md` への自動昇格は構造的に禁止。\n- Confidence 閾値: occurrence **count ≥ 3 → medium**、**count ≥ 5 → high**（`go\u002Finternal\u002Ffailurecodifier\u002Fconfidence.go`）。\n- 昇格先 heuristic: `proposed_ssot_target` フィールドで `patterns.md` または `decisions.md` を**提案するのみ**。\n\n## 使い方\n\n### Dry-run 提案（推奨）\n\n```bash\n.\u002Fscripts\u002Ffailure-codifier-propose.sh --dry-run\n```\n\nstdout は JSON 配列（`failure-rule.v1` 候補）。SSOT ファイルには一切書き込みません。\n\n### Go テスト\n\n```bash\ncd go && go test .\u002Finternal\u002Ffailurecodifier\u002F... -count=1\n```\n\n## 参照\n\n- 昇格ワークフロー: [references\u002Fpromotion-workflow.md](${CLAUDE_SKILL_DIR}\u002Freferences\u002Fpromotion-workflow.md)\n- Schema: `templates\u002Fschemas\u002Ffailure-rule.v1.json`\n- Core: `go\u002Finternal\u002Ffailurecodifier\u002F`\n\n## 禁止事項\n\n- `patterns.md` \u002F `decisions.md` への Write \u002F Edit（human 承認後も codifier 経由では不可）\n- `AutoPromote` \u002F unattended SSOT 更新\n- Plans.md の `cc:*` マーカー変更\n","# Failure Codifier\n\nbreezing orchestration ledger + Judgment Ledger から再現失敗を **read-only** で抽出し、`failure-rule.v1` 候補を confidence score 付きで提案します。\n\n## 核心契約\n\n- **human-approval-required**: codifier は dry-run 提案のみ。`patterns.md` \u002F `decisions.md` への自動昇格は構造的に禁止。\n- Confidence 閾値: occurrence **count ≥ 3 → medium**、**count ≥ 5 → high**（`go\u002Finternal\u002Ffailurecodifier\u002Fconfidence.go`）。\n- 昇格先 heuristic: `proposed_ssot_target` フィールドで `patterns.md` または `decisions.md` を**提案するのみ**。\n\n## 使い方\n\n### Dry-run 提案（推奨）\n\n```bash\n.\u002Fscripts\u002Ffailure-codifier-propose.sh --dry-run\n```\n\nstdout は JSON 配列（`failure-rule.v1` 候補）。SSOT ファイルには一切書き込みません。\n\n### Go テスト\n\n```bash\ncd go && go test .\u002Finternal\u002Ffailurecodifier\u002F... -count=1\n```\n\n## 参照\n\n- 昇格ワークフロー: [references\u002Fpromotion-workflow.md](${CLAUDE_SKILL_DIR}\u002Freferences\u002Fpromotion-workflow.md)\n- Schema: `templates\u002Fschemas\u002Ffailure-rule.v1.json`\n- Core: `go\u002Finternal\u002Ffailurecodifier\u002F`\n\n## 禁止事項\n\n- `patterns.md` \u002F `decisions.md` への Write \u002F Edit（human 承認後も codifier 経由では不可）\n- `AutoPromote` \u002F unattended SSOT 更新\n- Plans.md の `cc:*` マーカー変更\n",{"name":5,"description":7,"allowed-tools":53,"argument-hint":56,"description-en":7,"description-ja":57,"user-invocable":58},[54,45,55],"Read","Grep","[propose|explain]","breezing ログと Judgment Ledger から再現失敗パターンを抽出し、confidence 付き failure-rule.v1 候補を提案する。patterns.md \u002F decisions.md への昇格は human-approval-required（自動昇格禁止）。Use when user mentions failure codifier, 失敗パターン, self-learning loop, codify failures. Do NOT load for: SSOT 直接編集, 自動昇格.",true,"main","c2304c325d4432f51d632e0586d886767b0f41ea","skills\u002Ffailure-codifier",305,"https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness","https:\u002F\u002Fgithub.com\u002FChachamaru127","https:\u002F\u002Fcanai.jp\u002F","Going all-in on the AI business from April 2025\r\nOSS release: 3k Stars\r\nAI adoption starting with \"I want\"\r\nAX Support | Tokenomics | AISDR |","2026-11-11 17:18:34",{"source":8,"skillName":5,"commands":69,"prompt":79,"zipAvailable":58},[70,73,76],{"tool":71,"command":72},"npx","npx skills add Chachamaru127\u002Fclaude-code-harness --skill failure-codifier",{"tool":74,"command":75},"bunx","bunx skills add Chachamaru127\u002Fclaude-code-harness --skill failure-codifier",{"tool":77,"command":78},"pnpm","pnpm dlx skills add Chachamaru127\u002Fclaude-code-harness --skill failure-codifier","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fskills\u002Ffailure-codifier\u002FSKILL.md",[81],{"path":82,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fpromotion-workflow.md","REFERENCE","参考文档",2563,"https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fskills\u002Ffailure-codifier\u002Freferences\u002Fpromotion-workflow.md",[88,105,114,131,155,179],{"skillNo":89,"name":90,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":98,"publishedAt":48},"01M6C4VZCJB9EN3KZXGNARAF6P","escape-skill","https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fzz-review-escape\u002FSKILL.md",[93],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[99,100,101,102,25,103,104],"escape skill","escape","Tools","false","path","quoted",{"skillNo":106,"name":107,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":48},"01M6C4VYAJW332S5R2MM3RNE0G","zz-review-empty","https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fzz-review-empty\u002FSKILL.md",[],[111,112,113,102,25],"review","zz review empty","empty",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":121,"publishedAt":48},"01M6C4VWW4GNAZ2680GY04S3EW","session-send","This skill should be used when the user asks to notify other session, requests a session handoff, says tell other agent, or needs a cross-session message.","https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fskills\u002Fsession-send\u002FSKILL.md",[120],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},[122,123,124,125,126,45,127,128,129,130,21],"session","session send","send","handoff","session handoff","user","message","notify","requests",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":138,"publishedAt":48},"01M6C4VSMYH6XQGR087HQ9Y7HT","memory","Manage SSOT, memory, and cross-tool memory search. Guardian of decisions.md and patterns.md. Use when user mentions memory, SSOT, decisions.md, patterns.md, merging, migration, SSOT promotion, sync memory, save learnings, memory search, harness-mem, past decisions, or record this. Do NOT load for: implementation work, reviews, ad-hoc notes, or in-session logging.","https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fskills\u002Fmemory\u002FSKILL.md",[137],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},[133,139,140,141,142,143,144,145,45,146,147,148,38,37,149,150,127,122,20,151,152,29,153,26,154,25,24,22,21],"MCP","sync","notes","harness","search","memory search","guardian","migrate","tool","work","write","edit","migration","manage","learnings","reviews",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":161,"publishedAt":48},"01M6C4VQ3507BV9XRX4BDSES6J","maintenance","File cleanup and archiving. Tidies up bloated Plans.md, session-log.md, old logs, and state files. Trigger: \u002Fmaintenance, cleanup, archive, organize, split session-log. Do NOT load for: implementation, review, release, new feature development.","https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fskills\u002Fmaintenance\u002FSKILL.md",[],[157,111,162,163,164,165,166,167,47,45,168,39,37,149,150,169,122,170,171,172,29,173,174,175,176,177,25,24,22,178],"development","cleanup","run","release","state","file","archive","new feature","up","log","files","feature","plans","trigger","整理","split","new",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":197,"publishedAt":48},"01M6C4VK473YJ872RNMBYK7P4R","japanese-writing-drafter","Detect when the operator corrects the agent's Japanese phrasing mid-conversation (rewrites a sentence, calls out a style problem, says 'this wording is bad, say it like X instead') and draft a pending writing-rule proposal into ~\u002F.claude\u002Fwriting-lint\u002Fproposals.jsonl for later human review. This skill is the ONLY writer of proposals.jsonl — it never edits rules.jsonl and never sets status to anything but pending. Promotion to rules.jsonl only happens via the human-run scripts\u002Fwriting-rule-approve.sh. Use when user mentions writing-rule proposal, 表現を直して, 文体を直して, その言い方はNG, writing lint 提案, 指摘をルール化して. Do NOT load for: approving or rejecting proposals (use scripts\u002Fwriting-rule-approve.sh), listing pending proposals (use scripts\u002Fwriting-rule-list.sh), or scanning text against the existing dictionary (the writinglint engine \u002F PostToolUse hook does that).","https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fskills\u002Fjapanese-writing-drafter\u002FSKILL.md",[185,188,191,192],{"categoryNo":186,"categoryName":187,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":189,"categoryName":190,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},{"categoryNo":193,"categoryName":194,"taxonomyType":195,"taxonomyTypeDesc":196},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[198,199,200,111,201,164,202,203,45,42,204,205,206,37,207,36,20,208,32,209,210,211,212,213,214,215,216,217,28,218,21,219],"writing","japanese writing drafter","japanese","status","lint","operator","text","engine","Rules","list","never","scanning","say","human review","later","conversation","writer","human","scripts","problem","jsonl","listing"]