[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C4PRGAVNTHJ5CPZ4JHCQ1F":3,"skill-same:01M6C4PRGAVNTHJ5CPZ4JHCQ1F":128},{"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":23,"publishedAt":51,"linkOnly":52,"markdownContent":53,"markdownBody":54,"frontMatter":55,"refName":72,"commitSha":73,"skillDirectory":74,"forksCount":75,"repositoryHtmlUrl":76,"repositoryHomepageUrl":6,"ownerHtmlUrl":77,"ownerBlogUrl":78,"ownerDescription":79,"updatedAt":80,"install":81,"resources":93},"01M6C4PRGAVNTHJ5CPZ4JHCQ1F","harness-setup",null,"HAR: Project init, tool setup, agent config, memory setup, skill mirror sync. Trigger: setup, init, new project, CI\u002FCodex setup, harness-mem, mirror. Do NOT load for: implementation, review, release, planning.","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\u002Fcodex\u002F.codex\u002Fskills\u002Fharness-setup\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50],"setup","harness setup","harness","Bash","new","2026","codex setup","project","mem","localize","project init","initialize","write","read","agent config","tool","review","ci","release","planning","core","init","codex cli","workflow","memory","codex","cli","2026-11-10 10:12:30",false,"---\nname: harness-setup\ndescription: \"HAR: Project init, tool setup, agent config, memory setup, skill mirror sync. Trigger: setup, init, new project, CI\u002FCodex setup, harness-mem, mirror. Do NOT load for: implementation, review, release, planning.\"\ndescription-en: \"HAR: Project init, tool setup, agent config, memory setup, skill mirror sync. Trigger: setup, init, new project, CI\u002FCodex setup, harness-mem, mirror. Do NOT load for: implementation, review, release, planning.\"\ndescription-ja: \"HAR:プロジェクト初期化・ツール設定・エージェント構成・メモリ設定・skill mirror 同期を担当。セットアップ、初期化、新規プロジェクト、CI\u002FCodex CLI セットアップ、harness-mem、mirror で起動。実装・レビュー・リリース・プランニングには使わない。\"\nkind: workflow\npurpose: \"Initialize and repair Harness project configuration\"\ntrigger: \"setup, init, new project, CI\u002FCodex setup, harness-mem, mirror\"\nshape: workflow\nrole: generator\npair: harness-sync\nowner: harness-core\nsince: \"2026-05-05\"\nallowed-tools: [\"Read\", \"Write\", \"Edit\", \"Grep\", \"Glob\", \"Bash\"]\nargument-hint: \"[init|ci|codex|harness-mem|mirrors|agents|localize]\"\nuser-invocable: true\neffort: medium\n---\n\n# Harness Setup\n\nHarness の統合セットアップスキル。\n以下の旧スキルを統合:\n\n- `setup` — 統合セットアップハブ\n- `harness-init` — プロジェクト初期化\n- `harness-update` — Harness アップデート\n- `maintenance` — ファイル整理・クリーンアップ\n\n## Quick Reference\n\n| サブコマンド | 動作 | 詳細 |\n|------------|------|------|\n| `\u002Fharness-setup init` | 新規プロジェクト初期化（CLAUDE.md + Plans.md + hooks + sync + doctor）| `${CLAUDE_SKILL_DIR}\u002Freferences\u002Finit.md` |\n| `\u002Fharness-setup ci` | CI\u002FCD パイプライン設定 | `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fci.md` |\n| `\u002Fharness-setup codex` | Codex CLI インストール・設定 | `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fcodex.md` |\n| `\u002Fharness-setup harness-mem` | harness-mem 統合・メモリ設定 | `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fharness-mem.md` |\n| `\u002Fharness-setup mirrors` | skills\u002F → 公開 mirror bundle 更新 | `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fmirrors-agents-localize.md` |\n| `\u002Fharness-setup agents` | agents\u002F エージェント設定 | `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fmirrors-agents-localize.md` |\n| `\u002Fharness-setup localize` | CLAUDE.md ルールのローカライズ | `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fmirrors-agents-localize.md` |\n| marketplace \u002F update | Plugin install, update, dependency policy | `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fmarketplace.md` |\n| maintenance | ファイル整理・クリーンアップ | `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fmaintenance.md` |\n\n> **Built-in slash discovery (CC 2.1.108+)**:\n> `\u002Finit` のような built-in slash command も発見される。\n> Harness 固有の bootstrap が必要な時だけ `\u002Fharness-setup init` と使い分ける。\n\n> **Claude Code setup guidance (CC 2.1.120+)**:\n> MCP `alwaysLoad`、`${CLAUDE_EFFORT}`、`claude plugin prune`、`claude project purge`、\n> `ANTHROPIC_BEDROCK_SERVICE_TIER`、`claude_code.skill_activated.invocation_trigger`、\n> Windows PowerShell primary shell、forked skills \u002F subagents の deferred tools は\n> `docs\u002Fclaude-code-setup-mcp-telemetry-provider.md` を正本として扱う。\n\n> **Codex plugin workflows**:\n> Codex `\u002Fgoal` と `Plans.md` を二重管理しない。\n> plugin-bundled hooks は opt-in、external agent import は ownership 明記、\n> MultiAgentV2 \u002F `agents.max_threads = 8` は上限として扱い、\n> sticky environments \u002F app-server artifacts は safe default を優先する。\n> Codex `0.130.0` stable の `codex remote-control`、large thread pagination、\n> selected-environment `view_image`、live app-server config refresh、\n> accurate turn diffs、plugin details bundled hooks、sharing discoverability controls は\n> `docs\u002Fcodex-plugin-workflows-policy.md` を正本として扱う。\n> 詳細は `docs\u002Fcodex-plugin-workflows-policy.md` と `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fcodex.md` を参照。\n\n## Execution\n\n状態確認だけの依頼は read-only の診断で完了する。setup 依頼は対象、望む状態、合格条件を既存設定と照合し、明示された surface の変更を進める。\n不足情報は設定や契約を読み取りで回収する。任意機能を追加したり、対象外の設定や保護された設定を目的から推測して変更したりしない。\n\n1. ユーザーの目的に対応する Quick Reference 行を選ぶ。\n2. 該当する `${CLAUDE_SKILL_DIR}\u002Freferences\u002F*.md` を読む。\n3. 参照ファイルの手順に従い、dry-run がある操作は dry-run を先に実行する。\n4. setup 後は必要に応じて `harness doctor`、`bash scripts\u002Fsync-skill-mirrors.sh --check`、`bash scripts\u002Fci\u002Fcheck-consistency.sh` で確認する。\n\n## Upstream Policy Anchors\n\n- `docs\u002Fplugin-managed-settings-policy.md` — plugin managed settings policy; normal defaults must not inherit managed marketplace restrictions.\n- `docs\u002Fcodex-provider-setup-policy.md` — Codex provider setup policy, including `amazon-bedrock` and `model_provider = \"amazon-bedrock\"` examples.\n- Codex `0.123.0` 以降の MCP diagnostics \u002F plugin MCP loading guidance: use `\u002Fmcp verbose` and `docs\u002Fcodex-mcp-diagnostics.md` for diagnostics.\n- Codex sandbox \u002F execution policy (0.123.0+): see `docs\u002Fcodex-sandbox-execution-policy.md` for `remote_sandbox_config` and execution constraints.\n\n## Cursor 実装バックエンド導入\n\n詳細手順は `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fcursor.md` を読む。\n契約アンカー: `set-impl-backend.sh` は AI 実行可。`permissions.json`、`.cursorignore`、`*.cursor.sh` allowlist はユーザー手動で、AI が編集できない protected path として扱う。\n根拠ルールは `.claude\u002Frules\u002Fcursor-cli-only.md` と `docs\u002Fsandbox-allowlist-recipe.md`。\n\n## Reference Index\n\n- `${CLAUDE_SKILL_DIR}\u002Freferences\u002Finit.md` — init, Go binary verification, plugin sync, doctor.\n- `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fci.md` — GitHub Actions CI setup.\n- `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fcodex.md` — Codex CLI, provider\u002Fmodel metadata, app-server, MCP diagnostics, sandbox policy.\n- `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fcursor.md` — Cursor implementation backend setup and boundaries.\n- `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fharness-mem.md` — memory directory and template setup.\n- `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fmirrors-agents-localize.md` — mirror sync, agent setup, localization.\n- `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fmarketplace.md` — plugin marketplace install\u002Fupdate and managed dependency policy.\n- `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fmaintenance.md` — cleanup commands and related skills.\n\n## 関連スキル\n\n- `harness-sync` — 設定\u002FPlans\u002Fgit 状態の同期確認\n- `harness-work` — 実装タスク実行\n- `harness-review` — 品質レビュー\n- `maintenance` — ファイル整理（統合済み）\n","# Harness Setup\n\nHarness の統合セットアップスキル。\n以下の旧スキルを統合:\n\n- `setup` — 統合セットアップハブ\n- `harness-init` — プロジェクト初期化\n- `harness-update` — Harness アップデート\n- `maintenance` — ファイル整理・クリーンアップ\n\n## Quick Reference\n\n| サブコマンド | 動作 | 詳細 |\n|------------|------|------|\n| `\u002Fharness-setup init` | 新規プロジェクト初期化（CLAUDE.md + Plans.md + hooks + sync + doctor）| `${CLAUDE_SKILL_DIR}\u002Freferences\u002Finit.md` |\n| `\u002Fharness-setup ci` | CI\u002FCD パイプライン設定 | `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fci.md` |\n| `\u002Fharness-setup codex` | Codex CLI インストール・設定 | `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fcodex.md` |\n| `\u002Fharness-setup harness-mem` | harness-mem 統合・メモリ設定 | `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fharness-mem.md` |\n| `\u002Fharness-setup mirrors` | skills\u002F → 公開 mirror bundle 更新 | `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fmirrors-agents-localize.md` |\n| `\u002Fharness-setup agents` | agents\u002F エージェント設定 | `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fmirrors-agents-localize.md` |\n| `\u002Fharness-setup localize` | CLAUDE.md ルールのローカライズ | `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fmirrors-agents-localize.md` |\n| marketplace \u002F update | Plugin install, update, dependency policy | `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fmarketplace.md` |\n| maintenance | ファイル整理・クリーンアップ | `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fmaintenance.md` |\n\n> **Built-in slash discovery (CC 2.1.108+)**:\n> `\u002Finit` のような built-in slash command も発見される。\n> Harness 固有の bootstrap が必要な時だけ `\u002Fharness-setup init` と使い分ける。\n\n> **Claude Code setup guidance (CC 2.1.120+)**:\n> MCP `alwaysLoad`、`${CLAUDE_EFFORT}`、`claude plugin prune`、`claude project purge`、\n> `ANTHROPIC_BEDROCK_SERVICE_TIER`、`claude_code.skill_activated.invocation_trigger`、\n> Windows PowerShell primary shell、forked skills \u002F subagents の deferred tools は\n> `docs\u002Fclaude-code-setup-mcp-telemetry-provider.md` を正本として扱う。\n\n> **Codex plugin workflows**:\n> Codex `\u002Fgoal` と `Plans.md` を二重管理しない。\n> plugin-bundled hooks は opt-in、external agent import は ownership 明記、\n> MultiAgentV2 \u002F `agents.max_threads = 8` は上限として扱い、\n> sticky environments \u002F app-server artifacts は safe default を優先する。\n> Codex `0.130.0` stable の `codex remote-control`、large thread pagination、\n> selected-environment `view_image`、live app-server config refresh、\n> accurate turn diffs、plugin details bundled hooks、sharing discoverability controls は\n> `docs\u002Fcodex-plugin-workflows-policy.md` を正本として扱う。\n> 詳細は `docs\u002Fcodex-plugin-workflows-policy.md` と `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fcodex.md` を参照。\n\n## Execution\n\n状態確認だけの依頼は read-only の診断で完了する。setup 依頼は対象、望む状態、合格条件を既存設定と照合し、明示された surface の変更を進める。\n不足情報は設定や契約を読み取りで回収する。任意機能を追加したり、対象外の設定や保護された設定を目的から推測して変更したりしない。\n\n1. ユーザーの目的に対応する Quick Reference 行を選ぶ。\n2. 該当する `${CLAUDE_SKILL_DIR}\u002Freferences\u002F*.md` を読む。\n3. 参照ファイルの手順に従い、dry-run がある操作は dry-run を先に実行する。\n4. setup 後は必要に応じて `harness doctor`、`bash scripts\u002Fsync-skill-mirrors.sh --check`、`bash scripts\u002Fci\u002Fcheck-consistency.sh` で確認する。\n\n## Upstream Policy Anchors\n\n- `docs\u002Fplugin-managed-settings-policy.md` — plugin managed settings policy; normal defaults must not inherit managed marketplace restrictions.\n- `docs\u002Fcodex-provider-setup-policy.md` — Codex provider setup policy, including `amazon-bedrock` and `model_provider = \"amazon-bedrock\"` examples.\n- Codex `0.123.0` 以降の MCP diagnostics \u002F plugin MCP loading guidance: use `\u002Fmcp verbose` and `docs\u002Fcodex-mcp-diagnostics.md` for diagnostics.\n- Codex sandbox \u002F execution policy (0.123.0+): see `docs\u002Fcodex-sandbox-execution-policy.md` for `remote_sandbox_config` and execution constraints.\n\n## Cursor 実装バックエンド導入\n\n詳細手順は `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fcursor.md` を読む。\n契約アンカー: `set-impl-backend.sh` は AI 実行可。`permissions.json`、`.cursorignore`、`*.cursor.sh` allowlist はユーザー手動で、AI が編集できない protected path として扱う。\n根拠ルールは `.claude\u002Frules\u002Fcursor-cli-only.md` と `docs\u002Fsandbox-allowlist-recipe.md`。\n\n## Reference Index\n\n- `${CLAUDE_SKILL_DIR}\u002Freferences\u002Finit.md` — init, Go binary verification, plugin sync, doctor.\n- `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fci.md` — GitHub Actions CI setup.\n- `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fcodex.md` — Codex CLI, provider\u002Fmodel metadata, app-server, MCP diagnostics, sandbox policy.\n- `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fcursor.md` — Cursor implementation backend setup and boundaries.\n- `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fharness-mem.md` — memory directory and template setup.\n- `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fmirrors-agents-localize.md` — mirror sync, agent setup, localization.\n- `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fmarketplace.md` — plugin marketplace install\u002Fupdate and managed dependency policy.\n- `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fmaintenance.md` — cleanup commands and related skills.\n\n## 関連スキル\n\n- `harness-sync` — 設定\u002FPlans\u002Fgit 状態の同期確認\n- `harness-work` — 実装タスク実行\n- `harness-review` — 品質レビュー\n- `maintenance` — ファイル整理（統合済み）\n",{"kind":47,"name":5,"pair":56,"role":57,"owner":58,"shape":47,"since":59,"effort":60,"purpose":61,"trigger":62,"description":7,"allowed-tools":63,"argument-hint":69,"description-en":7,"description-ja":70,"user-invocable":71},"harness-sync","generator","harness-core","2026-05-05","medium","Initialize and repair Harness project configuration","setup, init, new project, CI\u002FCodex setup, harness-mem, mirror",[64,65,66,67,68,27],"Read","Write","Edit","Grep","Glob","[init|ci|codex|harness-mem|mirrors|agents|localize]","HAR:プロジェクト初期化・ツール設定・エージェント構成・メモリ設定・skill mirror 同期を担当。セットアップ、初期化、新規プロジェクト、CI\u002FCodex CLI セットアップ、harness-mem、mirror で起動。実装・レビュー・リリース・プランニングには使わない。",true,"main","c2304c325d4432f51d632e0586d886767b0f41ea","codex\u002F.codex\u002Fskills\u002Fharness-setup",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":82,"prompt":92,"zipAvailable":71},[83,86,89],{"tool":84,"command":85},"npx","npx skills add Chachamaru127\u002Fclaude-code-harness --skill harness-setup",{"tool":87,"command":88},"bunx","bunx skills add Chachamaru127\u002Fclaude-code-harness --skill harness-setup",{"tool":90,"command":91},"pnpm","pnpm dlx skills add Chachamaru127\u002Fclaude-code-harness --skill harness-setup","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fcodex\u002F.codex\u002Fskills\u002Fharness-setup\u002FSKILL.md",[94,100,104,108,112,116,120,124],{"path":95,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fci.md","REFERENCE","参考文档",412,"https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fcodex\u002F.codex\u002Fskills\u002Fharness-setup\u002Freferences\u002Fci.md",{"path":101,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Fcodex.md",7665,"https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fcodex\u002F.codex\u002Fskills\u002Fharness-setup\u002Freferences\u002Fcodex.md",{"path":105,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Fcursor.md",3414,"https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fcodex\u002F.codex\u002Fskills\u002Fharness-setup\u002Freferences\u002Fcursor.md",{"path":109,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":110,"sourceHtmlUrl":111},"references\u002Fharness-mem.md",583,"https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fcodex\u002F.codex\u002Fskills\u002Fharness-setup\u002Freferences\u002Fharness-mem.md",{"path":113,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":114,"sourceHtmlUrl":115},"references\u002Finit.md",2556,"https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fcodex\u002F.codex\u002Fskills\u002Fharness-setup\u002Freferences\u002Finit.md",{"path":117,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":118,"sourceHtmlUrl":119},"references\u002Fmaintenance.md",751,"https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fcodex\u002F.codex\u002Fskills\u002Fharness-setup\u002Freferences\u002Fmaintenance.md",{"path":121,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":122,"sourceHtmlUrl":123},"references\u002Fmarketplace.md",2844,"https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fcodex\u002F.codex\u002Fskills\u002Fharness-setup\u002Freferences\u002Fmarketplace.md",{"path":125,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":126,"sourceHtmlUrl":127},"references\u002Fmirrors-agents-localize.md",1197,"https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Fcodex\u002F.codex\u002Fskills\u002Fharness-setup\u002Freferences\u002Fmirrors-agents-localize.md",[129,143,151,169,195,219],{"skillNo":130,"name":131,"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":132,"categories":133,"keywords":135,"publishedAt":51},"01M6C4VZCJB9EN3KZXGNARAF6P","escape-skill","https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fzz-review-escape\u002FSKILL.md",[134],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[136,137,138,139,140,141,142],"escape skill","escape","Tools","false","true","path","quoted",{"skillNo":144,"name":145,"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":146,"categories":147,"keywords":148,"publishedAt":51},"01M6C4VYAJW332S5R2MM3RNE0G","zz-review-empty","https:\u002F\u002Fgithub.com\u002FChachamaru127\u002Fclaude-code-harness\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fzz-review-empty\u002FSKILL.md",[],[40,149,150,139,140],"zz review empty","empty",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":158,"publishedAt":51},"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",[157],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[159,160,161,162,163,27,164,165,166,167,168],"session","session send","send","handoff","session handoff","user","message","notify","requests","when",{"skillNo":170,"name":48,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":175,"publishedAt":51},"01M6C4VSMYH6XQGR087HQ9Y7HT","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",[174],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[48,176,177,178,26,179,180,181,27,182,39,183,184,37,36,185,164,159,186,187,188,189,190,191,192,140,193,194,168],"MCP","sync","notes","search","memory search","guardian","migrate","work","decisions","edit","use","migration","manage","do","learnings","promotion","reviews","load","for",{"skillNo":196,"name":197,"nameZh":6,"description":198,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":199,"categories":200,"keywords":201,"publishedAt":51},"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",[],[197,40,202,203,204,42,205,206,207,27,208,209,37,36,185,210,159,211,212,213,189,214,215,216,217,218,140,193,194,28],"development","cleanup","run","state","file","logs","archive","grep","new feature","up","log","files","feature","plans","trigger","整理","split",{"skillNo":220,"name":221,"nameZh":6,"description":222,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":223,"categories":224,"keywords":237,"publishedAt":51},"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",[225,228,231,232],{"categoryNo":226,"categoryName":227,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":229,"categoryName":230,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":233,"categoryName":234,"taxonomyType":235,"taxonomyTypeDesc":236},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[238,239,240,40,241,204,242,243,27,244,245,246,247,37,248,249,186,250,251,252,253,254,255,256,257,258,259,260,261,262,168,263],"writing","japanese writing drafter","japanese","status","lint","operator","提案","text","engine","Rules","list","proposals","never","only","scanning","say","human review","later","conversation","writer","human","scripts","problem","proposal","jsonl","listing"]