[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CZRDZYKKHTVXYR02PRFAYW":3,"skill-same:01M6CZRDZYKKHTVXYR02PRFAYW":71},{"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":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M6CZRDZYKKHTVXYR02PRFAYW","kiro-debug",null,"Investigate implementation failures using root-cause-first debugging. Use when an implementer is blocked, verification fails, or repeated remediation does not converge.","j5ik2o\u002Fai-tools","j5ik2o","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F461711?v=4","01M6CR6HZJM242J0HDRJT5GY6J","Junichi Kato","01M6CZP6PXKYDDNX5A7PZ3P4DY",28,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fj5ik2o\u002Fai-tools\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fkiro-debug\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"kiro debug","kiro","debug","read","summary","root-cause","implementation","use","webfetch","implementer","grep","Bash","investigate","first","remediation","verification","debugging","2026-11-10 10:12:30",false,"---\nname: kiro-debug\ndescription: Investigate implementation failures using root-cause-first debugging. Use when an implementer is blocked, verification fails, or repeated remediation does not converge.\nallowed-tools: Read, Bash, Grep, Glob, WebSearch, WebFetch\nargument-hint: \u003Cfailure-summary>\n---\n\n# kiro-debug\n\n## Overview\n\nThis skill is for fresh-context root cause investigation. It combines local evidence, runtime\u002Fconfig inspection, and external documentation or issue research when available. It is not a patch generator for guess-first debugging.\n\n## When to Use\n\n- Implementer reports `BLOCKED`\n- Reviewer rejection repeats after remediation\n- Validation fails unexpectedly\n- A task appears to conflict with runtime or platform reality\n- The same failure survives more than one attempted fix\n\nDo not use this skill to speculate about fixes before gathering evidence.\n\n## Inputs\n\nProvide:\n- Exact failure symptom or blocker statement\n- Error messages, stack trace, and failing command output\n- Current `git diff` or summary of uncommitted failed changes\n- Task brief: what was being built\n- Reviewer feedback, if the failure came from review rejection\n- Relevant spec file paths (`requirements.md`, `design.md`)\n- Relevant requirement\u002Fdesign section numbers\n- Relevant `## Implementation Notes`\n- Runtime or environment constraints already known\n\n## Outputs\n\nReturn:\n- `ROOT_CAUSE`\n- `CATEGORY`\n- `FIX_PLAN`\n- `VERIFICATION`\n- `NEXT_ACTION: RETRY_TASK | BLOCK_TASK | STOP_FOR_HUMAN`\n- `CONFIDENCE: HIGH | MEDIUM | LOW`\n- `NOTES`\n\nUse the language specified in `spec.json`.\n\n## Method\n\n### 1. Read the Error Carefully\nExtract:\n- Exact error text\n- Stack trace or failure location\n- The command that produced the failure\n- Whether the failure is deterministic or intermittent\n\n### 2. Inspect Local Runtime and Repository State\nInspect the repository for local evidence:\n- `package.json`, `pyproject.toml`, `go.mod`, `Makefile`, `README*`\n- Build config\n- `tsconfig` or equivalent language\u002Fruntime config\n- Runtime-specific config\n- Dependency versions and scripts\n- Relevant changed files from `git diff`\n\n### 3. Search the Web if Available\nIf web access is available, search:\n- The exact error message\n- The technology + symptom combination\n- Official documentation\n- Version-specific issue trackers or migration notes\n\nPrefer:\n- Official docs\n- Official repos\u002Fissues\n- Version-specific references\n- Runtime-specific documentation\n\n### 4. Classify the Root Cause\nUse one category:\n- `MISSING_DEPENDENCY`\n- `RUNTIME_MISMATCH`\n- `MODULE_FORMAT`\n- `NATIVE_ABI`\n- `CONFIG_GAP`\n- `LOGIC_ERROR`\n- `TASK_ORDERING_PROBLEM`\n- `TASK_DECOMPOSITION_PROBLEM`\n- `SPEC_CONFLICT`\n- `EXTERNAL_DEPENDENCY`\n\n### 5. Determine the Smallest Safe Next Action\nDecide whether the issue can be fixed inside this repo by:\n- Editing files\n- Adjusting configuration\n- Adding or correcting dependencies\n- Restructuring code\n\nUse `NEXT_ACTION: RETRY_TASK` when the issue is repo-fixable inside the current approved task plan.\n\n### 6. Determine Whether the Task Plan Is Still Valid\nDecide whether the current approved task plan is still safe to execute as written.\n\nPrefer `NEXT_ACTION: STOP_FOR_HUMAN` when:\n- A missing prerequisite task should exist before this one\n- The current task is ordered incorrectly relative to unfinished work\n- The current task boundary is wrong and should be split or merged\n- The task is too large or ambiguous to fix safely inside the current implementation loop\n\nUse `NEXT_ACTION: BLOCK_TASK` only when the current task should stop but the rest of the queue can still proceed safely.\n\nDo not propose a brute-force code fix as a substitute for revising `tasks.md` or the approved plan.\n\n## Critical Rule\n\nDo not propose a multi-fix shotgun plan. Identify the root cause first, then produce the smallest plausible fix plan. If the true problem is a spec conflict or architecture problem, say so directly.\n\n## Stop \u002F Escalate\n\nUse `NEXT_ACTION: STOP_FOR_HUMAN` when the blocker genuinely requires:\n- Human product\u002Frequirements decision\n- External credentials or inaccessible services\n- Hardware or unavailable external systems\n- Re-scoping due to spec\u002Fplatform conflict\n\nIf the issue is fixable by repo changes inside the current task plan, do not escalate prematurely.\n\n## Common Rationalizations\n\n| Rationalization | Reality |\n|---|---|\n| “This probably just needs a quick patch” | Patch-first debugging creates rework. |\n| “Let’s try a few fixes” | Multi-fix guessing hides root cause. |\n| “The spec is probably wrong, I’ll adapt it” | Spec conflicts must be surfaced explicitly. |\n| “The docs search is optional” | For runtime\u002Fdependency issues, docs and version issues often contain the shortest path to root cause. |\n\n## Output Format\n\n```md\n## Debug Report\n- ROOT_CAUSE: \u003C1-2 sentence root cause>\n- CATEGORY: MISSING_DEPENDENCY | RUNTIME_MISMATCH | MODULE_FORMAT | NATIVE_ABI | CONFIG_GAP | LOGIC_ERROR | TASK_ORDERING_PROBLEM | TASK_DECOMPOSITION_PROBLEM | SPEC_CONFLICT | EXTERNAL_DEPENDENCY\n- FIX_PLAN:\n  1. \u003Cspecific repo-fixable action>\n  2. \u003Cspecific repo-fixable action>\n- VERIFICATION: \u003Ccommand(s) to confirm the fix>\n- NEXT_ACTION: RETRY_TASK | BLOCK_TASK | STOP_FOR_HUMAN\n- CONFIDENCE: HIGH | MEDIUM | LOW\n- NOTES: \u003Ccontext the next implementer should know>\n```\n","# kiro-debug\n\n## Overview\n\nThis skill is for fresh-context root cause investigation. It combines local evidence, runtime\u002Fconfig inspection, and external documentation or issue research when available. It is not a patch generator for guess-first debugging.\n\n## When to Use\n\n- Implementer reports `BLOCKED`\n- Reviewer rejection repeats after remediation\n- Validation fails unexpectedly\n- A task appears to conflict with runtime or platform reality\n- The same failure survives more than one attempted fix\n\nDo not use this skill to speculate about fixes before gathering evidence.\n\n## Inputs\n\nProvide:\n- Exact failure symptom or blocker statement\n- Error messages, stack trace, and failing command output\n- Current `git diff` or summary of uncommitted failed changes\n- Task brief: what was being built\n- Reviewer feedback, if the failure came from review rejection\n- Relevant spec file paths (`requirements.md`, `design.md`)\n- Relevant requirement\u002Fdesign section numbers\n- Relevant `## Implementation Notes`\n- Runtime or environment constraints already known\n\n## Outputs\n\nReturn:\n- `ROOT_CAUSE`\n- `CATEGORY`\n- `FIX_PLAN`\n- `VERIFICATION`\n- `NEXT_ACTION: RETRY_TASK | BLOCK_TASK | STOP_FOR_HUMAN`\n- `CONFIDENCE: HIGH | MEDIUM | LOW`\n- `NOTES`\n\nUse the language specified in `spec.json`.\n\n## Method\n\n### 1. Read the Error Carefully\nExtract:\n- Exact error text\n- Stack trace or failure location\n- The command that produced the failure\n- Whether the failure is deterministic or intermittent\n\n### 2. Inspect Local Runtime and Repository State\nInspect the repository for local evidence:\n- `package.json`, `pyproject.toml`, `go.mod`, `Makefile`, `README*`\n- Build config\n- `tsconfig` or equivalent language\u002Fruntime config\n- Runtime-specific config\n- Dependency versions and scripts\n- Relevant changed files from `git diff`\n\n### 3. Search the Web if Available\nIf web access is available, search:\n- The exact error message\n- The technology + symptom combination\n- Official documentation\n- Version-specific issue trackers or migration notes\n\nPrefer:\n- Official docs\n- Official repos\u002Fissues\n- Version-specific references\n- Runtime-specific documentation\n\n### 4. Classify the Root Cause\nUse one category:\n- `MISSING_DEPENDENCY`\n- `RUNTIME_MISMATCH`\n- `MODULE_FORMAT`\n- `NATIVE_ABI`\n- `CONFIG_GAP`\n- `LOGIC_ERROR`\n- `TASK_ORDERING_PROBLEM`\n- `TASK_DECOMPOSITION_PROBLEM`\n- `SPEC_CONFLICT`\n- `EXTERNAL_DEPENDENCY`\n\n### 5. Determine the Smallest Safe Next Action\nDecide whether the issue can be fixed inside this repo by:\n- Editing files\n- Adjusting configuration\n- Adding or correcting dependencies\n- Restructuring code\n\nUse `NEXT_ACTION: RETRY_TASK` when the issue is repo-fixable inside the current approved task plan.\n\n### 6. Determine Whether the Task Plan Is Still Valid\nDecide whether the current approved task plan is still safe to execute as written.\n\nPrefer `NEXT_ACTION: STOP_FOR_HUMAN` when:\n- A missing prerequisite task should exist before this one\n- The current task is ordered incorrectly relative to unfinished work\n- The current task boundary is wrong and should be split or merged\n- The task is too large or ambiguous to fix safely inside the current implementation loop\n\nUse `NEXT_ACTION: BLOCK_TASK` only when the current task should stop but the rest of the queue can still proceed safely.\n\nDo not propose a brute-force code fix as a substitute for revising `tasks.md` or the approved plan.\n\n## Critical Rule\n\nDo not propose a multi-fix shotgun plan. Identify the root cause first, then produce the smallest plausible fix plan. If the true problem is a spec conflict or architecture problem, say so directly.\n\n## Stop \u002F Escalate\n\nUse `NEXT_ACTION: STOP_FOR_HUMAN` when the blocker genuinely requires:\n- Human product\u002Frequirements decision\n- External credentials or inaccessible services\n- Hardware or unavailable external systems\n- Re-scoping due to spec\u002Fplatform conflict\n\nIf the issue is fixable by repo changes inside the current task plan, do not escalate prematurely.\n\n## Common Rationalizations\n\n| Rationalization | Reality |\n|---|---|\n| “This probably just needs a quick patch” | Patch-first debugging creates rework. |\n| “Let’s try a few fixes” | Multi-fix guessing hides root cause. |\n| “The spec is probably wrong, I’ll adapt it” | Spec conflicts must be surfaced explicitly. |\n| “The docs search is optional” | For runtime\u002Fdependency issues, docs and version issues often contain the shortest path to root cause. |\n\n## Output Format\n\n```md\n## Debug Report\n- ROOT_CAUSE: \u003C1-2 sentence root cause>\n- CATEGORY: MISSING_DEPENDENCY | RUNTIME_MISMATCH | MODULE_FORMAT | NATIVE_ABI | CONFIG_GAP | LOGIC_ERROR | TASK_ORDERING_PROBLEM | TASK_DECOMPOSITION_PROBLEM | SPEC_CONFLICT | EXTERNAL_DEPENDENCY\n- FIX_PLAN:\n  1. \u003Cspecific repo-fixable action>\n  2. \u003Cspecific repo-fixable action>\n- VERIFICATION: \u003Ccommand(s) to confirm the fix>\n- NEXT_ACTION: RETRY_TASK | BLOCK_TASK | STOP_FOR_HUMAN\n- CONFIDENCE: HIGH | MEDIUM | LOW\n- NOTES: \u003Ccontext the next implementer should know>\n```\n",{"name":5,"description":7,"allowed-tools":46,"argument-hint":47},"Read, Bash, Grep, Glob, WebSearch, WebFetch","\u003Cfailure-summary>","main","3e6b722545091ed1bb6b81fe15f38189099154c1",".claude\u002Fskills\u002Fkiro-debug",0,"https:\u002F\u002Fgithub.com\u002Fj5ik2o\u002Fai-tools","https:\u002F\u002Fgithub.com\u002Fj5ik2o","https:\u002F\u002Flapras.com\u002Fpublic\u002FNHXS5RH","I'm a tech-lead in the IDEO;PLUS Inc, is lover to Scala\u002FRust, Akka, DDD\u002FCQRS+Event Sourcing.","2026-11-11 20:34:50",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add j5ik2o\u002Fai-tools --skill kiro-debug",{"tool":63,"command":64},"bunx","bunx skills add j5ik2o\u002Fai-tools --skill kiro-debug",{"tool":66,"command":67},"pnpm","pnpm dlx skills add j5ik2o\u002Fai-tools --skill kiro-debug","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fj5ik2o\u002Fai-tools\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fkiro-debug\u002FSKILL.md",true,[],[72,87,94,115,126,138],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":83,"publishedAt":41},"01M6D03X604YGMM6YFEG4M6767","takt","TAKT ワークフローエンジン。Agent Team を使ったマルチエージェントオーケストレーション。ワークフロー YAML（steps \u002F initial_step）に従ってマルチエージェントを実行する。","https:\u002F\u002Fgithub.com\u002Fj5ik2o\u002Fai-tools\u002Fblob\u002Fmain\u002Fplugins\u002Ftakt\u002Fskills\u002Fj5ik2o-takt-workflow-builder\u002Freferences\u002Ftakt\u002Fbuiltins\u002Fskill\u002FSKILL.md",[78],{"categoryNo":79,"categoryName":80,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[74,84,85,86],"agent team","team","yaml",{"skillNo":88,"name":74,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":41},"01M6D03TAJ6WKRV6XACZHZ70NS","TAKT ワークフローエンジン。codex exec でサブエージェントを起動し、ワークフロー YAML（steps \u002F initial_step）に従って マルチエージェントオーケストレーションを実行する。","https:\u002F\u002Fgithub.com\u002Fj5ik2o\u002Fai-tools\u002Fblob\u002Fmain\u002Fplugins\u002Ftakt\u002Fskills\u002Fj5ik2o-takt-workflow-builder\u002Freferences\u002Ftakt\u002Fbuiltins\u002Fskill-codex\u002FSKILL.md",[],[74,86,93],"codex",{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":104,"publishedAt":41},"01M6D02V9SQ13TEDYDGN67K3WA","j5ik2o-takt-workflow-builder","TAKTワークフロー（ワークフローYAML）の作成・カスタマイズスキル。Faceted Prompting （Persona\u002FPolicy\u002FInstruction\u002FKnowledge\u002FOutput Contract）に基づくファセット群の 生成を含む。references\u002Ftaktにあるtaktのソースコード・ドキュメント・ビルトインワークフロー群を 参照資料として活用する。ユーザーの要件をヒアリングし、step構成、ルール設計、 ファセットファイル生成を一括で行う。 トリガー：「ワークフローを作りたい」「ワークフローを定義」「taktのワークフローを作成」 「新しいtaktワークフローを作って」「takt workflow」「ワークフローYAML」","https:\u002F\u002Fgithub.com\u002Fj5ik2o\u002Fai-tools\u002Fblob\u002Fmain\u002Fplugins\u002Ftakt\u002Fskills\u002Fj5ik2o-takt-workflow-builder\u002FSKILL.md",[100,101],{"categoryNo":79,"categoryName":80,"taxonomyType":81,"taxonomyTypeDesc":82},{"categoryNo":102,"categoryName":103,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000037","律师与法务",[105,74,106,107,108,109,110,111,112,113,114],"j5ik2o takt workflow builder","builder","workflow builder","workflow","生成","contract","references","knowledge","persona","policy",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":41},"01M6D02P0Y4DEJ19J6V4S5VZ2S","j5ik2o-takt-task-builder","TAKTのtasks.yaml（タスクメタデータ）とタスクディレクトリ（.takt\u002Ftasks\u002F{slug}\u002Forder.md）の 作成・編集を支援するスキル。TaskRecordスキーマに準拠したYAMLエントリの生成、 order.mdタスク仕様書の作成、ステータス遷移ルールの検証を行う。 references\u002Ftaktにあるtaskスキーマ定義・ドキュメントを参照資料として活用する。 トリガー：「タスクを追加」「tasks.yamlを編集」「taktタスクを作成」 「タスク仕様書を書く」「order.mdを作成」「takt task」「タスクを定義」 「pendingタスクを追加」「GitHub Issueからタスク作成」","https:\u002F\u002Fgithub.com\u002Fj5ik2o\u002Fai-tools\u002Fblob\u002Fmain\u002Fplugins\u002Ftakt\u002Fskills\u002Fj5ik2o-takt-task-builder\u002FSKILL.md",[],[74,122,123,106,111,109,86,124,125],"j5ik2o takt task builder","task","tasks","github",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":133,"publishedAt":41},"01M6D022WYSR825B6KB2CSNNY0","j5ik2o-takt-skill-updater","nrslib\u002Ftakt の新バージョンリリース時に、takt-*スキル群（j5ik2o-takt-task-builder, j5ik2o-takt-workflow-builder, j5ik2o-takt-facet-builder, j5ik2o-takt-analyzer, j5ik2o-takt-optimizer）を最新のtaktバージョンに追従させるスキル。 TypeScriptスキーマ（taskRecordSchemas.ts \u002F taskExecutionSchemas.ts）、ワークフローYAML、ファセットMarkdownの差分を検出し、 SKILL.md・参照ドキュメント（task-schema.md等）を体系的に更新する。 トリガー：「taktスキルを更新」「takt-*スキルの鮮度チェック」「taktバージョンアップ対応」 「スキルが古くないか確認」「takt skill updater」","https:\u002F\u002Fgithub.com\u002Fj5ik2o\u002Fai-tools\u002Fblob\u002Fmain\u002Fplugins\u002Ftakt\u002Fskills\u002Fj5ik2o-takt-skill-updater\u002FSKILL.md",[132],{"categoryNo":79,"categoryName":80,"taxonomyType":81,"taxonomyTypeDesc":82},[74,134,135,108,136,106,123,137],"skill updater","j5ik2o takt skill updater","schema","optimizer",{"skillNo":139,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":143,"publishedAt":41},"01M6D01Z6WJEXJTXRKEK6N2NBM","https:\u002F\u002Fgithub.com\u002Fj5ik2o\u002Fai-tools\u002Fblob\u002Fmain\u002Fplugins\u002Ftakt\u002Fskills\u002Fj5ik2o-takt-optimizer\u002Freferences\u002Ftakt\u002Fbuiltins\u002Fskill\u002FSKILL.md",[142],{"categoryNo":79,"categoryName":80,"taxonomyType":81,"taxonomyTypeDesc":82},[74,85,84,86]]