[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NQ4ZXG14PJXVQZHTPY5GZY":3,"skill-same:01M6NQ4ZXG14PJXVQZHTPY5GZY":65},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":14,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":49,"ownerDescription":6,"updatedAt":50,"install":51,"resources":64},"01M6NQ4ZXG14PJXVQZHTPY5GZY","app-plan-feature-stories",null,"Decompose a piece of work into a 3-tier Feature > Story > Task plan tree, written to disk as self-contained markdown files. Use when the user asks to plan a feature, break down work, write an implementation plan, or create a task tree for a larger effort.","carlosmarte\u002Fai-agent-artifacts","carlosmarte","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F3478576?v=4","01M6NPRTEXZG86XJXMGQ05A24X","Carlos Marte","01M6NPRTK4A6A4Q8CMWMH1ZY7W",0,"MIT","https:\u002F\u002Fgithub.com\u002Fcarlosmarte\u002Fai-agent-artifacts\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fapp-plan-feature-stories\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"app plan feature stories","plan","stories","plan feature","feature","app","as","implementation plan","down","for","tree","break down","create","self","task","files","decompose","use","work","disk","2026-11-10 10:12:30",false,"---\nname: app-plan-feature-stories\ndescription: Decompose a piece of work into a 3-tier Feature > Story > Task plan tree, written to disk as self-contained markdown files. Use when the user asks to plan a feature, break down work, write an implementation plan, or create a task tree for a larger effort.\ntier: app\n---\n\n# Plan: Feature > Stories > Tasks\n\nDecompose work into a **3-tier hierarchy** written to disk. Each file is self-contained and independently actionable.\n\nThis skill mirrors the slash command `\u002Fplan-feature-story-task`. Use it when a model does not auto-load slash commands or the user invokes the skill explicitly.\n\n## Input\n\nThe user provides a description of work to be done. It may be vague or detailed. Understand it deeply before decomposing.\n\n## Workflow\n\n### Phase 0: Name the Plan Directory\n\nFormat: `\u003Csuggested_name>-\u003Cdate>-\u003Csession_id>`\n\n1. **`\u003Csuggested_name>`** — short kebab-case slug (max 4 words) derived from the work (e.g., `auth-middleware-rewrite`, `api-rate-limiting`)\n2. **`\u003Cdate>`** — today's date in `YYYYMMDD` (e.g., `20260416`)\n3. **`\u003Csession_id>`** — short UUID v4 prefix, 8 hex chars (e.g., `a1b2c3d4`)\n\nExample: `auth-middleware-rewrite-20260416-a1b2c3d4`\n\nPlace under the project root at `.\u002Fplans\u002F\u003Csuggested_name>-\u003Cdate>-\u003Csession_id>\u002F`. All references below to `\u003Cplan-dir>\u002F` point here. If the user specifies a different location, use that instead.\n\n### Phase 1: Understand\n\n1. Read the user's request carefully.\n2. Explore the codebase to understand relevant code, architecture, patterns.\n3. Ask clarifying questions if scope, goals, or constraints are ambiguous. Do not proceed until context is sufficient.\n\n### Phase 2: Decompose\n\nThree levels:\n\n**Feature** — a distinct, deliverable capability. _\"What does the user\u002Fsystem gain when this is done?\"_\n- Independently shippable\n- Named by capability delivered, not implementation detail\n\n**Story** — a behavior slice within a feature. _\"What specific behavior changes when this story is complete?\"_\n- One observable change (user-facing or system-facing)\n- Orderable by dependency within a feature\n- Completable in a single focused session\n\n**Task** — an atomic implementation step within a story. _\"What exact code change do I make, and how do I verify it worked?\"_\n- Targets specific files with specific changes\n- Minutes to hours, not days\n- Includes verification steps (test, behavior check, command)\n\n### Phase 3: Write the Plan\n\nCreate this tree under `.\u002Fplans\u002F\u003Cplan-dir>\u002F`:\n\n```\n\u003Cplan-dir>\u002F\n├── README.md\n├── features\u002F\n│   ├── 01-\u003Cfeature-name>.md\n│   └── 02-\u003Cfeature-name>.md\n├── stories\u002F\n│   ├── 01\u002F\n│   │   ├── 01-\u003Cstory-name>.md\n│   │   └── 02-\u003Cstory-name>.md\n│   └── 02\u002F\n│       └── 01-\u003Cstory-name>.md\n└── tasks\u002F\n    ├── 01\u002F\n    │   ├── 01\u002F\n    │   │   ├── 01-\u003Ctask-name>.md\n    │   │   └── 02-\u003Ctask-name>.md\n    │   └── 02\u002F\n    │       └── 01-\u003Ctask-name>.md\n    └── 02\u002F\n        └── 01\u002F\n            └── 01-\u003Ctask-name>.md\n```\n\nNaming: `\u003CNN>-\u003Ckebab-case-name>.md`. Numeric prefix preserves ordering. Stories and tasks are grouped by their parent's feature number.\n\n## File Templates\n\n### `\u003Cplan-dir>\u002FREADME.md`\n\n```markdown\n# Plan: \u003CPlan Title>\n\n## Goal\n\n\u003CWhat this plan achieves — 2-3 sentences>\n\n## Scope\n\n\u003CIn scope and explicitly out of scope>\n\n## Features\n\n| #   | Feature                                     | Stories | Description      |\n| --- | ------------------------------------------- | ------- | ---------------- |\n| 01  | [Feature Name](features\u002F01-feature-name.md) | N       | One-line summary |\n\n## Execution Order\n\n\u003CRecommended order, noting dependencies>\n```\n\n### `\u003Cplan-dir>\u002Ffeatures\u002FNN-feature-name.md`\n\n```markdown\n# Feature: \u003CFeature Title>\n\n## Goal\n\n\u003CCapability this feature delivers — 1-2 sentences>\n\n## Acceptance Criteria\n\n- [ ] \u003CObservable outcome 1>\n- [ ] \u003CObservable outcome 2>\n\n## Stories\n\n| #   | Story                                        | Tasks | Description      |\n| --- | -------------------------------------------- | ----- | ---------------- |\n| 01  | [Story Name](..\u002Fstories\u002FNN\u002F01-story-name.md) | N     | One-line summary |\n\n## Notes\n\n\u003CArchitectural decisions, constraints, context specific to this feature>\n```\n\n### `\u003Cplan-dir>\u002Fstories\u002FNN\u002FNN-story-name.md`\n\n```markdown\n# Story: \u003CStory Title>\n\n**Feature:** [\u003CParent Feature Name>](..\u002F..\u002Ffeatures\u002FNN-feature-name.md)\n\n## Context\n\n\u003CWhy this story exists and what behavior it changes — enough to understand without reading the parent>\n\n## Acceptance Criteria\n\n- [ ] \u003CTestable behavior 1>\n\n## Dependencies\n\n- \u003COther stories this depends on, with paths, or \"None\">\n\n## Tasks\n\n| #   | Task                                           | Description      |\n| --- | ---------------------------------------------- | ---------------- |\n| 01  | [Task Name](..\u002F..\u002Ftasks\u002FNN\u002FNN\u002F01-task-name.md) | One-line summary |\n```\n\n### `\u003Cplan-dir>\u002Ftasks\u002FNN\u002FNN\u002FNN-task-name.md`\n\n```markdown\n# Task: \u003CTask Title>\n\n**Story:** [\u003CParent Story Name>](..\u002F..\u002F..\u002Fstories\u002FNN\u002FNN-story-name.md)\n\n## Context\n\n\u003CWhat this task accomplishes and why — enough to execute without reading parent files>\n\n## Target Files\n\n- `\u003Cpath\u002Fto\u002Ffile.ext>` — \u003Cwhat changes>\n\n## Changes\n\n\u003CSpecific code changes. Concrete: function names, data structures, logic flow.>\n\n## Verification\n\n- [ ] \u003CCommand to run, test to check, behavior to observe>\n```\n\n## Rules\n\n1. **Self-contained files** — every file includes enough context to act on independently.\n2. **Relative links** — all cross-references use relative markdown links.\n3. **No empty shells** — every field has real content. If you cannot fill a field, decomposition is not detailed enough — investigate further.\n4. **Concrete tasks** — name specific files and describe specific changes. \"Update the config\" is not a task. \"Add `rateLimitPool` field to `src\u002Fconfig\u002Fschema.mjs` with Zod enum validation\" is a task.\n5. **Verify before writing** — confirm file paths, function names, and patterns by reading actual code before referencing them.\n\n## After Writing\n\nSummarize to the user:\n\n- Total count: N features, N stories, N tasks\n- Recommended execution order\n- Risks, open questions, or decisions needing user input\n\n## Reference\n\nSource command: `.claude\u002Fcommands\u002Fplan-feature-story-task.md`.\n","# Plan: Feature > Stories > Tasks\n\nDecompose work into a **3-tier hierarchy** written to disk. Each file is self-contained and independently actionable.\n\nThis skill mirrors the slash command `\u002Fplan-feature-story-task`. Use it when a model does not auto-load slash commands or the user invokes the skill explicitly.\n\n## Input\n\nThe user provides a description of work to be done. It may be vague or detailed. Understand it deeply before decomposing.\n\n## Workflow\n\n### Phase 0: Name the Plan Directory\n\nFormat: `\u003Csuggested_name>-\u003Cdate>-\u003Csession_id>`\n\n1. **`\u003Csuggested_name>`** — short kebab-case slug (max 4 words) derived from the work (e.g., `auth-middleware-rewrite`, `api-rate-limiting`)\n2. **`\u003Cdate>`** — today's date in `YYYYMMDD` (e.g., `20260416`)\n3. **`\u003Csession_id>`** — short UUID v4 prefix, 8 hex chars (e.g., `a1b2c3d4`)\n\nExample: `auth-middleware-rewrite-20260416-a1b2c3d4`\n\nPlace under the project root at `.\u002Fplans\u002F\u003Csuggested_name>-\u003Cdate>-\u003Csession_id>\u002F`. All references below to `\u003Cplan-dir>\u002F` point here. If the user specifies a different location, use that instead.\n\n### Phase 1: Understand\n\n1. Read the user's request carefully.\n2. Explore the codebase to understand relevant code, architecture, patterns.\n3. Ask clarifying questions if scope, goals, or constraints are ambiguous. Do not proceed until context is sufficient.\n\n### Phase 2: Decompose\n\nThree levels:\n\n**Feature** — a distinct, deliverable capability. _\"What does the user\u002Fsystem gain when this is done?\"_\n- Independently shippable\n- Named by capability delivered, not implementation detail\n\n**Story** — a behavior slice within a feature. _\"What specific behavior changes when this story is complete?\"_\n- One observable change (user-facing or system-facing)\n- Orderable by dependency within a feature\n- Completable in a single focused session\n\n**Task** — an atomic implementation step within a story. _\"What exact code change do I make, and how do I verify it worked?\"_\n- Targets specific files with specific changes\n- Minutes to hours, not days\n- Includes verification steps (test, behavior check, command)\n\n### Phase 3: Write the Plan\n\nCreate this tree under `.\u002Fplans\u002F\u003Cplan-dir>\u002F`:\n\n```\n\u003Cplan-dir>\u002F\n├── README.md\n├── features\u002F\n│   ├── 01-\u003Cfeature-name>.md\n│   └── 02-\u003Cfeature-name>.md\n├── stories\u002F\n│   ├── 01\u002F\n│   │   ├── 01-\u003Cstory-name>.md\n│   │   └── 02-\u003Cstory-name>.md\n│   └── 02\u002F\n│       └── 01-\u003Cstory-name>.md\n└── tasks\u002F\n    ├── 01\u002F\n    │   ├── 01\u002F\n    │   │   ├── 01-\u003Ctask-name>.md\n    │   │   └── 02-\u003Ctask-name>.md\n    │   └── 02\u002F\n    │       └── 01-\u003Ctask-name>.md\n    └── 02\u002F\n        └── 01\u002F\n            └── 01-\u003Ctask-name>.md\n```\n\nNaming: `\u003CNN>-\u003Ckebab-case-name>.md`. Numeric prefix preserves ordering. Stories and tasks are grouped by their parent's feature number.\n\n## File Templates\n\n### `\u003Cplan-dir>\u002FREADME.md`\n\n```markdown\n# Plan: \u003CPlan Title>\n\n## Goal\n\n\u003CWhat this plan achieves — 2-3 sentences>\n\n## Scope\n\n\u003CIn scope and explicitly out of scope>\n\n## Features\n\n| #   | Feature                                     | Stories | Description      |\n| --- | ------------------------------------------- | ------- | ---------------- |\n| 01  | [Feature Name](features\u002F01-feature-name.md) | N       | One-line summary |\n\n## Execution Order\n\n\u003CRecommended order, noting dependencies>\n```\n\n### `\u003Cplan-dir>\u002Ffeatures\u002FNN-feature-name.md`\n\n```markdown\n# Feature: \u003CFeature Title>\n\n## Goal\n\n\u003CCapability this feature delivers — 1-2 sentences>\n\n## Acceptance Criteria\n\n- [ ] \u003CObservable outcome 1>\n- [ ] \u003CObservable outcome 2>\n\n## Stories\n\n| #   | Story                                        | Tasks | Description      |\n| --- | -------------------------------------------- | ----- | ---------------- |\n| 01  | [Story Name](..\u002Fstories\u002FNN\u002F01-story-name.md) | N     | One-line summary |\n\n## Notes\n\n\u003CArchitectural decisions, constraints, context specific to this feature>\n```\n\n### `\u003Cplan-dir>\u002Fstories\u002FNN\u002FNN-story-name.md`\n\n```markdown\n# Story: \u003CStory Title>\n\n**Feature:** [\u003CParent Feature Name>](..\u002F..\u002Ffeatures\u002FNN-feature-name.md)\n\n## Context\n\n\u003CWhy this story exists and what behavior it changes — enough to understand without reading the parent>\n\n## Acceptance Criteria\n\n- [ ] \u003CTestable behavior 1>\n\n## Dependencies\n\n- \u003COther stories this depends on, with paths, or \"None\">\n\n## Tasks\n\n| #   | Task                                           | Description      |\n| --- | ---------------------------------------------- | ---------------- |\n| 01  | [Task Name](..\u002F..\u002Ftasks\u002FNN\u002FNN\u002F01-task-name.md) | One-line summary |\n```\n\n### `\u003Cplan-dir>\u002Ftasks\u002FNN\u002FNN\u002FNN-task-name.md`\n\n```markdown\n# Task: \u003CTask Title>\n\n**Story:** [\u003CParent Story Name>](..\u002F..\u002F..\u002Fstories\u002FNN\u002FNN-story-name.md)\n\n## Context\n\n\u003CWhat this task accomplishes and why — enough to execute without reading parent files>\n\n## Target Files\n\n- `\u003Cpath\u002Fto\u002Ffile.ext>` — \u003Cwhat changes>\n\n## Changes\n\n\u003CSpecific code changes. Concrete: function names, data structures, logic flow.>\n\n## Verification\n\n- [ ] \u003CCommand to run, test to check, behavior to observe>\n```\n\n## Rules\n\n1. **Self-contained files** — every file includes enough context to act on independently.\n2. **Relative links** — all cross-references use relative markdown links.\n3. **No empty shells** — every field has real content. If you cannot fill a field, decomposition is not detailed enough — investigate further.\n4. **Concrete tasks** — name specific files and describe specific changes. \"Update the config\" is not a task. \"Add `rateLimitPool` field to `src\u002Fconfig\u002Fschema.mjs` with Zod enum validation\" is a task.\n5. **Verify before writing** — confirm file paths, function names, and patterns by reading actual code before referencing them.\n\n## After Writing\n\nSummarize to the user:\n\n- Total count: N features, N stories, N tasks\n- Recommended execution order\n- Risks, open questions, or decisions needing user input\n\n## Reference\n\nSource command: `.claude\u002Fcommands\u002Fplan-feature-story-task.md`.\n",{"name":5,"tier":24,"description":7},"main","b78f8878258c912b66be9d4b56b316515e44c728",".claude\u002Fskills\u002Fapp-plan-feature-stories","https:\u002F\u002Fgithub.com\u002Fcarlosmarte\u002Fai-agent-artifacts","https:\u002F\u002Fgithub.com\u002Fcarlosmarte","http:\u002F\u002Fcarlosmarte.me\u002F","2026-08-25 00:53:46",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add carlosmarte\u002Fai-agent-artifacts --skill app-plan-feature-stories",{"tool":57,"command":58},"bunx","bunx skills add carlosmarte\u002Fai-agent-artifacts --skill app-plan-feature-stories",{"tool":60,"command":61},"pnpm","pnpm dlx skills add carlosmarte\u002Fai-agent-artifacts --skill app-plan-feature-stories","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcarlosmarte\u002Fai-agent-artifacts\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fapp-plan-feature-stories\u002FSKILL.md",true,[],[66,92,119,158,184,207],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":39},"01M6NQ7MN7FKWQE3CKRWKVAC9K","validation_handoff","Forces the agent to conclude its response by generating a strict validation checklist and outlining pending actions, focusing heavily on defensive execution and edge-case testing.","https:\u002F\u002Fgithub.com\u002Fcarlosmarte\u002Fai-agent-artifacts\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalidation_handoff\u002FSKILL.md",[],[73,74,75,76,77,78,79,80,81,82,83,84,85,23,86,87,88,89,90,91],"handoff","validation","validation handoff","testing","architecture","edge","actions","refactor","execution","system","implementation","checklist","feature implementation","end","case","defensive","hook","at","pending",{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":39},"01M6NQ74C8EKMSABDNN4T6TFBD","project-ployglot-project-scafford","Scaffold a polyglot library project as TypeScript + Python twin packages under `packages\u002Fts\u002F` + `packages\u002Fpy\u002F`, with a shared `SPEC.md`, cross-language `tests\u002Fparity\u002Ffixtures.json`, side-by-side `examples\u002Fsdk\u002F` + `examples\u002Fapi\u002F` documentation, per-package `Makefile`, and a root orchestrator that exposes `make ci`. Open-source friendly — no organization-specific paths or scopes baked in. Use when starting a new polyglot library, porting a single-language library to a twin, or auditing\u002Fregularizing an existing two-language repo against the canonical layout.","https:\u002F\u002Fgithub.com\u002Fcarlosmarte\u002Fai-agent-artifacts\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fproject-ployglot-project-scafford\u002FSKILL.md",[],[99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118],"project","project ployglot project scafford","documentation","packages","run","ci","api","open","makefile","Bash","read","orchestrator","only","organization","shared","layout","dry","false","scope","\u003Cslug>",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":141,"publishedAt":39},"01M6NQ6VJVPM37YA73T8BCD3VF","playwright-ui-locator","Auto-heal Playwright tests after a frontend developer changes a div's class, id, or other selector. Catches a failing Playwright test, captures the old vs new DOM tree, finds the element that drifted, derives the most stable replacement locator, and proposes the fix as a GitHub pull request (confident heals) or files a GitHub issue (ambiguous \u002F element-removed cases) — never editing the working tree directly. Trigger when Playwright tests fail with \"locator resolved to 0 elements\", \"Timeout waiting for selector\", or after a UI refactor \u002F class rename \u002F Tailwind cleanup broke previously-passing tests.","https:\u002F\u002Fgithub.com\u002Fcarlosmarte\u002Fai-agent-artifacts\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fplaywright-test-gh-auto-heal-ui-locator\u002FSKILL.md",[125,130,133,136],{"categoryNo":126,"categoryName":127,"taxonomyType":128,"taxonomyTypeDesc":129},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",{"categoryNo":131,"categoryName":132,"taxonomyType":128,"taxonomyTypeDesc":129},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":134,"categoryName":135,"taxonomyType":128,"taxonomyTypeDesc":129},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":137,"categoryName":138,"taxonomyType":139,"taxonomyTypeDesc":140},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[142,143,144,145,146,147,108,109,148,149,150,151,152,153,154,34,155,116,156,157],"playwright","ui","playwright ui locator","frontend","cleanup","Tailwind","write","edit","fix","snapshot","auto","never","issue","rename","element","request",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":167,"publishedAt":39},"01M6NQ6BCW05C6Y6VRV0RBQD1V","org-learn-context-window","Distill the current conversation into a reusable command or skill artifact. Use when the user wants to capture a workflow they just executed (create a reusable slash command) or formalize a resolution\u002Fmistake\u002Fcorrection into a reusable skill so the same class of issue never recurs.","https:\u002F\u002Fgithub.com\u002Fcarlosmarte\u002Fai-agent-artifacts\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Forg-learn-context-window\u002FSKILL.md",[164],{"categoryNo":165,"categoryName":166,"taxonomyType":128,"taxonomyTypeDesc":129},"01JBSEEDCAT000000000000023","Skill与智能体开发",[168,169,170,171,172,173,31,174,175,176,177,178,36,153,154,179,180,181,182,183],"learn","context","org","window","org learn context window","workflow","just","capture","distill","command","user","reusable","conversation","artifact","resolution","skill artifact",{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":191,"publishedAt":39},"01M6NQ66NFPQM1PDBHP1B2G82X","org-agent-skill-creator","Scaffold and validate scope-aware agent skills (company, enterprise, org, team, project, application). Use when the user asks to create a new agent skill, generate a SKILL.md file, scaffold a skill directory, or validate that existing skill directories meet SKILL_SPEC.md (frontmatter, naming rules, structure, scope\u002Ftier).","https:\u002F\u002Fgithub.com\u002Fcarlosmarte\u002Fai-agent-artifacts\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Forg-agent-skill-creator\u002FSKILL.md",[190],{"categoryNo":165,"categoryName":166,"taxonomyType":128,"taxonomyTypeDesc":129},[192,193,170,194,195,196,31,197,198,199,200,36,201,202,99,117,203,204,205,206],"skill creator","agent skill","agent skill creator","creator","org agent skill creator","file","Enterprise","team","Rules","structure","new agent","directories","Existing","company","Meet",{"skillNo":208,"name":209,"nameZh":6,"description":210,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":211,"categories":212,"keywords":216,"publishedAt":39},"01M6NQ5VSH5M682YMYDF9H9KFE","app-workshop-session-pdf-recap-next","Extract content from a workshop session PDF and produce a structured recap focused on (1) what was learned, (2) next steps, and (3) possible enhancements. Ingests a single PDF file path, parses session material (slides, transcripts, exercises, Q&A), and emits a Markdown report with Learning Recap, Next Steps, and Enhancement Opportunities sections with page-level traceability. Use when the user asks to \"summarize a workshop\", \"recap a training PDF\", \"pull next steps from a session deck\", or provides a workshop\u002Fseminar\u002Ftutorial PDF and wants a learn-and-act summary.","https:\u002F\u002Fgithub.com\u002Fcarlosmarte\u002Fai-agent-artifacts\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fapp-workshop-session-pdf-recap-next\u002FSKILL.md",[213],{"categoryNo":214,"categoryName":215,"taxonomyType":128,"taxonomyTypeDesc":129},"01JBSEEDCAT000000000000002","文档处理",[217,218,219,220,24,221,222,168,223,224,225,226,227,228,36,229,116,230,231,232],"PDF","recap","session","next","app workshop session pdf recap next","training","pull","produce","learning","slides","page","tutorial","deck","material","traceability","next steps"]