[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NQ66NFPQM1PDBHP1B2G82X":3,"skill-same:01M6NQ66NFPQM1PDBHP1B2G82X":70},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":14,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":6,"updatedAt":55,"install":56,"resources":69},"01M6NQ66NFPQM1PDBHP1B2G82X","org-agent-skill-creator",null,"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).","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\u002Forg-agent-skill-creator\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],"agent skill","org agent skill creator","creator","agent skill creator","org","skill creator","use","structure","new agent","project","Rules","scope","team","Enterprise","directories","file","Existing","company","Meet","create","2026-11-10 10:12:30",false,"---\nname: org-agent-skill-creator\ndescription: 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).\ntier: org\n---\n\n# Agent Skill Creator (Scope-Aware)\n\nScaffold a new agent skill OR validate an existing one against `SKILL_SPEC.md`. Every skill is scoped to **one** of six tiers — each tier owns a distinct slice of knowledge\u002Fcontext — and the scope is encoded in both the directory-name prefix and the `tier:` frontmatter field.\n\nThis skill mirrors the slash commands `\u002Fagent-skill-create` and `\u002Fagent-skill-validate`. Use it when slash commands are not auto-loaded or when the user invokes the skill explicitly.\n\n## Mode Selection\n\nPick a mode based on the user's request:\n\n- **create** — user wants to make a new skill (\"create a skill\", \"scaffold a new skill\", \"new agent skill\")\n- **validate** — user wants to check existing skills (\"validate skill X\", \"check if this skill meets the spec\", \"audit skills\")\n\nIf ambiguous, ask the user which mode before proceeding.\n\n---\n\n## Scope Tiers\n\nEvery skill belongs to exactly one scope. The scope determines what kind of knowledge\u002Fcontext the skill encodes, the directory-name prefix, and the `tier:` frontmatter value.\n\n| Scope | Prefix | `tier:` value | Knowledge \u002F context the skill owns |\n|-------|--------|---------------|------------------------------------|\n| **company** | `company-` | `company` | Company-wide policy, brand, legal\u002Fcompliance baselines, security floor, code-of-conduct. Applies to every employee and every codebase the company touches. |\n| **enterprise** | `enterprise-` | `enterprise` | Multi-org \u002F multi-division standards: shared platforms, cross-BU governance, procurement-approved tooling, enterprise architecture patterns. Sits above org but below company. |\n| **org** | `org-` | `org` | Engineering-org or business-unit standards: shared workflows, common tooling choices, on-call\u002Frelease norms, naming conventions, repo-template policy. |\n| **team** | `team-` | `team` | Team-level conventions: tech-stack picks, coding style, review checklist, on-call rotation, sprint cadence. Specific to one squad\u002Fteam. |\n| **project** | `project-` | `project` | Project-specific architecture, build\u002Ftest pipeline, dependency graph, domain language, milestone plan. Bound to one repo or coordinated set of repos. |\n| **application** | `app-` | `application` | Application-runtime concerns: deployed surfaces, integration points, env-config, observability, customer-facing behavior. Bound to one running service or product. |\n\nNote: `application` uses the historical `app-` prefix to stay backwards-compatible with existing skills (e.g. `app-plan-feature-stories`). Do not introduce `application-` as a prefix.\n\n### Scope decision questions\n\nWhen the user is unsure which scope to pick, ask:\n\n1. **Who is the audience?** Every employee → company. Multiple orgs\u002FBUs → enterprise. One org → org. One team → team. One repo → project. One running service → application.\n2. **Where does the knowledge live today?** Legal\u002Fpolicy site → company. Enterprise wiki \u002F architecture council → enterprise. Org handbook → org. Team README → team. Repo docs → project. Runbook \u002F service dashboard → application.\n3. **If this knowledge were wrong, who would file the bug?** Picks the owning scope.\n\n---\n\n## Create Mode\n\n### Input\n\nExpected args: `\u003Cskill-name>` or `\u003Cskill-name> \u003Cshort description>`.\n- If only a name is given, ask for a description before proceeding.\n- If empty, ask for a name, scope, and description.\n\n### Step 1: Ask the user which scope to create\n\n**Always ask** which scope the new skill belongs to. Present the six options with their one-line knowledge\u002Fcontext summaries (from the table above) so the user can pick deliberately. If the user names a scope that isn't in the table, push back and offer the closest match — do not invent a seventh tier.\n\nMap the chosen scope to its `\u003Cprefix>` and `\u003Ctier>` for use in Steps 2–5.\n\n### Step 2: Validate the Skill Name\n\nCheck against SKILL_SPEC Section 3.1:\n\n- 1–64 characters\n- Lowercase alphanumeric (`a-z`, `0-9`) and hyphens (`-`) only\n- Cannot start or end with a hyphen\n- Cannot contain consecutive hyphens (`--`)\n\n**Scope-prefix rule:** the final directory name must begin with the chosen scope's prefix (e.g. `team-onboarding-checklist`, `project-ployglot-release-flow`). If the user-provided name lacks the prefix, prepend it automatically and show the corrected name back to the user for confirmation.\n\nIf the name is invalid for any other reason, explain why and suggest a corrected version. Do not proceed until valid.\n\n### Step 3: Determine Skill Location\n\nThe skill directory should be created as a sibling of other skill directories under `.agents\u002Fskills\u002F`. Confirm the target path with the user:\n\n```\n.agents\u002Fskills\u002F\u003Cprefix>\u003Cskill-stem>\u002F\n```\n\n### Step 4: Gather Skill Details\n\nAsk the user (if not provided):\n\n1. **Description** (required) — what it does and when to trigger it\n2. **Knowledge \u002F context payload** — what scope-specific knowledge this skill carries (the answer should reflect the chosen tier — e.g. a `team-` skill should reference team artifacts, not company policy)\n3. **Instructions** — step-by-step body content for the agent\n4. **Optional directories** — `scripts\u002F`, `references\u002F`, `assets\u002F`\n5. **Optional frontmatter** — `license`, `compatibility`, `metadata`, `allowed-tools`\n\n### Step 5: Create the Directory Structure\n\n```\n\u003Cprefix>\u003Cskill-stem>\u002F\n├── SKILL.md\n├── scripts\u002F       # only if requested\n├── references\u002F    # only if requested\n└── assets\u002F        # only if requested\n```\n\n### Step 6: Generate SKILL.md\n\n```markdown\n---\nname: \u003Cprefix>\u003Cskill-stem>\ndescription: \u003Cdescription>\ntier: \u003Ctier>\n---\n\n# \u003CSkill Title>\n\n\u003CBody: scope-specific knowledge, instructions, examples, edge cases>\n```\n\nInclude any optional frontmatter the user specified. Keep the body under 500 lines. The body should make the scope explicit — a `tier: team` skill should not silently embed company-wide policy, and a `tier: company` skill should not encode one team's tech stack.\n\n### Step 7: Validate\n\nRun the **validate mode** mentally against the new skill (including the new tier check in Step 2 below) and report any issues.\n\n### Output\n\n```\n## Created: \u003Cskill-name>\n\nScope: \u003Ctier> (\u003Cone-line knowledge\u002Fcontext summary>)\nLocation: \u003Cfull-path>\n\n### Structure\n\u003Ctree output>\n\n### SKILL.md Preview\n\u003Cfirst 20 lines>\n\nStatus: All validation checks passed.\n```\n\n---\n\n## Validate Mode\n\n### Input\n\nExpected args: path to a skill directory, OR empty \u002F `.` to scan `.agents\u002Fskills\u002F` for all skill directories (any directory containing `SKILL.md`).\n\n### Step 1: Structural Validation\n\n- [ ] Skill directory exists\n- [ ] `SKILL.md` file exists inside\n\n### Step 2: Frontmatter Validation\n\nParse the YAML frontmatter block (between `---` delimiters) and check:\n\n**Required:**\n- [ ] `name` exists and is 1–64 characters\n- [ ] `name` uses only lowercase alphanumeric (`a-z`, `0-9`) and hyphens (`-`)\n- [ ] `name` does not start or end with a hyphen\n- [ ] `name` does not contain consecutive hyphens (`--`)\n- [ ] `name` exactly matches the parent directory name\n- [ ] `description` exists, is non-empty, and is 1–1024 characters\n- [ ] `tier` exists and is one of: `company`, `enterprise`, `org`, `team`, `project`, `application`\n- [ ] `tier` matches the directory-name prefix per the scope table (`company-` → `company`, `enterprise-` → `enterprise`, `org-` → `org`, `team-` → `team`, `project-` → `project`, `app-` → `application`)\n\n**Optional (if present):**\n- [ ] `license` — short string\n- [ ] `compatibility` — max 500 characters\n- [ ] `metadata` — string-to-string key-value map\n- [ ] `allowed-tools` — space-delimited string\n\n### Step 3: Body Content Validation\n\n- [ ] Markdown body exists after the frontmatter\n- [ ] Body is under 500 lines (warn if exceeded)\n- [ ] File references use relative paths (no absolute paths like `\u002Ffoo\u002Fbar`)\n- [ ] Body content is consistent with the declared `tier` (warn if a `tier: team` skill encodes obvious company-wide policy, or vice versa)\n\n### Step 4: Optional Directory Checks\n\nIf present, verify non-empty:\n\n- [ ] `scripts\u002F` — executable or recognized script extensions\n- [ ] `references\u002F` — `.md` or documentation files\n- [ ] `assets\u002F` — resource files\n\n### Output\n\n```\n## Validation: \u003Cskill-name>\n\nScope: \u003Ctier>\nStatus: PASS | FAIL | WARN\n\n### Results\n- [x] Check that passed\n- [ ] Check that failed — reason\n\n### Summary\nX\u002FY checks passed. Z warnings.\n```\n\nFor multiple skills, append a summary table:\n\n```\n| Skill | Scope | Status | Passed | Warnings | Errors |\n|-------|-------|--------|--------|----------|--------|\n```\n\n## Reference\n\nFull spec: `SKILL_SPEC.md` at the repo root.\nSource commands: `.agents\u002Fcommands\u002Fagent-skill-create.md`, `.agents\u002Fcommands\u002Fagent-skill-validate.md`.\n","# Agent Skill Creator (Scope-Aware)\n\nScaffold a new agent skill OR validate an existing one against `SKILL_SPEC.md`. Every skill is scoped to **one** of six tiers — each tier owns a distinct slice of knowledge\u002Fcontext — and the scope is encoded in both the directory-name prefix and the `tier:` frontmatter field.\n\nThis skill mirrors the slash commands `\u002Fagent-skill-create` and `\u002Fagent-skill-validate`. Use it when slash commands are not auto-loaded or when the user invokes the skill explicitly.\n\n## Mode Selection\n\nPick a mode based on the user's request:\n\n- **create** — user wants to make a new skill (\"create a skill\", \"scaffold a new skill\", \"new agent skill\")\n- **validate** — user wants to check existing skills (\"validate skill X\", \"check if this skill meets the spec\", \"audit skills\")\n\nIf ambiguous, ask the user which mode before proceeding.\n\n---\n\n## Scope Tiers\n\nEvery skill belongs to exactly one scope. The scope determines what kind of knowledge\u002Fcontext the skill encodes, the directory-name prefix, and the `tier:` frontmatter value.\n\n| Scope | Prefix | `tier:` value | Knowledge \u002F context the skill owns |\n|-------|--------|---------------|------------------------------------|\n| **company** | `company-` | `company` | Company-wide policy, brand, legal\u002Fcompliance baselines, security floor, code-of-conduct. Applies to every employee and every codebase the company touches. |\n| **enterprise** | `enterprise-` | `enterprise` | Multi-org \u002F multi-division standards: shared platforms, cross-BU governance, procurement-approved tooling, enterprise architecture patterns. Sits above org but below company. |\n| **org** | `org-` | `org` | Engineering-org or business-unit standards: shared workflows, common tooling choices, on-call\u002Frelease norms, naming conventions, repo-template policy. |\n| **team** | `team-` | `team` | Team-level conventions: tech-stack picks, coding style, review checklist, on-call rotation, sprint cadence. Specific to one squad\u002Fteam. |\n| **project** | `project-` | `project` | Project-specific architecture, build\u002Ftest pipeline, dependency graph, domain language, milestone plan. Bound to one repo or coordinated set of repos. |\n| **application** | `app-` | `application` | Application-runtime concerns: deployed surfaces, integration points, env-config, observability, customer-facing behavior. Bound to one running service or product. |\n\nNote: `application` uses the historical `app-` prefix to stay backwards-compatible with existing skills (e.g. `app-plan-feature-stories`). Do not introduce `application-` as a prefix.\n\n### Scope decision questions\n\nWhen the user is unsure which scope to pick, ask:\n\n1. **Who is the audience?** Every employee → company. Multiple orgs\u002FBUs → enterprise. One org → org. One team → team. One repo → project. One running service → application.\n2. **Where does the knowledge live today?** Legal\u002Fpolicy site → company. Enterprise wiki \u002F architecture council → enterprise. Org handbook → org. Team README → team. Repo docs → project. Runbook \u002F service dashboard → application.\n3. **If this knowledge were wrong, who would file the bug?** Picks the owning scope.\n\n---\n\n## Create Mode\n\n### Input\n\nExpected args: `\u003Cskill-name>` or `\u003Cskill-name> \u003Cshort description>`.\n- If only a name is given, ask for a description before proceeding.\n- If empty, ask for a name, scope, and description.\n\n### Step 1: Ask the user which scope to create\n\n**Always ask** which scope the new skill belongs to. Present the six options with their one-line knowledge\u002Fcontext summaries (from the table above) so the user can pick deliberately. If the user names a scope that isn't in the table, push back and offer the closest match — do not invent a seventh tier.\n\nMap the chosen scope to its `\u003Cprefix>` and `\u003Ctier>` for use in Steps 2–5.\n\n### Step 2: Validate the Skill Name\n\nCheck against SKILL_SPEC Section 3.1:\n\n- 1–64 characters\n- Lowercase alphanumeric (`a-z`, `0-9`) and hyphens (`-`) only\n- Cannot start or end with a hyphen\n- Cannot contain consecutive hyphens (`--`)\n\n**Scope-prefix rule:** the final directory name must begin with the chosen scope's prefix (e.g. `team-onboarding-checklist`, `project-ployglot-release-flow`). If the user-provided name lacks the prefix, prepend it automatically and show the corrected name back to the user for confirmation.\n\nIf the name is invalid for any other reason, explain why and suggest a corrected version. Do not proceed until valid.\n\n### Step 3: Determine Skill Location\n\nThe skill directory should be created as a sibling of other skill directories under `.agents\u002Fskills\u002F`. Confirm the target path with the user:\n\n```\n.agents\u002Fskills\u002F\u003Cprefix>\u003Cskill-stem>\u002F\n```\n\n### Step 4: Gather Skill Details\n\nAsk the user (if not provided):\n\n1. **Description** (required) — what it does and when to trigger it\n2. **Knowledge \u002F context payload** — what scope-specific knowledge this skill carries (the answer should reflect the chosen tier — e.g. a `team-` skill should reference team artifacts, not company policy)\n3. **Instructions** — step-by-step body content for the agent\n4. **Optional directories** — `scripts\u002F`, `references\u002F`, `assets\u002F`\n5. **Optional frontmatter** — `license`, `compatibility`, `metadata`, `allowed-tools`\n\n### Step 5: Create the Directory Structure\n\n```\n\u003Cprefix>\u003Cskill-stem>\u002F\n├── SKILL.md\n├── scripts\u002F       # only if requested\n├── references\u002F    # only if requested\n└── assets\u002F        # only if requested\n```\n\n### Step 6: Generate SKILL.md\n\n```markdown\n---\nname: \u003Cprefix>\u003Cskill-stem>\ndescription: \u003Cdescription>\ntier: \u003Ctier>\n---\n\n# \u003CSkill Title>\n\n\u003CBody: scope-specific knowledge, instructions, examples, edge cases>\n```\n\nInclude any optional frontmatter the user specified. Keep the body under 500 lines. The body should make the scope explicit — a `tier: team` skill should not silently embed company-wide policy, and a `tier: company` skill should not encode one team's tech stack.\n\n### Step 7: Validate\n\nRun the **validate mode** mentally against the new skill (including the new tier check in Step 2 below) and report any issues.\n\n### Output\n\n```\n## Created: \u003Cskill-name>\n\nScope: \u003Ctier> (\u003Cone-line knowledge\u002Fcontext summary>)\nLocation: \u003Cfull-path>\n\n### Structure\n\u003Ctree output>\n\n### SKILL.md Preview\n\u003Cfirst 20 lines>\n\nStatus: All validation checks passed.\n```\n\n---\n\n## Validate Mode\n\n### Input\n\nExpected args: path to a skill directory, OR empty \u002F `.` to scan `.agents\u002Fskills\u002F` for all skill directories (any directory containing `SKILL.md`).\n\n### Step 1: Structural Validation\n\n- [ ] Skill directory exists\n- [ ] `SKILL.md` file exists inside\n\n### Step 2: Frontmatter Validation\n\nParse the YAML frontmatter block (between `---` delimiters) and check:\n\n**Required:**\n- [ ] `name` exists and is 1–64 characters\n- [ ] `name` uses only lowercase alphanumeric (`a-z`, `0-9`) and hyphens (`-`)\n- [ ] `name` does not start or end with a hyphen\n- [ ] `name` does not contain consecutive hyphens (`--`)\n- [ ] `name` exactly matches the parent directory name\n- [ ] `description` exists, is non-empty, and is 1–1024 characters\n- [ ] `tier` exists and is one of: `company`, `enterprise`, `org`, `team`, `project`, `application`\n- [ ] `tier` matches the directory-name prefix per the scope table (`company-` → `company`, `enterprise-` → `enterprise`, `org-` → `org`, `team-` → `team`, `project-` → `project`, `app-` → `application`)\n\n**Optional (if present):**\n- [ ] `license` — short string\n- [ ] `compatibility` — max 500 characters\n- [ ] `metadata` — string-to-string key-value map\n- [ ] `allowed-tools` — space-delimited string\n\n### Step 3: Body Content Validation\n\n- [ ] Markdown body exists after the frontmatter\n- [ ] Body is under 500 lines (warn if exceeded)\n- [ ] File references use relative paths (no absolute paths like `\u002Ffoo\u002Fbar`)\n- [ ] Body content is consistent with the declared `tier` (warn if a `tier: team` skill encodes obvious company-wide policy, or vice versa)\n\n### Step 4: Optional Directory Checks\n\nIf present, verify non-empty:\n\n- [ ] `scripts\u002F` — executable or recognized script extensions\n- [ ] `references\u002F` — `.md` or documentation files\n- [ ] `assets\u002F` — resource files\n\n### Output\n\n```\n## Validation: \u003Cskill-name>\n\nScope: \u003Ctier>\nStatus: PASS | FAIL | WARN\n\n### Results\n- [x] Check that passed\n- [ ] Check that failed — reason\n\n### Summary\nX\u002FY checks passed. Z warnings.\n```\n\nFor multiple skills, append a summary table:\n\n```\n| Skill | Scope | Status | Passed | Warnings | Errors |\n|-------|-------|--------|--------|----------|--------|\n```\n\n## Reference\n\nFull spec: `SKILL_SPEC.md` at the repo root.\nSource commands: `.agents\u002Fcommands\u002Fagent-skill-create.md`, `.agents\u002Fcommands\u002Fagent-skill-validate.md`.\n",{"name":5,"tier":28,"description":7},"main","b78f8878258c912b66be9d4b56b316515e44c728",".claude\u002Fskills\u002Forg-agent-skill-creator","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":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add carlosmarte\u002Fai-agent-artifacts --skill org-agent-skill-creator",{"tool":62,"command":63},"bunx","bunx skills add carlosmarte\u002Fai-agent-artifacts --skill org-agent-skill-creator",{"tool":65,"command":66},"pnpm","pnpm dlx skills add carlosmarte\u002Fai-agent-artifacts --skill org-agent-skill-creator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcarlosmarte\u002Fai-agent-artifacts\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Forg-agent-skill-creator\u002FSKILL.md",true,[],[71,98,123,161,184,211],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":44},"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",[],[78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97],"handoff","validation","validation handoff","testing","architecture","edge","actions","refactor","execution","system","implementation","checklist","feature implementation","feature","end","case","defensive","hook","at","pending",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":44},"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",[],[33,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,35,122],"project ployglot project scafford","documentation","packages","run","ci","api","open","makefile","Bash","read","orchestrator","only","organization","shared","layout","dry","false","\u003Cslug>",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":143,"publishedAt":44},"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",[129,132,135,138],{"categoryNo":130,"categoryName":131,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":133,"categoryName":134,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":136,"categoryName":137,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":139,"categoryName":140,"taxonomyType":141,"taxonomyTypeDesc":142},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[144,145,146,147,148,149,113,114,150,151,152,153,154,155,156,157,158,121,159,160],"playwright","ui","playwright ui locator","frontend","cleanup","Tailwind","write","edit","fix","snapshot","auto","never","issue","files","rename","element","request",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":168,"publishedAt":44},"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",[167],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[169,170,28,171,172,173,43,174,175,176,177,178,30,155,156,179,180,181,182,183],"learn","context","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":193,"publishedAt":44},"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",[190],{"categoryNo":191,"categoryName":192,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理",[194,195,196,197,198,199,200,169,201,202,203,204,205,206,30,207,121,208,209,210],"PDF","recap","session","next","app","app workshop session pdf recap next","training","pull","produce","learning","slides","page","tutorial","deck","material","traceability","next steps",{"skillNo":212,"name":213,"nameZh":6,"description":214,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":215,"categories":216,"keywords":218,"publishedAt":44},"01M6NQ5NFNK613NR7FM8HPAJ74","app-workshop-recaps-consolidate","Consolidate multiple workshop-session recap Markdown files (typically produced by the workshop-session-pdf-recap-next skill) into a single unified report. Merges and deduplicates learnings across sessions and emits six sections — Consolidated Recap, Follow-ups, Action Items, Next Steps, Possible Enhancements, and Industry \u002F External Viewpoint. The last section supplements the attendees' material with current external perspective via web research. Use when the user has a set of per-session recap files and wants one portfolio-level summary with an outside-in lens (\"consolidate these recaps\", \"merge my workshop notes\", \"cross-session summary\", \"roll up action items\").","https:\u002F\u002Fgithub.com\u002Fcarlosmarte\u002Fai-agent-artifacts\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fapp-workshop-recaps-consolidate\u002FSKILL.md",[217],{"categoryNo":191,"categoryName":192,"taxonomyType":21,"taxonomyTypeDesc":22},[219,198,220,194,221,222,113,223,195,224,225,157,226,197,227,121,228,210,229,230],"consolidate","app workshop recaps consolidate","notes","SET","markdown","portfolio","up","learnings","across","lens","follow-ups","websearch"]