[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79YGGD1C7CDFRMEVKA5RH4B":3,"skill-same:01M79YGGD1C7CDFRMEVKA5RH4B":84},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M79YGGD1C7CDFRMEVKA5RH4B","document-implement",null,"Execute the next pending step from docs\u002Fdocumentation-plan\u002Fplan.md and write domain docs for RAG. Use when documenting the repo or invoking \u002Fdocument-implement.","tibursocampos\u002Fagent-dev-toolkit","tibursocampos","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F37385246?v=4","01M79YF4CE4TH665XJJ7XSHXXK","Raphael Campos","01M79YF4D4KDQK01HZ6835E4A0",6,"MIT","https:\u002F\u002Fgithub.com\u002Ftibursocampos\u002Fagent-dev-toolkit\u002Fblob\u002Fmaster\u002Fcore\u002Fskills\u002Fdocument-implement\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: document-implement\ndescription: Execute the next pending step from docs\u002Fdocumentation-plan\u002Fplan.md and write domain docs for RAG. Use when documenting the repo or invoking \u002Fdocument-implement.\n---\n\n## STOP - Read before ANY tool call\n\nRead `_shared\u002Fskill-boilerplate.md` first. It holds the guardrails read, the session gate rule, the user `sim` rule, the one-step rule, the gate check, and the user chat language rule. The steps below are skill-specific only.\n\n---\n\n# Skill: document-implement\n\n## Trigger\n**Negative signal:** applies as defined in `_shared\u002Fskill-boilerplate.md`; the skill-specific signals are listed below.\n\nInvoke when the user asks for: `\u002Fdocument-implement`, `document repository`, `\u002Fdocument-implement`, or `execute documentation plan`.\n\nRequires `docs\u002Fdocumentation-plan\u002Fplan.md` in the **target workspace**. If missing, hand off to `\u002Fdocument-plan` (do not invent steps).\n\n## Outcome\n\nOne **documentation plan step** completed in the target repo: new\u002Fupdated markdown under `docs\u002F`, plan progress advanced, next step identified for a future session.\n\n**Cadence:** prefer **new file = one step**; **updates to existing docs = one coalesced step**. Use spawn only for large greenfield or large refactor steps (`SPAWN.md`).\n\n## Lazy-load\n\n| When | Path |\n|------|------|\n| Caveman Mode (if active) | `{{TOOLKIT_ROOT}}\u002Fskills\u002F_shared\u002Fcaveman\u002FCAVEMAN.md` - **Full cap** |\n| Doc-plan stack detection \u002F plan template | `{{TOOLKIT_ROOT}}\u002Fskills\u002Fdocument-plan\u002Freferences\u002Fstack-detection.md`, `...\u002Fplan-template.md` |\n| This skill reference index (routing only) | `skills\u002Fdocument-implement\u002Freference.md` |\n| Process step detail (lazy) | `skills\u002Fdocument-implement\u002Freferences\u002F\u003Csection>.md` |\n| SDD vs RAG plan boundary | `{{TOOLKIT_ROOT}}\u002Fskills\u002F_shared\u002Fsdd-artifacts\u002FSTORAGE.md` |\n| Session gates (PLAN-scoped) | `{{TOOLKIT_ROOT}}\u002Fskills\u002F_shared\u002Fsdd-artifacts\u002FSESSION.md` |\n| Spawn vs in-parent (large new\u002Frefactor steps) | `{{TOOLKIT_ROOT}}\u002Fskills\u002F_shared\u002Fagents\u002FSPAWN.md` |\n| Language surfaces (chat vs spawn) | `{{TOOLKIT_ROOT}}\u002Fskills\u002F_shared\u002Fagents\u002FLANGUAGE.md` |\n\n**Never by default:** do not preload all `references\u002F*.md`, full document-plan packs, or unrelated SDD contracts. Load **one** `references\u002F\u003Csection>.md` per Process step (`SKILL-REFERENCE-RETRIEVAL.md`).\n\n## Process\n\nRead `references\u002F\u003Csection>.md` for execution detail — **not** full `reference.md`.\n\n### Step -1b - Caveman Mode (Full cap)\n1. Read `{{SDD_ROOT}}\u002Fpreferences.json` (create `{ \"caveman_mode\": false, \"caveman_level\": \"full\" }` if missing).\n2. If `caveman_mode` is false: continue without compression.\n3. If true: load `{{TOOLKIT_ROOT}}\u002Fskills\u002F_shared\u002Fcaveman\u002FCAVEMAN.md`; apply **Full** participation cap + prefs `caveman_level` (Lite skills never escalate); show once: `[Caveman] Modo ativo (respostas compactas, level={effective}). Digite caveman off para desativar.`\n4. Honor `caveman on|off|status|lite|full|ultra` (and `stop caveman` \u002F `normal mode`) during the session.\n5. Auto-Clarity + never-compress gates\u002Fdrafts\u002Fpaths per `CAVEMAN.md`.\n\n### 0. Workspace, plan, and stack\n\n1. Confirm **target repository**.\n2. Resolve **doc plan path** = absolute `$Cwd\u002Fdocs\u002Fdocumentation-plan\u002Fplan.md` (or user-given alternate). If absent -> stop and suggest `\u002Fdocument-plan`.\n3. Load\u002Fcreate **develop session** keyed by that full plan path per `SESSION.md` (`plan-{plan-hash}.json`). Gates `step_confirmed` \u002F `tests_run` live **only** there - never use flat `{repo-hash}.json` for them.\n4. Read the plan. Read **Doc language** from plan header. If missing, ask the doc-language question (ids `pt-br` \u002F `en`) before writing `docs\u002F` (`references\u002Fdoc-language.md`).\n5. Re-detect stack briefly (Glob per `document-plan\u002Freferences\u002Fstack-detection.md`) if plan is stale.\n\n**Not Classic SDD \u002F Orchestrated Delivery:** only the documentation plan applies here - not `features\u002F**\u002FPLAN\u002F`. For feature delivery PRD\u002FPLAN, use `sdd-spec` \u002F `sdd-plan` \u002F `sdd-develop` and `STORAGE.md`. Prerequisite rules: `references\u002Fprerequisite.md`.\n\n### 1. Select step\n\nPick the first step with **Status:** Pending (or **Pendente**) whose dependencies are completed (`references\u002Fstep-selection.md`). If user names a step id, use that step after validating deps.\n\nSummarize objective and deliverables. If `step_confirmed` is false: ask in the **user chat language** to implement this doc step, with `confirm` and `cancel` choices (ids and render rule: `core\u002Fskills\u002F_shared\u002Fagents\u002FQUESTIONS.md`); set gate `true` only after a `confirm` answer. That gate has no written deadline: follow `core\u002Fpolicy\u002Fguardrails.md` § Open questions without a written deadline. Use the host interactive question when the host offers one; otherwise ask in text. Send no further message until the operator answers every pending question. Silence, timeout, end of turn, a lone emoji, or an ambiguous or unrelated reply is not approval; a clear affirmative reply in any language is. After the answer, resume this skill until the doc step finishes or this skill declares a blocker with the cause. The `confirm` answer stays required before writes.\n\n### 2. Execute step\n\nFollow the step's **Tasks** in the plan (`references\u002Fwriting-guidelines.md`):\n\n- Glob\u002FGrep\u002FRead source; document facts evidenced in code\u002Fconfig\n- Write paths listed in **Deliverables** (e.g. `docs\u002Fdomains\u002F\u003Cslug>.md`)\n- Use **doc language** from plan; keep file paths and type names in English\n- No secrets, tokens, or internal-only URLs in markdown\n\n**Spawn (Axis A — `SPAWN.md`):** for **Kind: new** large greenfield docs, or **Kind: refactor** \u002F large multi-file doc changes, when effective `subagents=native` and work is independent, prefer ≤2 specialist children (scoped **paths** + **receipt**; omit Agent `model`). Trivial or single-file **update** stays **in-parent**. If `subagents=none` or Agent unavailable → **fallback in-parent** (never hard-fail). Do not paste guideline packs into child prompts.\n\n### 3. Update plan\n\nBefore marking the step done: set `tests_run=true` on the scoped develop session after reporting what was written (doc verification - no app test suite required).\n\nEdit `docs\u002Fdocumentation-plan\u002Fplan.md` in place per `references\u002Fplan-update.md`:\n\n| Field | Value |\n|-------|--------|\n| Step status | Completed \u002F Concluido |\n| **Completed:** | `YYYY-MM-DD` |\n| Deliverables \u002F acceptance | `[x]` when met |\n| Progress | `N\u002FM` and bar |\n| **Next step** | following pending step |\n\nAfter complete: clear `step_confirmed` and `tests_run` to `false` on the scoped develop session (`SESSION.md` after-step rules).\n\n### 4. Context checkpoint\n\nCheckpoint durable workflow progress at the workflow-defined boundaries; context usage does not add a stop gate.\n\n### 5. Report\n\nFiles written, step completed, progress `N\u002FM`, suggested handoff. Manual validation: `references\u002Fvalidation.md`. Optional commit: `references\u002Foptional-commit.md`.\n\n## Must not\n\n- Run without `docs\u002Fdocumentation-plan\u002Fplan.md` (unless user gives an explicit alternate plan path)\n- Use flat `{repo-hash}.json` for `step_confirmed` \u002F `tests_run` when the doc plan path is known - always PLAN-scoped develop session\n- Assume MES or fixed stack versions\n- Write product `docs\u002F` before doc language is known\n- Complete multiple **Kind: new** plan steps in one session when context is high - prefer one new-doc step per session\n- Hard-fail when Agent\u002Fsubagents unavailable on a heavy doc step (fallback **in-parent** per `SPAWN.md`)\n- Require external wiki or work-item APIs\n\n## Handoff\n\n| Situation | Next |\n|-----------|------|\n| No plan | `\u002Fdocument-plan` |\n| Next doc step (new chat) | `\u002Fdocument-implement` |\n| All steps done | `\u002Fcode-review` (optional) or `\u002Fcommit` |\n| Feature code change | `\u002Fsdd-spec` -> `sdd-plan` -> `sdd-develop` |\n","## STOP - Read before ANY tool call\n\nRead `_shared\u002Fskill-boilerplate.md` first. It holds the guardrails read, the session gate rule, the user `sim` rule, the one-step rule, the gate check, and the user chat language rule. The steps below are skill-specific only.\n\n---\n\n# Skill: document-implement\n\n## Trigger\n**Negative signal:** applies as defined in `_shared\u002Fskill-boilerplate.md`; the skill-specific signals are listed below.\n\nInvoke when the user asks for: `\u002Fdocument-implement`, `document repository`, `\u002Fdocument-implement`, or `execute documentation plan`.\n\nRequires `docs\u002Fdocumentation-plan\u002Fplan.md` in the **target workspace**. If missing, hand off to `\u002Fdocument-plan` (do not invent steps).\n\n## Outcome\n\nOne **documentation plan step** completed in the target repo: new\u002Fupdated markdown under `docs\u002F`, plan progress advanced, next step identified for a future session.\n\n**Cadence:** prefer **new file = one step**; **updates to existing docs = one coalesced step**. Use spawn only for large greenfield or large refactor steps (`SPAWN.md`).\n\n## Lazy-load\n\n| When | Path |\n|------|------|\n| Caveman Mode (if active) | `{{TOOLKIT_ROOT}}\u002Fskills\u002F_shared\u002Fcaveman\u002FCAVEMAN.md` - **Full cap** |\n| Doc-plan stack detection \u002F plan template | `{{TOOLKIT_ROOT}}\u002Fskills\u002Fdocument-plan\u002Freferences\u002Fstack-detection.md`, `...\u002Fplan-template.md` |\n| This skill reference index (routing only) | `skills\u002Fdocument-implement\u002Freference.md` |\n| Process step detail (lazy) | `skills\u002Fdocument-implement\u002Freferences\u002F\u003Csection>.md` |\n| SDD vs RAG plan boundary | `{{TOOLKIT_ROOT}}\u002Fskills\u002F_shared\u002Fsdd-artifacts\u002FSTORAGE.md` |\n| Session gates (PLAN-scoped) | `{{TOOLKIT_ROOT}}\u002Fskills\u002F_shared\u002Fsdd-artifacts\u002FSESSION.md` |\n| Spawn vs in-parent (large new\u002Frefactor steps) | `{{TOOLKIT_ROOT}}\u002Fskills\u002F_shared\u002Fagents\u002FSPAWN.md` |\n| Language surfaces (chat vs spawn) | `{{TOOLKIT_ROOT}}\u002Fskills\u002F_shared\u002Fagents\u002FLANGUAGE.md` |\n\n**Never by default:** do not preload all `references\u002F*.md`, full document-plan packs, or unrelated SDD contracts. Load **one** `references\u002F\u003Csection>.md` per Process step (`SKILL-REFERENCE-RETRIEVAL.md`).\n\n## Process\n\nRead `references\u002F\u003Csection>.md` for execution detail — **not** full `reference.md`.\n\n### Step -1b - Caveman Mode (Full cap)\n1. Read `{{SDD_ROOT}}\u002Fpreferences.json` (create `{ \"caveman_mode\": false, \"caveman_level\": \"full\" }` if missing).\n2. If `caveman_mode` is false: continue without compression.\n3. If true: load `{{TOOLKIT_ROOT}}\u002Fskills\u002F_shared\u002Fcaveman\u002FCAVEMAN.md`; apply **Full** participation cap + prefs `caveman_level` (Lite skills never escalate); show once: `[Caveman] Modo ativo (respostas compactas, level={effective}). Digite caveman off para desativar.`\n4. Honor `caveman on|off|status|lite|full|ultra` (and `stop caveman` \u002F `normal mode`) during the session.\n5. Auto-Clarity + never-compress gates\u002Fdrafts\u002Fpaths per `CAVEMAN.md`.\n\n### 0. Workspace, plan, and stack\n\n1. Confirm **target repository**.\n2. Resolve **doc plan path** = absolute `$Cwd\u002Fdocs\u002Fdocumentation-plan\u002Fplan.md` (or user-given alternate). If absent -> stop and suggest `\u002Fdocument-plan`.\n3. Load\u002Fcreate **develop session** keyed by that full plan path per `SESSION.md` (`plan-{plan-hash}.json`). Gates `step_confirmed` \u002F `tests_run` live **only** there - never use flat `{repo-hash}.json` for them.\n4. Read the plan. Read **Doc language** from plan header. If missing, ask the doc-language question (ids `pt-br` \u002F `en`) before writing `docs\u002F` (`references\u002Fdoc-language.md`).\n5. Re-detect stack briefly (Glob per `document-plan\u002Freferences\u002Fstack-detection.md`) if plan is stale.\n\n**Not Classic SDD \u002F Orchestrated Delivery:** only the documentation plan applies here - not `features\u002F**\u002FPLAN\u002F`. For feature delivery PRD\u002FPLAN, use `sdd-spec` \u002F `sdd-plan` \u002F `sdd-develop` and `STORAGE.md`. Prerequisite rules: `references\u002Fprerequisite.md`.\n\n### 1. Select step\n\nPick the first step with **Status:** Pending (or **Pendente**) whose dependencies are completed (`references\u002Fstep-selection.md`). If user names a step id, use that step after validating deps.\n\nSummarize objective and deliverables. If `step_confirmed` is false: ask in the **user chat language** to implement this doc step, with `confirm` and `cancel` choices (ids and render rule: `core\u002Fskills\u002F_shared\u002Fagents\u002FQUESTIONS.md`); set gate `true` only after a `confirm` answer. That gate has no written deadline: follow `core\u002Fpolicy\u002Fguardrails.md` § Open questions without a written deadline. Use the host interactive question when the host offers one; otherwise ask in text. Send no further message until the operator answers every pending question. Silence, timeout, end of turn, a lone emoji, or an ambiguous or unrelated reply is not approval; a clear affirmative reply in any language is. After the answer, resume this skill until the doc step finishes or this skill declares a blocker with the cause. The `confirm` answer stays required before writes.\n\n### 2. Execute step\n\nFollow the step's **Tasks** in the plan (`references\u002Fwriting-guidelines.md`):\n\n- Glob\u002FGrep\u002FRead source; document facts evidenced in code\u002Fconfig\n- Write paths listed in **Deliverables** (e.g. `docs\u002Fdomains\u002F\u003Cslug>.md`)\n- Use **doc language** from plan; keep file paths and type names in English\n- No secrets, tokens, or internal-only URLs in markdown\n\n**Spawn (Axis A — `SPAWN.md`):** for **Kind: new** large greenfield docs, or **Kind: refactor** \u002F large multi-file doc changes, when effective `subagents=native` and work is independent, prefer ≤2 specialist children (scoped **paths** + **receipt**; omit Agent `model`). Trivial or single-file **update** stays **in-parent**. If `subagents=none` or Agent unavailable → **fallback in-parent** (never hard-fail). Do not paste guideline packs into child prompts.\n\n### 3. Update plan\n\nBefore marking the step done: set `tests_run=true` on the scoped develop session after reporting what was written (doc verification - no app test suite required).\n\nEdit `docs\u002Fdocumentation-plan\u002Fplan.md` in place per `references\u002Fplan-update.md`:\n\n| Field | Value |\n|-------|--------|\n| Step status | Completed \u002F Concluido |\n| **Completed:** | `YYYY-MM-DD` |\n| Deliverables \u002F acceptance | `[x]` when met |\n| Progress | `N\u002FM` and bar |\n| **Next step** | following pending step |\n\nAfter complete: clear `step_confirmed` and `tests_run` to `false` on the scoped develop session (`SESSION.md` after-step rules).\n\n### 4. Context checkpoint\n\nCheckpoint durable workflow progress at the workflow-defined boundaries; context usage does not add a stop gate.\n\n### 5. Report\n\nFiles written, step completed, progress `N\u002FM`, suggested handoff. Manual validation: `references\u002Fvalidation.md`. Optional commit: `references\u002Foptional-commit.md`.\n\n## Must not\n\n- Run without `docs\u002Fdocumentation-plan\u002Fplan.md` (unless user gives an explicit alternate plan path)\n- Use flat `{repo-hash}.json` for `step_confirmed` \u002F `tests_run` when the doc plan path is known - always PLAN-scoped develop session\n- Assume MES or fixed stack versions\n- Write product `docs\u002F` before doc language is known\n- Complete multiple **Kind: new** plan steps in one session when context is high - prefer one new-doc step per session\n- Hard-fail when Agent\u002Fsubagents unavailable on a heavy doc step (fallback **in-parent** per `SPAWN.md`)\n- Require external wiki or work-item APIs\n\n## Handoff\n\n| Situation | Next |\n|-----------|------|\n| No plan | `\u002Fdocument-plan` |\n| Next doc step (new chat) | `\u002Fdocument-implement` |\n| All steps done | `\u002Fcode-review` (optional) or `\u002Fcommit` |\n| Feature code change | `\u002Fsdd-spec` -> `sdd-plan` -> `sdd-develop` |\n",{"name":5,"description":7},"master","d199760b9c98388be72a799dafccb9e981aa6d5f","core\u002Fskills\u002Fdocument-implement",0,"https:\u002F\u002Fgithub.com\u002Ftibursocampos\u002Fagent-dev-toolkit","https:\u002F\u002Ftibursocampos.github.io\u002Fagent-dev-toolkit\u002F","https:\u002F\u002Fgithub.com\u002Ftibursocampos","2026-11-08 02:36:34",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add tibursocampos\u002Fagent-dev-toolkit --skill document-implement",{"tool":38,"command":39},"bunx","bunx skills add tibursocampos\u002Fagent-dev-toolkit --skill document-implement",{"tool":41,"command":42},"pnpm","pnpm dlx skills add tibursocampos\u002Fagent-dev-toolkit --skill document-implement","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftibursocampos\u002Fagent-dev-toolkit\u002Fblob\u002Fmaster\u002Fcore\u002Fskills\u002Fdocument-implement\u002FSKILL.md",true,[46,52,56,60,64,68,72,76,80],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"reference.md","REFERENCE","参考文档",800,"https:\u002F\u002Fgithub.com\u002Ftibursocampos\u002Fagent-dev-toolkit\u002Fblob\u002Fmaster\u002Fcore\u002Fskills\u002Fdocument-implement\u002Freference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fcontext-management.md",427,"https:\u002F\u002Fgithub.com\u002Ftibursocampos\u002Fagent-dev-toolkit\u002Fblob\u002Fmaster\u002Fcore\u002Fskills\u002Fdocument-implement\u002Freferences\u002Fcontext-management.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fdoc-language.md",429,"https:\u002F\u002Fgithub.com\u002Ftibursocampos\u002Fagent-dev-toolkit\u002Fblob\u002Fmaster\u002Fcore\u002Fskills\u002Fdocument-implement\u002Freferences\u002Fdoc-language.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Foptional-commit.md",168,"https:\u002F\u002Fgithub.com\u002Ftibursocampos\u002Fagent-dev-toolkit\u002Fblob\u002Fmaster\u002Fcore\u002Fskills\u002Fdocument-implement\u002Freferences\u002Foptional-commit.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fplan-update.md",701,"https:\u002F\u002Fgithub.com\u002Ftibursocampos\u002Fagent-dev-toolkit\u002Fblob\u002Fmaster\u002Fcore\u002Fskills\u002Fdocument-implement\u002Freferences\u002Fplan-update.md",{"path":69,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fprerequisite.md",568,"https:\u002F\u002Fgithub.com\u002Ftibursocampos\u002Fagent-dev-toolkit\u002Fblob\u002Fmaster\u002Fcore\u002Fskills\u002Fdocument-implement\u002Freferences\u002Fprerequisite.md",{"path":73,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fstep-selection.md",662,"https:\u002F\u002Fgithub.com\u002Ftibursocampos\u002Fagent-dev-toolkit\u002Fblob\u002Fmaster\u002Fcore\u002Fskills\u002Fdocument-implement\u002Freferences\u002Fstep-selection.md",{"path":77,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fvalidation.md",229,"https:\u002F\u002Fgithub.com\u002Ftibursocampos\u002Fagent-dev-toolkit\u002Fblob\u002Fmaster\u002Fcore\u002Fskills\u002Fdocument-implement\u002Freferences\u002Fvalidation.md",{"path":81,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fwriting-guidelines.md",593,"https:\u002F\u002Fgithub.com\u002Ftibursocampos\u002Fagent-dev-toolkit\u002Fblob\u002Fmaster\u002Fcore\u002Fskills\u002Fdocument-implement\u002Freferences\u002Fwriting-guidelines.md",[85,92,99,106,113,120],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M79YNFMWYYP2QKV43VKJ90K0","user-own-skill","Operator-owned skill that is not part of the toolkit.","https:\u002F\u002Fgithub.com\u002Ftibursocampos\u002Fagent-dev-toolkit\u002Fblob\u002Fmaster\u002Fscripts\u002Fvalidation\u002Ffixtures\u002Fseed-user-root\u002Fskills\u002Fuser-own-skill\u002FSKILL.md",[],[],{"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":19},"01M79YNCCEJ2J9MF2Q1WYXE265","vue-developer","Implement or fix small-to-medium Vue 3 features without full SDD (Composition API, Pinia, configured project test runner; Vitest is a fallback for new projects). Use for isolated Vue work or when invoking \u002Fvue-developer.","https:\u002F\u002Fgithub.com\u002Ftibursocampos\u002Fagent-dev-toolkit\u002Fblob\u002Fmaster\u002Fcore\u002Fskills\u002Fvue-developer\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M79YN85A2VGFD1P359F77YZ8","test-coverage","Run .NET Coverlet coverage, report Sonar-aligned metrics, and evaluate against a threshold (default 80%). Use for coverage reports or when invoking \u002Ftest-coverage.","https:\u002F\u002Fgithub.com\u002Ftibursocampos\u002Fagent-dev-toolkit\u002Fblob\u002Fmaster\u002Fcore\u002Fskills\u002Ftest-coverage\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M79YN42PG910XDKK6AKBJB1H","split-story-checklist","Break refined backlog steps into a dependency-aware task checklist (backend, frontend, tests). Prefer features\u002F... story folders. Use when breaking down tasks or invoking \u002Fsplit-story-checklist.","https:\u002F\u002Fgithub.com\u002Ftibursocampos\u002Fagent-dev-toolkit\u002Fblob\u002Fmaster\u002Fcore\u002Fskills\u002Fsplit-story-checklist\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":19},"01M79YMZKTTY1NSH39AYN6YSYZ","sdd-spec","Create a PRD for a new feature or change (agent PRD .md; language per LANGUAGE.md + preferences under features\u002F). Feeds sdd-plan. Use when creating a spec or invoking \u002Fsdd-spec.","https:\u002F\u002Fgithub.com\u002Ftibursocampos\u002Fagent-dev-toolkit\u002Fblob\u002Fmaster\u002Fcore\u002Fskills\u002Fsdd-spec\u002FSKILL.md",[],[],{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":19},"01M79YMV0YHHGCG527JEGY4RN0","sdd-plan","Create a baby-step PLAN from an existing PRD (agent PLAN .md; language per LANGUAGE.md + preferences). Feeds sdd-develop. Use when creating a plan or invoking \u002Fsdd-plan.","https:\u002F\u002Fgithub.com\u002Ftibursocampos\u002Fagent-dev-toolkit\u002Fblob\u002Fmaster\u002Fcore\u002Fskills\u002Fsdd-plan\u002FSKILL.md",[],[]]