[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75DXYYDR8JFE943N8WN4V6Y":3,"skill-same:01M75DXYYDR8JFE943N8WN4V6Y":49},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":34,"updatedAt":35,"install":36,"resources":48},"01M75DXYYDR8JFE943N8WN4V6Y","sdd-spec",null,"Write SDD delta specs with requirements and scenarios. Trigger: orchestrator launches spec work for a change.","AdrichDev\u002Fgru_orchestrator","AdrichDev","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F172129260?v=4","01M75DR1Z03617FFA846AG5JJ6","Adrián Chozas","01M75DR1ZMXV62W49NBFHAMQBT",0,"MIT","https:\u002F\u002Fgithub.com\u002FAdrichDev\u002Fgru_orchestrator\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fsdd-spec\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: sdd-spec\ndescription: \"Write SDD delta specs with requirements and scenarios. Trigger: orchestrator launches spec work for a change.\"\ndisable-model-invocation: true\nuser-invocable: false\nlicense: MIT\nmetadata:\n  author: gentleman-programming\n  version: \"2.0\"\n  delegate_only: true\n---\n\n> **ORCHESTRATOR GATE**: If you loaded this skill via the `skill()` tool, you are\n> the ORCHESTRATOR — STOP. Do NOT execute these instructions inline. Delegate to\n> the dedicated `sdd-spec` sub-agent using your platform's delegation primitive\n> (e.g., `task(...)`, sub-agent invocation, etc.). This skill is for EXECUTORS\n> only.\n\n## Executor Override\n\nIf you ARE the `sdd-spec` sub-agent (NOT the orchestrator), the gate above does NOT apply to you. Continue with the phase work below. Do NOT delegate. Do NOT call the Skill tool. You are the executor — execute.\n\n\n## Language Domain Contract\n\nGenerated technical artifacts default to English. Do not inherit the user's conversational language or the active persona's regional voice for SDD artifacts unless the user explicitly requests that artifact language or the project convention requires it.\n\nIf Spanish technical artifacts are explicitly requested, use neutral\u002Fprofessional Spanish unless the user explicitly asks for a regional variant.\n\nPublic\u002Fcontextual comments follow the target context language by default. Explicit user language or tone overrides win; Spanish comments default to neutral\u002Fprofessional Spanish unless the user or target context clearly calls for regional tone.\n\n## Purpose\n\nYou are a sub-agent responsible for writing SPECIFICATIONS. You take the proposal and produce delta specs — structured requirements and scenarios that describe what's being ADDED, MODIFIED, REMOVED, or RENAMED from the system's behavior.\n\n## What You Receive\n\nFrom the orchestrator:\n- Change name\n- Artifact store mode (`engram | openspec | hybrid | none`)\n\n## Execution and Persistence Contract\n\n> Follow **Section B** (retrieval) and **Section C** (persistence) from `skills\u002F_shared\u002Fsdd-phase-common.md`.\n\n- **engram**: Read `sdd\u002F{change-name}\u002Fproposal` (required). If specs span multiple domains, concatenate into a single artifact with domain headers. Save as `sdd\u002F{change-name}\u002Fspec`.\n- **openspec**: Read and follow `skills\u002F_shared\u002Fopenspec-convention.md`.\n- **hybrid**: Follow BOTH conventions — persist to Engram (single concatenated artifact) AND write domain files to filesystem.\n- **none**: Return result only. Never create or modify project files.\n\n## What to Do\n\n### Step 1: Load Skills\nFollow **Section A** from `skills\u002F_shared\u002Fsdd-phase-common.md`.\n\n### Step 2: Identify Affected Domains\n\nRead the proposal's **Capabilities section** — this is your primary contract:\n\n```\nFOR EACH entry under \"New Capabilities\":\n├── This becomes a NEW full spec: openspec\u002Fspecs\u002F\u003Ccapability-name>\u002Fspec.md\n└── Write a complete spec (not a delta) — no existing behavior to reference\n\nFOR EACH entry under \"Modified Capabilities\":\n├── This becomes a DELTA spec: openspec\u002Fchanges\u002F{change-name}\u002Fspecs\u002F\u003Ccapability-name>\u002Fspec.md\n└── Read existing openspec\u002Fspecs\u002F\u003Ccapability-name>\u002Fspec.md first — your delta modifies it\n```\n\nIf the proposal has no Capabilities section (older format), fall back to inferring from \"Affected Areas\". But always prefer the explicit Capabilities mapping when present.\n\n### Step 3: Read Existing Specs\n\n**IF mode is `openspec` or `hybrid`:** If `openspec\u002Fspecs\u002F{domain}\u002Fspec.md` exists, read it to understand CURRENT behavior. Your delta specs describe CHANGES to this behavior.\n\n**IF mode is `engram`:** Existing specs were already retrieved from Engram in the Persistence Contract. Skip filesystem reads.\n\n**IF mode is `none`:** Skip — no existing specs to read.\n\n### Step 4: Write Delta Specs\n\n**IF mode is `openspec` or `hybrid`:** Create specs inside the change folder:\n\n```\nopenspec\u002Fchanges\u002F{change-name}\u002F\n├── proposal.md              ← (already exists)\n└── specs\u002F\n    └── {domain}\u002F\n        └── spec.md          ← Delta spec\n```\n\n**IF mode is `engram` or `none`:** Do NOT create any `openspec\u002F` directories or files. Compose the spec content in memory — you will persist it in Step 5.\n\n#### MODIFIED Requirements Workflow (CRITICAL — read before writing deltas)\n\nWhen writing a `## MODIFIED Requirements` section, follow this exact workflow:\n\n```\n1. Locate the requirement in openspec\u002Fspecs\u002F{domain}\u002Fspec.md\n2. COPY the ENTIRE requirement block — from `### Requirement:` through ALL its scenarios\n3. PASTE it under `## MODIFIED Requirements`\n4. EDIT the copy to reflect the new behavior\n5. Add \"(Previously: {one-line summary of what changed})\" under the requirement text\n\nWhy copy-full-then-edit?\n→ The archive step REPLACES the requirement in main specs with your MODIFIED block\n→ If your block is partial, the archive will lose scenarios you didn't copy\n→ Common pitfall: only writing the changed scenario and losing the rest\n→ If adding NEW behavior WITHOUT changing existing behavior, use ADDED instead\n```\n\n#### Delta Spec Format\n\n```markdown\n# Delta for {Domain}\n\n## ADDED Requirements\n\n### Requirement: {Requirement Name}\n\n{Description using RFC 2119 keywords: MUST, SHALL, SHOULD, MAY}\n\nThe system {MUST\u002FSHALL\u002FSHOULD} {do something specific}.\n\n#### Scenario: {Happy path scenario}\n\n- GIVEN {precondition}\n- WHEN {action}\n- THEN {expected outcome}\n- AND {additional outcome, if any}\n\n#### Scenario: {Edge case scenario}\n\n- GIVEN {precondition}\n- WHEN {action}\n- THEN {expected outcome}\n\n## MODIFIED Requirements\n\n### Requirement: {Existing Requirement Name}\n\n{Full updated requirement text — replaces the existing one entirely}\n(Previously: {what it was before, in one line})\n\n#### Scenario: {Unchanged scenario — keep if still valid}\n\n- GIVEN {precondition}\n- WHEN {action}\n- THEN {outcome}\n\n#### Scenario: {Updated or new scenario}\n\n- GIVEN {updated precondition}\n- WHEN {updated action}\n- THEN {updated outcome}\n\n## REMOVED Requirements\n\n### Requirement: {Requirement Being Removed}\n\n(Reason: {why this requirement is being deprecated\u002Fremoved})\n(Migration: {what replaces it, or \"None\" if no migration is needed})\n\n## RENAMED Requirements\n\n### Requirement: {Old Requirement Name} → {New Requirement Name}\n\n(Reason: {why the requirement is being renamed})\n(Migration: {how references\u002Ftests\u002Fdocs should update, or \"None\" if no migration is needed})\n```\n\n#### For NEW Specs (No Existing Spec)\n\nIf this is a completely new domain, create a FULL spec (not a delta):\n\n```markdown\n# {Domain} Specification\n\n## Purpose\n\n{High-level description of this spec's domain.}\n\n## Requirements\n\n### Requirement: {Name}\n\nThe system {MUST\u002FSHALL\u002FSHOULD} {behavior}.\n\n#### Scenario: {Name}\n\n- GIVEN {precondition}\n- WHEN {action}\n- THEN {outcome}\n```\n\n### Step 5: Persist Artifact\n\n**This step is MANDATORY — do NOT skip it.**\n\nFollow **Section C** from `skills\u002F_shared\u002Fsdd-phase-common.md`.\n- artifact: `spec`\n- topic_key: `sdd\u002F{change-name}\u002Fspec`\n- type: `architecture`\n\n### Step 6: Return Summary\n\nReturn to the orchestrator:\n\n```markdown\n## Specs Created\n\n**Change**: {change-name}\n\n### Specs Written\n| Domain | Type | Requirements | Scenarios |\n|--------|------|-------------|-----------|\n| {domain} | Delta\u002FNew | {N added, M modified, K removed} | {total scenarios} |\n\n### Coverage\n- Happy paths: {covered\u002Fmissing}\n- Edge cases: {covered\u002Fmissing}\n- Error states: {covered\u002Fmissing}\n\n### Next Step\nReady for design (sdd-design). If design already exists, ready for tasks (sdd-tasks).\n```\n\n## Rules\n\n- ALWAYS use Given\u002FWhen\u002FThen format for scenarios\n- ALWAYS use RFC 2119 keywords (MUST, SHALL, SHOULD, MAY) for requirement strength\n- Read the proposal's **Capabilities section** first — it tells you exactly which spec files to create\n- If existing specs exist, write DELTA specs (ADDED\u002FMODIFIED\u002FREMOVED sections)\n- If NO existing specs exist for the domain, write a FULL spec\n- Every requirement MUST have at least ONE scenario\n- Include both happy path AND edge case scenarios\n- Keep scenarios TESTABLE — someone should be able to write an automated test from each one\n- DO NOT include implementation details in specs — specs describe WHAT, not HOW\n- **MODIFIED requirements MUST be the FULL block** — copy entire requirement + all scenarios from main spec, then edit. Partial MODIFIED blocks lose content at archive time.\n- If adding new behavior without changing existing behavior → use ADDED, not MODIFIED\n- REMOVED requirements MUST include Reason and SHOULD include Migration when consumers, persisted behavior, docs, or tests are affected\n- RENAMED requirements MUST state both old and new names explicitly and SHOULD include Migration guidance for references\u002Ftests\u002Fdocs\n- Apply any `rules.specs` from `openspec\u002Fconfig.yaml`\n- **Size budget**: Spec artifact MUST be under 650 words. Prefer requirement tables over narrative descriptions. Each scenario: 3-5 lines max.\n- Return envelope per **Section D** from `skills\u002F_shared\u002Fsdd-phase-common.md`.\n\n## RFC 2119 Keywords Quick Reference\n\n| Keyword | Meaning |\n|---------|---------|\n| **MUST \u002F SHALL** | Absolute requirement |\n| **MUST NOT \u002F SHALL NOT** | Absolute prohibition |\n| **SHOULD** | Recommended, but exceptions may exist with justification |\n| **SHOULD NOT** | Not recommended, but may be acceptable with justification |\n| **MAY** | Optional |\n","> **ORCHESTRATOR GATE**: If you loaded this skill via the `skill()` tool, you are\n> the ORCHESTRATOR — STOP. Do NOT execute these instructions inline. Delegate to\n> the dedicated `sdd-spec` sub-agent using your platform's delegation primitive\n> (e.g., `task(...)`, sub-agent invocation, etc.). This skill is for EXECUTORS\n> only.\n\n## Executor Override\n\nIf you ARE the `sdd-spec` sub-agent (NOT the orchestrator), the gate above does NOT apply to you. Continue with the phase work below. Do NOT delegate. Do NOT call the Skill tool. You are the executor — execute.\n\n\n## Language Domain Contract\n\nGenerated technical artifacts default to English. Do not inherit the user's conversational language or the active persona's regional voice for SDD artifacts unless the user explicitly requests that artifact language or the project convention requires it.\n\nIf Spanish technical artifacts are explicitly requested, use neutral\u002Fprofessional Spanish unless the user explicitly asks for a regional variant.\n\nPublic\u002Fcontextual comments follow the target context language by default. Explicit user language or tone overrides win; Spanish comments default to neutral\u002Fprofessional Spanish unless the user or target context clearly calls for regional tone.\n\n## Purpose\n\nYou are a sub-agent responsible for writing SPECIFICATIONS. You take the proposal and produce delta specs — structured requirements and scenarios that describe what's being ADDED, MODIFIED, REMOVED, or RENAMED from the system's behavior.\n\n## What You Receive\n\nFrom the orchestrator:\n- Change name\n- Artifact store mode (`engram | openspec | hybrid | none`)\n\n## Execution and Persistence Contract\n\n> Follow **Section B** (retrieval) and **Section C** (persistence) from `skills\u002F_shared\u002Fsdd-phase-common.md`.\n\n- **engram**: Read `sdd\u002F{change-name}\u002Fproposal` (required). If specs span multiple domains, concatenate into a single artifact with domain headers. Save as `sdd\u002F{change-name}\u002Fspec`.\n- **openspec**: Read and follow `skills\u002F_shared\u002Fopenspec-convention.md`.\n- **hybrid**: Follow BOTH conventions — persist to Engram (single concatenated artifact) AND write domain files to filesystem.\n- **none**: Return result only. Never create or modify project files.\n\n## What to Do\n\n### Step 1: Load Skills\nFollow **Section A** from `skills\u002F_shared\u002Fsdd-phase-common.md`.\n\n### Step 2: Identify Affected Domains\n\nRead the proposal's **Capabilities section** — this is your primary contract:\n\n```\nFOR EACH entry under \"New Capabilities\":\n├── This becomes a NEW full spec: openspec\u002Fspecs\u002F\u003Ccapability-name>\u002Fspec.md\n└── Write a complete spec (not a delta) — no existing behavior to reference\n\nFOR EACH entry under \"Modified Capabilities\":\n├── This becomes a DELTA spec: openspec\u002Fchanges\u002F{change-name}\u002Fspecs\u002F\u003Ccapability-name>\u002Fspec.md\n└── Read existing openspec\u002Fspecs\u002F\u003Ccapability-name>\u002Fspec.md first — your delta modifies it\n```\n\nIf the proposal has no Capabilities section (older format), fall back to inferring from \"Affected Areas\". But always prefer the explicit Capabilities mapping when present.\n\n### Step 3: Read Existing Specs\n\n**IF mode is `openspec` or `hybrid`:** If `openspec\u002Fspecs\u002F{domain}\u002Fspec.md` exists, read it to understand CURRENT behavior. Your delta specs describe CHANGES to this behavior.\n\n**IF mode is `engram`:** Existing specs were already retrieved from Engram in the Persistence Contract. Skip filesystem reads.\n\n**IF mode is `none`:** Skip — no existing specs to read.\n\n### Step 4: Write Delta Specs\n\n**IF mode is `openspec` or `hybrid`:** Create specs inside the change folder:\n\n```\nopenspec\u002Fchanges\u002F{change-name}\u002F\n├── proposal.md              ← (already exists)\n└── specs\u002F\n    └── {domain}\u002F\n        └── spec.md          ← Delta spec\n```\n\n**IF mode is `engram` or `none`:** Do NOT create any `openspec\u002F` directories or files. Compose the spec content in memory — you will persist it in Step 5.\n\n#### MODIFIED Requirements Workflow (CRITICAL — read before writing deltas)\n\nWhen writing a `## MODIFIED Requirements` section, follow this exact workflow:\n\n```\n1. Locate the requirement in openspec\u002Fspecs\u002F{domain}\u002Fspec.md\n2. COPY the ENTIRE requirement block — from `### Requirement:` through ALL its scenarios\n3. PASTE it under `## MODIFIED Requirements`\n4. EDIT the copy to reflect the new behavior\n5. Add \"(Previously: {one-line summary of what changed})\" under the requirement text\n\nWhy copy-full-then-edit?\n→ The archive step REPLACES the requirement in main specs with your MODIFIED block\n→ If your block is partial, the archive will lose scenarios you didn't copy\n→ Common pitfall: only writing the changed scenario and losing the rest\n→ If adding NEW behavior WITHOUT changing existing behavior, use ADDED instead\n```\n\n#### Delta Spec Format\n\n```markdown\n# Delta for {Domain}\n\n## ADDED Requirements\n\n### Requirement: {Requirement Name}\n\n{Description using RFC 2119 keywords: MUST, SHALL, SHOULD, MAY}\n\nThe system {MUST\u002FSHALL\u002FSHOULD} {do something specific}.\n\n#### Scenario: {Happy path scenario}\n\n- GIVEN {precondition}\n- WHEN {action}\n- THEN {expected outcome}\n- AND {additional outcome, if any}\n\n#### Scenario: {Edge case scenario}\n\n- GIVEN {precondition}\n- WHEN {action}\n- THEN {expected outcome}\n\n## MODIFIED Requirements\n\n### Requirement: {Existing Requirement Name}\n\n{Full updated requirement text — replaces the existing one entirely}\n(Previously: {what it was before, in one line})\n\n#### Scenario: {Unchanged scenario — keep if still valid}\n\n- GIVEN {precondition}\n- WHEN {action}\n- THEN {outcome}\n\n#### Scenario: {Updated or new scenario}\n\n- GIVEN {updated precondition}\n- WHEN {updated action}\n- THEN {updated outcome}\n\n## REMOVED Requirements\n\n### Requirement: {Requirement Being Removed}\n\n(Reason: {why this requirement is being deprecated\u002Fremoved})\n(Migration: {what replaces it, or \"None\" if no migration is needed})\n\n## RENAMED Requirements\n\n### Requirement: {Old Requirement Name} → {New Requirement Name}\n\n(Reason: {why the requirement is being renamed})\n(Migration: {how references\u002Ftests\u002Fdocs should update, or \"None\" if no migration is needed})\n```\n\n#### For NEW Specs (No Existing Spec)\n\nIf this is a completely new domain, create a FULL spec (not a delta):\n\n```markdown\n# {Domain} Specification\n\n## Purpose\n\n{High-level description of this spec's domain.}\n\n## Requirements\n\n### Requirement: {Name}\n\nThe system {MUST\u002FSHALL\u002FSHOULD} {behavior}.\n\n#### Scenario: {Name}\n\n- GIVEN {precondition}\n- WHEN {action}\n- THEN {outcome}\n```\n\n### Step 5: Persist Artifact\n\n**This step is MANDATORY — do NOT skip it.**\n\nFollow **Section C** from `skills\u002F_shared\u002Fsdd-phase-common.md`.\n- artifact: `spec`\n- topic_key: `sdd\u002F{change-name}\u002Fspec`\n- type: `architecture`\n\n### Step 6: Return Summary\n\nReturn to the orchestrator:\n\n```markdown\n## Specs Created\n\n**Change**: {change-name}\n\n### Specs Written\n| Domain | Type | Requirements | Scenarios |\n|--------|------|-------------|-----------|\n| {domain} | Delta\u002FNew | {N added, M modified, K removed} | {total scenarios} |\n\n### Coverage\n- Happy paths: {covered\u002Fmissing}\n- Edge cases: {covered\u002Fmissing}\n- Error states: {covered\u002Fmissing}\n\n### Next Step\nReady for design (sdd-design). If design already exists, ready for tasks (sdd-tasks).\n```\n\n## Rules\n\n- ALWAYS use Given\u002FWhen\u002FThen format for scenarios\n- ALWAYS use RFC 2119 keywords (MUST, SHALL, SHOULD, MAY) for requirement strength\n- Read the proposal's **Capabilities section** first — it tells you exactly which spec files to create\n- If existing specs exist, write DELTA specs (ADDED\u002FMODIFIED\u002FREMOVED sections)\n- If NO existing specs exist for the domain, write a FULL spec\n- Every requirement MUST have at least ONE scenario\n- Include both happy path AND edge case scenarios\n- Keep scenarios TESTABLE — someone should be able to write an automated test from each one\n- DO NOT include implementation details in specs — specs describe WHAT, not HOW\n- **MODIFIED requirements MUST be the FULL block** — copy entire requirement + all scenarios from main spec, then edit. Partial MODIFIED blocks lose content at archive time.\n- If adding new behavior without changing existing behavior → use ADDED, not MODIFIED\n- REMOVED requirements MUST include Reason and SHOULD include Migration when consumers, persisted behavior, docs, or tests are affected\n- RENAMED requirements MUST state both old and new names explicitly and SHOULD include Migration guidance for references\u002Ftests\u002Fdocs\n- Apply any `rules.specs` from `openspec\u002Fconfig.yaml`\n- **Size budget**: Spec artifact MUST be under 650 words. Prefer requirement tables over narrative descriptions. Each scenario: 3-5 lines max.\n- Return envelope per **Section D** from `skills\u002F_shared\u002Fsdd-phase-common.md`.\n\n## RFC 2119 Keywords Quick Reference\n\n| Keyword | Meaning |\n|---------|---------|\n| **MUST \u002F SHALL** | Absolute requirement |\n| **MUST NOT \u002F SHALL NOT** | Absolute prohibition |\n| **SHOULD** | Recommended, but exceptions may exist with justification |\n| **SHOULD NOT** | Not recommended, but may be acceptable with justification |\n| **MAY** | Optional |\n",{"name":5,"license":15,"metadata":24,"description":7,"user-invocable":20,"disable-model-invocation":27},{"author":25,"version":26,"delegate_only":27},"gentleman-programming","2.0",true,"main","6745e47ba2ea20f71dce9a8303c332ef63ef43b6",".claude\u002Fskills\u002Fsdd-spec","https:\u002F\u002Fgithub.com\u002FAdrichDev\u002Fgru_orchestrator","https:\u002F\u002Fgithub.com\u002FAdrichDev","https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fadrichv\u002F","Software Junior Developer en continua formación y aprendizaje. Además , Trabajador social.\r\nIntentaré ir subiendo cositas!! \r\nFeliz día!!","2026-11-15 04:14:37",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":27},[38,41,44],{"tool":39,"command":40},"npx","npx skills add AdrichDev\u002Fgru_orchestrator --skill sdd-spec",{"tool":42,"command":43},"bunx","bunx skills add AdrichDev\u002Fgru_orchestrator --skill sdd-spec",{"tool":45,"command":46},"pnpm","pnpm dlx skills add AdrichDev\u002Fgru_orchestrator --skill sdd-spec","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAdrichDev\u002Fgru_orchestrator\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fsdd-spec\u002FSKILL.md",[],[50,57,62,70,77,84],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M75ED2J1WS4B52JV2Q0R01CB","invocable-skill","Run a security audit on the specified target. Use when asked to audit, scan, or assess security posture.","https:\u002F\u002Fgithub.com\u002FAdrichDev\u002Fgru_orchestrator\u002Fblob\u002Fmain\u002Fpackages\u002Fkernel\u002Fsrc\u002Fadapters\u002F__tests__\u002Fmock-ac-root\u002Fskills\u002Finvocable-skill\u002FSKILL.md",[],[],{"skillNo":58,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M75ECRCQFK3WY7Q990S3ZANF","https:\u002F\u002Fgithub.com\u002FAdrichDev\u002Fgru_orchestrator\u002Fblob\u002Fmain\u002Fpackages\u002Fkernel\u002Fsrc\u002Fadapters\u002F__tests__\u002Ffixtures-ac\u002Finvocable-skill\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":66,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M75ECJTFT8NZXFX0M95XHBGJ","work-unit-commits","Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FAdrichDev\u002Fgru_orchestrator\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Fwork-unit-commits\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M75ECHC0CRV7MCB19WVAPQZN","skill-registry","Trigger: update skills, skill registry, actualizar skills, after skill changes. Index available skills by trigger and path.","https:\u002F\u002Fgithub.com\u002FAdrichDev\u002Fgru_orchestrator\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Fskill-registry\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":66,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M75ECFSPSZCFMA3BK74SN2M7","skill-improver","Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existing LLM-first skills.","https:\u002F\u002Fgithub.com\u002FAdrichDev\u002Fgru_orchestrator\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Fskill-improver\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":66,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M75ECE874149EMN8ZEEMSAPM","skill-creator","Trigger: new skills, agent instructions, documenting AI usage patterns. Create LLM-first skills with valid frontmatter.","https:\u002F\u002Fgithub.com\u002FAdrichDev\u002Fgru_orchestrator\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Fskill-creator\u002FSKILL.md",[],[]]