[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ESBAH4GC9W3KYMP7APGF04":3,"skill-same:01M6ESBAH4GC9W3KYMP7APGF04":153},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":58,"commitSha":59,"skillDirectory":60,"forksCount":61,"repositoryHtmlUrl":62,"repositoryHomepageUrl":63,"ownerHtmlUrl":64,"ownerBlogUrl":6,"ownerDescription":65,"updatedAt":66,"install":67,"resources":80},"01M6ESBAH4GC9W3KYMP7APGF04","backend-ralph-plan",null,"Create a structured plan directory with Ralph Wiggum Loop integration for backend Django projects. Generates PLAN.md (task index), task files, and RALPH-PROMPT.md (the actual prompt for ralph-loop). Use for rigorous, iterative implementation requiring quality gates and verification.","ComeOnOliver\u002Fskillshub","ComeOnOliver","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F43215937?v=4","01M6E5JNFECJAAVFE0W7SMWWD2","Haoran Shu","01M6E5JNNDQS7AJZDYFQ8TPZCK",66,"MIT","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fdiversioteam\u002Fbackend-ralph-plan\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"backend ralph plan","plan","backend","ralph","read","gates","ralph-loop","task","files","use","edit","write","directory","prompt","django","projects","loop","Bash","verification","create","2026-11-10 10:12:30",false,"---\nname: backend-ralph-plan\ndescription: >\n  Create a structured plan directory with Ralph Wiggum Loop integration for\n  backend Django projects. Generates PLAN.md (task index), task files, and\n  RALPH-PROMPT.md (the actual prompt for ralph-loop). Use for rigorous,\n  iterative implementation requiring quality gates and verification.\nallowed-tools:\n  - Read\n  - Write\n  - Edit\n  - Glob\n  - Bash\n---\n\n# Backend RALPH Plan Skill\n\n## Purpose\n\nThis skill creates **two deliverables**:\n\n1. **PLAN.md** - Structured task index with quality tracking\n2. **RALPH-PROMPT.md** - The prompt fed to `\u002Fralph-wiggum:ralph-loop`\n\nThe key insight: Ralph works by feeding the **same prompt** repeatedly. Claude\nsees its previous work in files\u002Fgit and iterates. RALPH-PROMPT.md becomes that\nprompt, instructing Claude to work through tasks with strict quality gates.\n\n## When to Use\n\n- Backend Django features requiring rigorous quality control\n- Multi-task implementations needing iterative, autonomous execution\n- When you want continuous regression testing between tasks\n- Projects where you'll walk away and let Ralph complete the work\n\n## When NOT to Use\n\n- Quick prototypes or exploratory code\n- Frontend projects (create `frontend-ralph-plan` if needed)\n- Simple tasks that don't need iteration\n- Plans where human judgment is needed at each step\n\n## The Two-Step Process\n\n**Step 1: This skill creates the plan**\n```\ndocs\u002Fplans\u002F\u003Cslug>\u002F\n├── PLAN.md              # Task index with tracking\n├── RALPH-PROMPT.md      # Prompt for ralph-loop\n├── 001-\u003Ctask>.md        # Task files\n└── ...\n```\n\n**Step 2: Run the plan**\n```\n\u002Fplan-directory:run \u003Cslug>\n```\n\nThat's it. This command:\n1. Reads RALPH-PROMPT.md\n2. Extracts the completion promise\n3. Invokes `\u002Fralph-wiggum:ralph-loop` automatically\n\nOptional: `\u002Fplan-directory:run \u003Cslug> --max-iterations 50`\n\n## Required Inputs\n\n| Input | Required | Description |\n|-------|----------|-------------|\n| Plan title | Yes | Human-readable name |\n| Plan slug | Yes | Directory name, kebab-case |\n| Task list | Yes | Tasks with names and scopes |\n| Django app path | Yes | e.g., `optimo_surveys\u002F` |\n| Module path | Yes | e.g., `digest\u002F` |\n| Test filter | Yes | Pytest `-k` filter |\n\n### Tooling Configuration\n\n| Input | Default | Description |\n|-------|---------|-------------|\n| Lint command | `ruff check` | Prefix with `.bin\u002F` if needed |\n| Format command | `ruff format` | |\n| Type check | `ty` | Or `mypy`, `pyright` |\n| Test command | `pytest` | |\n| Test config | `` | e.g., `--dc=TestLocalApp` |\n| Django command | `django` | |\n| Coverage target | `90` | Minimum percentage |\n| Max iterations | `100` | Ralph loop limit |\n\n## Task Granularity Guidelines\n\n**Right-sized tasks for Ralph:**\n\n| Task Size | Checklist Items | Good For |\n|-----------|-----------------|----------|\n| Too small | 1-2 | Overhead exceeds value |\n| **Ideal** | **4-8** | **Clear scope, achievable in one iteration** |\n| Too large | 10+ | Gets stuck, split it |\n\n**Signs a task is too large:**\n- Requires multiple commits to feel \"done\"\n- Has more than 8 checklist items\n- Spans multiple unrelated concerns\n- Would take a human more than 2-4 hours\n\n**Split large tasks by:**\n- Separating model\u002Fservice\u002FAPI layers\n- Breaking by feature subset\n- Isolating integration points\n\n## Completion Promise Format\n\nThe promise must be **plan-specific**, not generic:\n\n```\nALL {{TASK_COUNT}} {{PLAN_SLUG_UPPER}} TASKS COMPLETE\n```\n\nExamples:\n- `ALL 4 USER-PREFERENCES TASKS COMPLETE`\n- `ALL 11 MANAGER-DIGEST TASKS COMPLETE`\n- `ALL 6 NOTIFICATION-SERVICE TASKS COMPLETE`\n\nThis prevents Claude from lying with a generic \"done\" when tasks remain.\n\n## RALPH-PROMPT.md: The Key File\n\nThe prompt is **iteration-aware**. It tells Claude to:\n\n1. **Orient first** - Check git log, read PLAN.md for current status\n2. **Don't repeat work** - Skip what's already committed\n3. **Verify rigorously** - Run all gates after each task\n4. **Commit progress** - Git commit after each task completion\n5. **Handle blockers** - Document, try alternatives, don't lie to exit\n\nSee `references\u002Fralph-prompt-template.md` for the full template.\nSee `examples\u002Fuser-preferences\u002F` for a complete working example.\n\n## Git Integration\n\nEach task completion includes a commit:\n\n```bash\ngit commit -m \"Complete 001 - Preferences Model\n\n- Added JSONField to User model\n- Created Pydantic schemas for validation\n- 5 tests added, 94% coverage\n\nPlan: user-preferences\"\n```\n\nThis is critical for Ralph because:\n- Progress persists across iterations\n- Claude can see what it did via `git log`\n- Partial progress is never lost\n\n## Handling Complex Codebases\n\nFor large\u002Funfamiliar codebases, add a **warm-up task**:\n\n```markdown\n# 000 - Codebase Orientation\n\n## Goal\nUnderstand existing patterns before implementing.\n\n## Checklist\n- [ ] Read existing models in `{{APP_PATH}}`\n- [ ] Identify service layer patterns\n- [ ] Note testing conventions\n- [ ] Document relevant existing code in Notes section\n\n## Completion Criteria\n- [ ] Notes section filled with findings\n- [ ] No implementation (orientation only)\n```\n\nThis prevents Claude from fighting existing patterns.\n\n## Escape Hatches\n\nIf Claude is genuinely stuck:\n\n1. **Blockers section** in task file:\n   ```markdown\n   ## Blockers\n   - **Blocked by:** External API not available\n   - **Attempted:** Mock implementation, local stub\n   - **Needs:** API credentials or decision to defer\n   ```\n\n2. **Skip to independent task** if dependencies allow\n\n3. **Max iterations** as ultimate safety net\n\nThe loop continues until genuine completion or max iterations.\nClaude should never lie to exit.\n\n## Workflow\n\n### 1. Gather Inputs\n\nAsk for all required inputs. Clarify:\n- Exact paths (trailing slashes matter)\n- Test filter that isolates this feature\n- Non-standard tooling (`.bin\u002F` wrappers)\n\n### 2. Analyze Dependencies\n\nBefore creating files:\n1. Identify foundation tasks (no dependencies)\n2. Map task dependencies\n3. Determine critical path\n4. Order to minimize blocking\n\n### 3. Create Files\n\n1. Create `docs\u002Fplans\u002F\u003Cslug>\u002F` directory\n2. Write `PLAN.md` with task index and tracking tables\n3. Write each task file with standard sections\n4. Write `RALPH-PROMPT.md` with all placeholders replaced\n\n### 4. Replace Placeholders\n\nIn RALPH-PROMPT.md, replace:\n- `{{PLAN_TITLE}}` → e.g., \"User Preferences API\"\n- `{{TASK_COUNT}}` → e.g., \"4\"\n- `{{PLAN_SLUG}}` → e.g., \"user-preferences\"\n- `{{PLAN_SLUG_UPPER}}` → e.g., \"USER-PREFERENCES\"\n- `{{LINT_CMD}}` → e.g., \".bin\u002Fruff check\"\n- `{{APP_PATH}}` → e.g., \"accounts\u002F\"\n- `{{MODULE_PATH}}` → e.g., \"preferences\u002F\"\n- All other command\u002Fpath placeholders\n\n### 5. Verify Deliverables\n\nBefore delivering:\n- [ ] PLAN.md has task index and tracking tables\n- [ ] All task files have Goal, Scope, Checklist, Tests, Completion Criteria\n- [ ] Task checklist items are 4-8 each (not too small, not too large)\n- [ ] RALPH-PROMPT.md has NO remaining `{{placeholders}}`\n- [ ] Execution order matches actual dependencies\n- [ ] Completion promise includes task count and slug\n\n## Example\n\nSee `examples\u002Fuser-preferences\u002F` for a complete working example:\n- `PLAN.md` - 4-task plan with tracking\n- `RALPH-PROMPT.md` - Iteration-aware prompt\n- `001-preferences-model.md` - Foundation task (model layer)\n- `002-preferences-service.md` - Service layer\n- `003-api-endpoints.md` - API layer\n- `004-caching-layer.md` - Performance optimization\n\n## Reference Files\n\n- `references\u002Fralph-prompt-template.md` - Full prompt template\n- `references\u002Fplan-template.md` - PLAN.md structure\n- `references\u002Fquality-gates.md` - Verification commands\n- `examples\u002Fuser-preferences\u002F` - Working example\n","# Backend RALPH Plan Skill\n\n## Purpose\n\nThis skill creates **two deliverables**:\n\n1. **PLAN.md** - Structured task index with quality tracking\n2. **RALPH-PROMPT.md** - The prompt fed to `\u002Fralph-wiggum:ralph-loop`\n\nThe key insight: Ralph works by feeding the **same prompt** repeatedly. Claude\nsees its previous work in files\u002Fgit and iterates. RALPH-PROMPT.md becomes that\nprompt, instructing Claude to work through tasks with strict quality gates.\n\n## When to Use\n\n- Backend Django features requiring rigorous quality control\n- Multi-task implementations needing iterative, autonomous execution\n- When you want continuous regression testing between tasks\n- Projects where you'll walk away and let Ralph complete the work\n\n## When NOT to Use\n\n- Quick prototypes or exploratory code\n- Frontend projects (create `frontend-ralph-plan` if needed)\n- Simple tasks that don't need iteration\n- Plans where human judgment is needed at each step\n\n## The Two-Step Process\n\n**Step 1: This skill creates the plan**\n```\ndocs\u002Fplans\u002F\u003Cslug>\u002F\n├── PLAN.md              # Task index with tracking\n├── RALPH-PROMPT.md      # Prompt for ralph-loop\n├── 001-\u003Ctask>.md        # Task files\n└── ...\n```\n\n**Step 2: Run the plan**\n```\n\u002Fplan-directory:run \u003Cslug>\n```\n\nThat's it. This command:\n1. Reads RALPH-PROMPT.md\n2. Extracts the completion promise\n3. Invokes `\u002Fralph-wiggum:ralph-loop` automatically\n\nOptional: `\u002Fplan-directory:run \u003Cslug> --max-iterations 50`\n\n## Required Inputs\n\n| Input | Required | Description |\n|-------|----------|-------------|\n| Plan title | Yes | Human-readable name |\n| Plan slug | Yes | Directory name, kebab-case |\n| Task list | Yes | Tasks with names and scopes |\n| Django app path | Yes | e.g., `optimo_surveys\u002F` |\n| Module path | Yes | e.g., `digest\u002F` |\n| Test filter | Yes | Pytest `-k` filter |\n\n### Tooling Configuration\n\n| Input | Default | Description |\n|-------|---------|-------------|\n| Lint command | `ruff check` | Prefix with `.bin\u002F` if needed |\n| Format command | `ruff format` | |\n| Type check | `ty` | Or `mypy`, `pyright` |\n| Test command | `pytest` | |\n| Test config | `` | e.g., `--dc=TestLocalApp` |\n| Django command | `django` | |\n| Coverage target | `90` | Minimum percentage |\n| Max iterations | `100` | Ralph loop limit |\n\n## Task Granularity Guidelines\n\n**Right-sized tasks for Ralph:**\n\n| Task Size | Checklist Items | Good For |\n|-----------|-----------------|----------|\n| Too small | 1-2 | Overhead exceeds value |\n| **Ideal** | **4-8** | **Clear scope, achievable in one iteration** |\n| Too large | 10+ | Gets stuck, split it |\n\n**Signs a task is too large:**\n- Requires multiple commits to feel \"done\"\n- Has more than 8 checklist items\n- Spans multiple unrelated concerns\n- Would take a human more than 2-4 hours\n\n**Split large tasks by:**\n- Separating model\u002Fservice\u002FAPI layers\n- Breaking by feature subset\n- Isolating integration points\n\n## Completion Promise Format\n\nThe promise must be **plan-specific**, not generic:\n\n```\nALL {{TASK_COUNT}} {{PLAN_SLUG_UPPER}} TASKS COMPLETE\n```\n\nExamples:\n- `ALL 4 USER-PREFERENCES TASKS COMPLETE`\n- `ALL 11 MANAGER-DIGEST TASKS COMPLETE`\n- `ALL 6 NOTIFICATION-SERVICE TASKS COMPLETE`\n\nThis prevents Claude from lying with a generic \"done\" when tasks remain.\n\n## RALPH-PROMPT.md: The Key File\n\nThe prompt is **iteration-aware**. It tells Claude to:\n\n1. **Orient first** - Check git log, read PLAN.md for current status\n2. **Don't repeat work** - Skip what's already committed\n3. **Verify rigorously** - Run all gates after each task\n4. **Commit progress** - Git commit after each task completion\n5. **Handle blockers** - Document, try alternatives, don't lie to exit\n\nSee `references\u002Fralph-prompt-template.md` for the full template.\nSee `examples\u002Fuser-preferences\u002F` for a complete working example.\n\n## Git Integration\n\nEach task completion includes a commit:\n\n```bash\ngit commit -m \"Complete 001 - Preferences Model\n\n- Added JSONField to User model\n- Created Pydantic schemas for validation\n- 5 tests added, 94% coverage\n\nPlan: user-preferences\"\n```\n\nThis is critical for Ralph because:\n- Progress persists across iterations\n- Claude can see what it did via `git log`\n- Partial progress is never lost\n\n## Handling Complex Codebases\n\nFor large\u002Funfamiliar codebases, add a **warm-up task**:\n\n```markdown\n# 000 - Codebase Orientation\n\n## Goal\nUnderstand existing patterns before implementing.\n\n## Checklist\n- [ ] Read existing models in `{{APP_PATH}}`\n- [ ] Identify service layer patterns\n- [ ] Note testing conventions\n- [ ] Document relevant existing code in Notes section\n\n## Completion Criteria\n- [ ] Notes section filled with findings\n- [ ] No implementation (orientation only)\n```\n\nThis prevents Claude from fighting existing patterns.\n\n## Escape Hatches\n\nIf Claude is genuinely stuck:\n\n1. **Blockers section** in task file:\n   ```markdown\n   ## Blockers\n   - **Blocked by:** External API not available\n   - **Attempted:** Mock implementation, local stub\n   - **Needs:** API credentials or decision to defer\n   ```\n\n2. **Skip to independent task** if dependencies allow\n\n3. **Max iterations** as ultimate safety net\n\nThe loop continues until genuine completion or max iterations.\nClaude should never lie to exit.\n\n## Workflow\n\n### 1. Gather Inputs\n\nAsk for all required inputs. Clarify:\n- Exact paths (trailing slashes matter)\n- Test filter that isolates this feature\n- Non-standard tooling (`.bin\u002F` wrappers)\n\n### 2. Analyze Dependencies\n\nBefore creating files:\n1. Identify foundation tasks (no dependencies)\n2. Map task dependencies\n3. Determine critical path\n4. Order to minimize blocking\n\n### 3. Create Files\n\n1. Create `docs\u002Fplans\u002F\u003Cslug>\u002F` directory\n2. Write `PLAN.md` with task index and tracking tables\n3. Write each task file with standard sections\n4. Write `RALPH-PROMPT.md` with all placeholders replaced\n\n### 4. Replace Placeholders\n\nIn RALPH-PROMPT.md, replace:\n- `{{PLAN_TITLE}}` → e.g., \"User Preferences API\"\n- `{{TASK_COUNT}}` → e.g., \"4\"\n- `{{PLAN_SLUG}}` → e.g., \"user-preferences\"\n- `{{PLAN_SLUG_UPPER}}` → e.g., \"USER-PREFERENCES\"\n- `{{LINT_CMD}}` → e.g., \".bin\u002Fruff check\"\n- `{{APP_PATH}}` → e.g., \"accounts\u002F\"\n- `{{MODULE_PATH}}` → e.g., \"preferences\u002F\"\n- All other command\u002Fpath placeholders\n\n### 5. Verify Deliverables\n\nBefore delivering:\n- [ ] PLAN.md has task index and tracking tables\n- [ ] All task files have Goal, Scope, Checklist, Tests, Completion Criteria\n- [ ] Task checklist items are 4-8 each (not too small, not too large)\n- [ ] RALPH-PROMPT.md has NO remaining `{{placeholders}}`\n- [ ] Execution order matches actual dependencies\n- [ ] Completion promise includes task count and slug\n\n## Example\n\nSee `examples\u002Fuser-preferences\u002F` for a complete working example:\n- `PLAN.md` - 4-task plan with tracking\n- `RALPH-PROMPT.md` - Iteration-aware prompt\n- `001-preferences-model.md` - Foundation task (model layer)\n- `002-preferences-service.md` - Service layer\n- `003-api-endpoints.md` - API layer\n- `004-caching-layer.md` - Performance optimization\n\n## Reference Files\n\n- `references\u002Fralph-prompt-template.md` - Full prompt template\n- `references\u002Fplan-template.md` - PLAN.md structure\n- `references\u002Fquality-gates.md` - Verification commands\n- `examples\u002Fuser-preferences\u002F` - Working example\n",{"name":5,"description":52,"allowed-tools":53},"Create a structured plan directory with Ralph Wiggum Loop integration for backend Django projects. Generates PLAN.md (task index), task files, and RALPH-PROMPT.md (the actual prompt for ralph-loop). Use for rigorous, iterative implementation requiring quality gates and verification.\n",[54,55,56,57,44],"Read","Write","Edit","Glob","main","def8531e65114c0fca8fb8551c1871ee0eed705c","skills\u002Faiskillstore\u002Fmarketplace\u002Fdiversioteam\u002Fbackend-ralph-plan",24,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub","https:\u002F\u002Fskillshub.wtf","https:\u002F\u002Fgithub.com\u002FComeOnOliver","AI & Blockchain Engineer\r\n","2026-06-24 22:07:19",{"source":8,"skillName":5,"commands":68,"prompt":78,"zipAvailable":79},[69,72,75],{"tool":70,"command":71},"npx","npx skills add ComeOnOliver\u002Fskillshub --skill backend-ralph-plan",{"tool":73,"command":74},"bunx","bunx skills add ComeOnOliver\u002Fskillshub --skill backend-ralph-plan",{"tool":76,"command":77},"pnpm","pnpm dlx skills add ComeOnOliver\u002Fskillshub --skill backend-ralph-plan","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fdiversioteam\u002Fbackend-ralph-plan\u002FSKILL.md",true,[81,87,91,95,99,103,107,111,115,119,123,127,131,135,141,145,149],{"path":82,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":85,"sourceHtmlUrl":86},"evals\u002Feval_queries.json","REFERENCE","参考文档",2361,"https:\u002F\u002Fgithub.com\u002Feugenelim\u002Fagent-ready-repo\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fauthor-delivery-brief\u002Fevals\u002Feval_queries.json",{"path":88,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":89,"sourceHtmlUrl":90},"evals\u002Fevals.json",8433,"https:\u002F\u002Fgithub.com\u002Feugenelim\u002Fagent-ready-repo\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fauthor-delivery-brief\u002Fevals\u002Fevals.json",{"path":92,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":93,"sourceHtmlUrl":94},"examples\u002Fshape-a-outcome-brief.md",2725,"https:\u002F\u002Fgithub.com\u002Feugenelim\u002Fagent-ready-repo\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fauthor-delivery-brief\u002Fexamples\u002Fshape-a-outcome-brief.md",{"path":96,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":97,"sourceHtmlUrl":98},"examples\u002Fshape-b-story-list-brief.md",2852,"https:\u002F\u002Fgithub.com\u002Feugenelim\u002Fagent-ready-repo\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fauthor-delivery-brief\u002Fexamples\u002Fshape-b-story-list-brief.md",{"path":100,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":101,"sourceHtmlUrl":102},"examples\u002Fuser-preferences\u002F001-preferences-model.md",2106,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fdiversioteam\u002Fbackend-ralph-plan\u002Fexamples\u002Fuser-preferences\u002F001-preferences-model.md",{"path":104,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":105,"sourceHtmlUrl":106},"examples\u002Fuser-preferences\u002F002-preferences-service.md",2068,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fdiversioteam\u002Fbackend-ralph-plan\u002Fexamples\u002Fuser-preferences\u002F002-preferences-service.md",{"path":108,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":109,"sourceHtmlUrl":110},"examples\u002Fuser-preferences\u002F003-api-endpoints.md",1957,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fdiversioteam\u002Fbackend-ralph-plan\u002Fexamples\u002Fuser-preferences\u002F003-api-endpoints.md",{"path":112,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":113,"sourceHtmlUrl":114},"examples\u002Fuser-preferences\u002F004-caching-layer.md",1913,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fdiversioteam\u002Fbackend-ralph-plan\u002Fexamples\u002Fuser-preferences\u002F004-caching-layer.md",{"path":116,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":117,"sourceHtmlUrl":118},"examples\u002Fuser-preferences\u002FPLAN.md",3385,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fdiversioteam\u002Fbackend-ralph-plan\u002Fexamples\u002Fuser-preferences\u002FPLAN.md",{"path":120,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":121,"sourceHtmlUrl":122},"examples\u002Fuser-preferences\u002FRALPH-PROMPT.md",3573,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fdiversioteam\u002Fbackend-ralph-plan\u002Fexamples\u002Fuser-preferences\u002FRALPH-PROMPT.md",{"path":124,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":125,"sourceHtmlUrl":126},"references\u002Fplan-template.md",2613,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fdiversioteam\u002Fbackend-ralph-plan\u002Freferences\u002Fplan-template.md",{"path":128,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":129,"sourceHtmlUrl":130},"references\u002Fquality-gates.md",4540,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fdiversioteam\u002Fbackend-ralph-plan\u002Freferences\u002Fquality-gates.md",{"path":132,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":133,"sourceHtmlUrl":134},"references\u002Fralph-prompt-template.md",4992,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fdiversioteam\u002Fbackend-ralph-plan\u002Freferences\u002Fralph-prompt-template.md",{"path":136,"resourceType":137,"resourceTypeDesc":138,"sizeBytes":139,"sourceHtmlUrl":140},"scripts\u002Fbrief_shape.py","SCRIPT","脚本",17490,"https:\u002F\u002Fgithub.com\u002Feugenelim\u002Fagent-ready-repo\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fauthor-delivery-brief\u002Fscripts\u002Fbrief_shape.py",{"path":142,"resourceType":137,"resourceTypeDesc":138,"sizeBytes":143,"sourceHtmlUrl":144},"scripts\u002Flint-brief-coverage.py",17259,"https:\u002F\u002Fgithub.com\u002Feugenelim\u002Fagent-ready-repo\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fauthor-delivery-brief\u002Fscripts\u002Flint-brief-coverage.py",{"path":146,"resourceType":137,"resourceTypeDesc":138,"sizeBytes":147,"sourceHtmlUrl":148},"scripts\u002Fsource_guard.py",2882,"https:\u002F\u002Fgithub.com\u002Feugenelim\u002Fagent-ready-repo\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fauthor-delivery-brief\u002Fscripts\u002Fsource_guard.py",{"path":150,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":151,"sourceHtmlUrl":152},"skill-report.json",10885,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fdiversioteam\u002Fbackend-ralph-plan\u002Fskill-report.json",[154,164,174,183,189,196],{"skillNo":155,"name":156,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":160,"publishedAt":47},"01M6FKJN13GMG4KY57J3QD8GY5","model-hierarchy-skill","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzscole\u002Fmodel-hierarchy-skill\u002Fmodel-hierarchy-skill\u002FSKILL.md",[159],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[161,162,163],"model","model hierarchy","model hierarchy skill",{"skillNo":165,"name":166,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":170,"publishedAt":47},"01M6FKJJJ6GCAMR4PPPRD12M5X","zoom-mcp","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-mcp\u002FSKILL.md",[169],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[171,172,173],"MCP","zoom","zoom mcp",{"skillNo":175,"name":176,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":179,"publishedAt":47},"01M6FKJE3KYT3KPEZMEEHYKA6K","zoom-apps-sdk","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-apps-sdk\u002FSKILL.md",[],[180,181,182,172],"sdk","zoom apps sdk","apps",{"skillNo":184,"name":185,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":188,"publishedAt":47},"01M6FKJ9EDH9Q5VWDF8HAJRSP0","windows","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwindows\u002FSKILL.md",[],[185],{"skillNo":190,"name":191,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":195,"publishedAt":47},"01M6FKJ666BEEFC3AE9GJ72Q93","whiteboard","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwhiteboard\u002FSKILL.md",[194],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[191],{"skillNo":197,"name":198,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":199,"categories":200,"keywords":201,"publishedAt":47},"01M6FKJ21WFCDGTJQ2Q91T9DVW","websockets","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwebsockets\u002FSKILL.md",[],[198]]