[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C5FF9FCGDKT9CDV4TTRC4V":3,"skill-same:01M6C5FF9FCGDKT9CDV4TTRC4V":79},{"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":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M6C5FF9FCGDKT9CDV4TTRC4V","blueprint-prp-execute",null,"Execute a PRP with validation loop, TDD, and quality gates. Use when asked to execute a PRP, run a planned feature from docs\u002Fprps\u002F, or delegate a PRP to subagents.","laurigates\u002Fclaude-plugins","laurigates","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F13014001?v=4","01M6C59YHWS9C7KMXKSRX1YXNP","Lauri Gates","01M6C59YP2APG9YAM4DWYQYGFJ",59,"MIT","https:\u002F\u002Fgithub.com\u002Flaurigates\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fblueprint-plugin\u002Fskills\u002Fblueprint-prp-execute\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"execute","blueprint prp execute","Blueprint","2026","subagents","wed","edit","write","when","task","gates","2025","feature","sep","read","run","Bash","loop","use","delegate","auth","2026-11-10 10:12:30",false,"---\ndescription: Execute a PRP with validation loop, TDD, and quality gates. Use when asked to execute a PRP, run a planned feature from docs\u002Fprps\u002F, or delegate a PRP to subagents.\nargs: \"[prp-name]\"\nargument-hint: \"Name of PRP to execute (e.g., feature-auth-oauth2)\"\nallowed-tools: Read, Write, Edit, Glob, Bash, Task, AskUserQuestion\ncreated: 2025-12-16\nmodified: 2026-11-04\nreviewed: 2026-09-02\nname: blueprint-prp-execute\n---\n\n# \u002Fblueprint:prp-execute\n\nExecute a PRP (Product Requirement Prompt) with systematic implementation, validation gates, TDD workflow, and quality assurance.\n\n**Usage**: `\u002Fblueprint:prp-execute [prp-name]`\n\n**Prerequisites**:\n- PRP exists in `docs\u002Fprps\u002F[prp-name].md`\n- Confidence score >= 7 (if lower, suggest `\u002Fblueprint:prp-create` refinement)\n\nFor detailed report templates, deferred items workflow, feature tracker sync, and error handling patterns, see [REFERENCE.md](REFERENCE.md).\n\n## When to Use This Skill\n\n| Use this skill when... | Use alternative when... |\n|------------------------|-------------------------|\n| Ready to implement a planned feature from a PRP | PRP is not yet ready (confidence \u003C 7) |\n| Want to execute with full validation and TDD workflow | Implementing ad-hoc features without documentation |\n| Need feature tracker and GitHub issue tracking | Working on isolated bug fixes |\n| Want automatic progress reporting and deferred items tracking | Quick prototyping without formal tracking |\n\n## Context\n\n- PRP file path: !`find . -maxdepth 3 -path \".\u002Fdocs\u002Fprps\u002F${1:-unknown}.md\"`\n- PRP confidence score: !`find . -path '*\u002Fdocs\u002Fprps\u002F*' -maxdepth 3 -name \"${1:-unknown}.md\" -exec grep -m1 \"^confidence:\" {} +`\n- Feature tracker enabled: !`find . -path '*\u002Fdocs\u002Fblueprint\u002F*' -maxdepth 3 -name 'feature-tracker.json' -type f`\n- Current branch: !`git rev-parse --abbrev-ref HEAD`\n- Uncommitted changes: !`git status --porcelain`\n\n## Parameters\n\nParse `$ARGUMENTS`:\n\n- `prp-name` (required): Name of PRP file in `docs\u002Fprps\u002F` (without .md extension)\n  - Example: `feature-auth-oauth2` → loads `docs\u002Fprps\u002Ffeature-auth-oauth2.md`\n\n## Execution\n\nExecute the complete PRP implementation workflow:\n\n### Step 1: Load and validate PRP\n\n1. Read PRP file: `docs\u002Fprps\u002F{prp-name}.md`\n2. Extract confidence score from frontmatter\n3. If confidence \u003C 7 → Error: \"PRP confidence too low. Run `\u002Fblueprint:prp-create {prp-name}` to refine\"\n4. **Check content quality with a fresh reader** (issue #3002). The confidence score and the structural hook (`check-prp-readiness.sh`) do not judge whether the content can be implemented, and the agent about to execute the PRP has a stake in calling it ready (`.claude\u002Frules\u002Floop-integrity.md` Pillar 1). Dispatch one `Task` agent (`subagent_type: general-purpose`) and give it only the PRP file path and the reader prompt in [REFERENCE.md](REFERENCE.md#prp-content-quality-check): no session context, no plan. It judges specific requirements, testable acceptance criteria, edge cases, and bounded scope, and returns a JSON verdict.\n   - `{\"ok\": true}` → continue\n   - `{\"ok\": false, \"reason\": ...}` → stop before any execution or delegation, print the reason, and suggest `\u002Fblueprint:prp-create {prp-name}` to refine the PRP\n5. If confidence >= 9 → Offer delegation: \"This PRP has high confidence. Execute now (current session) or create work-order for delegation?\"\n   - If work-order chosen → Run `\u002Fblueprint:work-order --from-prp {prp-name}` and exit\n   - If delegation to multiple subagents chosen → Create focused work-orders per module from Implementation Blueprint and exit\n6. Continue to Step 2 if executing now OR confidence 7-8\n7. Load all referenced curated rule entries (`.claude\u002Frules\u002F`) for context\n8. Parse the Implementation Blueprint into an ordered task checklist (dependencies first); track it with `TodoWrite` when the session has the task tools, otherwise carry it as a checklist in the response (see `.claude\u002Frules\u002Fagentic-permissions.md` § Task-tool availability)\n\n### Step 2: Establish baseline with validation gates\n\nRun pre-implementation validation gates (see [REFERENCE.md](REFERENCE.md#validation-gates)) to establish clean starting state:\n\n1. Linting gate: `[command from PRP]` - Expected: PASS\n2. Existing tests gate: `[command from PRP]` - Expected: PASS\n\nIf gates fail:\n- Document existing issues\n- Decide: fix first or proceed with note\n- Continue when ready\n\n### Step 3: Execute TDD implementation cycle\n\nFor each task in Implementation Blueprint:\n\n1. **RED phase**: Write failing test matching PRP TDD Requirements\n   - Create test file if needed\n   - Run tests → Confirm FAILURE (test is meaningful)\n\n2. **GREEN phase**: Implement minimal code to pass test\n   - Follow Codebase Intelligence patterns from PRP\n   - Apply patterns from curated rule references\n   - Watch for Known Gotchas\n   - Run tests → Confirm SUCCESS\n\n3. **REFACTOR phase**: Improve code while keeping tests green\n   - Extract common patterns\n   - Improve naming, add type hints\n   - Follow project conventions\n   - Stay inside the task's files and the PRP task list. A pre-existing bug or\n     unrelated cleanup you notice is not part of this change — record it as a\n     deferred item in Step 5 (a GitHub issue if it is Blocked or Phase 2,\n     otherwise Nice-to-Have). Do not commit scratch or exploratory tests.\n   - Run tests → Confirm PASS\n   - Run validation gates frequently (not just at end)\n\n4. **Mark progress**: once the task's tests pass, tick `Task N` in the checklist\n   from Step 1 (via `TodoWrite` when the task tools are present).\n\n### Step 4: Run comprehensive final validation\n\nExecute all validation gates from PRP (see [REFERENCE.md](REFERENCE.md#validation-gates)):\n- Linting: `[cmd]` - Expected: PASS\n- Type checking: `[cmd]` - Expected: PASS\n- Unit tests: `[cmd]` - Expected: PASS (all tests)\n- Integration tests: `[cmd]` - Expected: PASS (if applicable)\n- Coverage check: `[cmd]` - Expected: Meets threshold\n- Security scan: `[cmd]` - Expected: No high\u002Fcritical issues (if applicable)\n- Performance tests: `[cmd]` - Expected: Meets baseline (if defined)\n\nVerify each success criterion from PRP.\n\n### Step 5: Document deferred items\n\nIdentify and track any deferred work:\n\n1. Review Implementation Blueprint - items not completed\n2. Categorize each deferred item:\n   - **Phase 2 (Required)**: Must have GitHub issues created\n   - **Nice-to-Have**: Optional, no issue required\n   - **Blocked**: Cannot complete - document blocker, create issue\n3. Create GitHub issues for all Phase 2 and Blocked items (see [REFERENCE.md](REFERENCE.md#deferred-items-workflow))\n4. Update PRP with deferred items section linking to GitHub issues\n5. Do NOT proceed to Step 6 until all required issues are created\n\n### Step 6: Sync feature tracker (if enabled)\n\nIf feature tracker exists (`docs\u002Fblueprint\u002Ffeature-tracker.json`):\n\n1. Identify which feature codes (e.g., FR2.1) were addressed from PRP\n2. Update feature tracker for each code:\n   - Status: `complete` (all criteria met) or `partial` (some criteria met) or `in_progress`\n   - Files: List of modified\u002Fcreated files\n   - Tests: List of test files\n   - Commits: Commit hashes\n   - Notes: Implementation notes\n3. Recalculate statistics: completion percentages, phase status\n4. Update TODO.md: Check boxes for completed features\n5. Report feature tracker changes\n\n### Step 7: Report results and next steps\n\nGenerate comprehensive execution summary report:\n\n- **Tasks completed**: X\u002FY\n- **Tests added**: N\n- **Files modified**: [list]\n- **Validation results**: Table of all gates (PASS\u002FFAIL status)\n- **Success criteria**: All verified\n- **Deferred items summary**: Count and GitHub issue numbers\n- **Feature tracker updates**: Features updated and percentages\n- **New gotchas discovered**: [documented for future reference]\n- **Recommendations**: Follow-up work or curated rule updates\n\nPrompt user for next action:\n- Commit changes (Recommended) → Run `\u002Fgit:commit`\n- Create work-order for follow-up → Run `\u002Fblueprint:work-order`\n- Capture patterns as curated rules → Run `\u002Fblueprint:curate-docs`\n- Continue to next PRP → Run `\u002Fblueprint:prp-execute [next]`\n- Done for now → Exit\n\n## Agentic Optimizations\n\n| Context | Command |\n|---------|---------|\n| Check PRP exists | `test -f docs\u002Fprps\u002F${1}.md && echo \"EXISTS\" \\|\\| echo \"MISSING\"` |\n| Extract confidence | `head -50 docs\u002Fprps\u002F${1}.md \\| grep -m1 \"^confidence:\" \\| sed 's\u002F^[^:]*:[[:space:]]*\u002F\u002F'` |\n| List all PRPs | `ls docs\u002Fprps\u002F*.md 2>\u002Fdev\u002Fnull \\| xargs basename -s .md` |\n| Check feature tracker | `test -f docs\u002Fblueprint\u002Ffeature-tracker.json && echo \"YES\" \\|\\| echo \"NO\"` |\n| Fast validation | Run validation gates in parallel when possible |\n\n---\n\nFor detailed validation gate definitions, deferred items workflow, error handling procedures, and agent team coordination, see [REFERENCE.md](REFERENCE.md).\n","# \u002Fblueprint:prp-execute\n\nExecute a PRP (Product Requirement Prompt) with systematic implementation, validation gates, TDD workflow, and quality assurance.\n\n**Usage**: `\u002Fblueprint:prp-execute [prp-name]`\n\n**Prerequisites**:\n- PRP exists in `docs\u002Fprps\u002F[prp-name].md`\n- Confidence score >= 7 (if lower, suggest `\u002Fblueprint:prp-create` refinement)\n\nFor detailed report templates, deferred items workflow, feature tracker sync, and error handling patterns, see [REFERENCE.md](REFERENCE.md).\n\n## When to Use This Skill\n\n| Use this skill when... | Use alternative when... |\n|------------------------|-------------------------|\n| Ready to implement a planned feature from a PRP | PRP is not yet ready (confidence \u003C 7) |\n| Want to execute with full validation and TDD workflow | Implementing ad-hoc features without documentation |\n| Need feature tracker and GitHub issue tracking | Working on isolated bug fixes |\n| Want automatic progress reporting and deferred items tracking | Quick prototyping without formal tracking |\n\n## Context\n\n- PRP file path: !`find . -maxdepth 3 -path \".\u002Fdocs\u002Fprps\u002F${1:-unknown}.md\"`\n- PRP confidence score: !`find . -path '*\u002Fdocs\u002Fprps\u002F*' -maxdepth 3 -name \"${1:-unknown}.md\" -exec grep -m1 \"^confidence:\" {} +`\n- Feature tracker enabled: !`find . -path '*\u002Fdocs\u002Fblueprint\u002F*' -maxdepth 3 -name 'feature-tracker.json' -type f`\n- Current branch: !`git rev-parse --abbrev-ref HEAD`\n- Uncommitted changes: !`git status --porcelain`\n\n## Parameters\n\nParse `$ARGUMENTS`:\n\n- `prp-name` (required): Name of PRP file in `docs\u002Fprps\u002F` (without .md extension)\n  - Example: `feature-auth-oauth2` → loads `docs\u002Fprps\u002Ffeature-auth-oauth2.md`\n\n## Execution\n\nExecute the complete PRP implementation workflow:\n\n### Step 1: Load and validate PRP\n\n1. Read PRP file: `docs\u002Fprps\u002F{prp-name}.md`\n2. Extract confidence score from frontmatter\n3. If confidence \u003C 7 → Error: \"PRP confidence too low. Run `\u002Fblueprint:prp-create {prp-name}` to refine\"\n4. **Check content quality with a fresh reader** (issue #3002). The confidence score and the structural hook (`check-prp-readiness.sh`) do not judge whether the content can be implemented, and the agent about to execute the PRP has a stake in calling it ready (`.claude\u002Frules\u002Floop-integrity.md` Pillar 1). Dispatch one `Task` agent (`subagent_type: general-purpose`) and give it only the PRP file path and the reader prompt in [REFERENCE.md](REFERENCE.md#prp-content-quality-check): no session context, no plan. It judges specific requirements, testable acceptance criteria, edge cases, and bounded scope, and returns a JSON verdict.\n   - `{\"ok\": true}` → continue\n   - `{\"ok\": false, \"reason\": ...}` → stop before any execution or delegation, print the reason, and suggest `\u002Fblueprint:prp-create {prp-name}` to refine the PRP\n5. If confidence >= 9 → Offer delegation: \"This PRP has high confidence. Execute now (current session) or create work-order for delegation?\"\n   - If work-order chosen → Run `\u002Fblueprint:work-order --from-prp {prp-name}` and exit\n   - If delegation to multiple subagents chosen → Create focused work-orders per module from Implementation Blueprint and exit\n6. Continue to Step 2 if executing now OR confidence 7-8\n7. Load all referenced curated rule entries (`.claude\u002Frules\u002F`) for context\n8. Parse the Implementation Blueprint into an ordered task checklist (dependencies first); track it with `TodoWrite` when the session has the task tools, otherwise carry it as a checklist in the response (see `.claude\u002Frules\u002Fagentic-permissions.md` § Task-tool availability)\n\n### Step 2: Establish baseline with validation gates\n\nRun pre-implementation validation gates (see [REFERENCE.md](REFERENCE.md#validation-gates)) to establish clean starting state:\n\n1. Linting gate: `[command from PRP]` - Expected: PASS\n2. Existing tests gate: `[command from PRP]` - Expected: PASS\n\nIf gates fail:\n- Document existing issues\n- Decide: fix first or proceed with note\n- Continue when ready\n\n### Step 3: Execute TDD implementation cycle\n\nFor each task in Implementation Blueprint:\n\n1. **RED phase**: Write failing test matching PRP TDD Requirements\n   - Create test file if needed\n   - Run tests → Confirm FAILURE (test is meaningful)\n\n2. **GREEN phase**: Implement minimal code to pass test\n   - Follow Codebase Intelligence patterns from PRP\n   - Apply patterns from curated rule references\n   - Watch for Known Gotchas\n   - Run tests → Confirm SUCCESS\n\n3. **REFACTOR phase**: Improve code while keeping tests green\n   - Extract common patterns\n   - Improve naming, add type hints\n   - Follow project conventions\n   - Stay inside the task's files and the PRP task list. A pre-existing bug or\n     unrelated cleanup you notice is not part of this change — record it as a\n     deferred item in Step 5 (a GitHub issue if it is Blocked or Phase 2,\n     otherwise Nice-to-Have). Do not commit scratch or exploratory tests.\n   - Run tests → Confirm PASS\n   - Run validation gates frequently (not just at end)\n\n4. **Mark progress**: once the task's tests pass, tick `Task N` in the checklist\n   from Step 1 (via `TodoWrite` when the task tools are present).\n\n### Step 4: Run comprehensive final validation\n\nExecute all validation gates from PRP (see [REFERENCE.md](REFERENCE.md#validation-gates)):\n- Linting: `[cmd]` - Expected: PASS\n- Type checking: `[cmd]` - Expected: PASS\n- Unit tests: `[cmd]` - Expected: PASS (all tests)\n- Integration tests: `[cmd]` - Expected: PASS (if applicable)\n- Coverage check: `[cmd]` - Expected: Meets threshold\n- Security scan: `[cmd]` - Expected: No high\u002Fcritical issues (if applicable)\n- Performance tests: `[cmd]` - Expected: Meets baseline (if defined)\n\nVerify each success criterion from PRP.\n\n### Step 5: Document deferred items\n\nIdentify and track any deferred work:\n\n1. Review Implementation Blueprint - items not completed\n2. Categorize each deferred item:\n   - **Phase 2 (Required)**: Must have GitHub issues created\n   - **Nice-to-Have**: Optional, no issue required\n   - **Blocked**: Cannot complete - document blocker, create issue\n3. Create GitHub issues for all Phase 2 and Blocked items (see [REFERENCE.md](REFERENCE.md#deferred-items-workflow))\n4. Update PRP with deferred items section linking to GitHub issues\n5. Do NOT proceed to Step 6 until all required issues are created\n\n### Step 6: Sync feature tracker (if enabled)\n\nIf feature tracker exists (`docs\u002Fblueprint\u002Ffeature-tracker.json`):\n\n1. Identify which feature codes (e.g., FR2.1) were addressed from PRP\n2. Update feature tracker for each code:\n   - Status: `complete` (all criteria met) or `partial` (some criteria met) or `in_progress`\n   - Files: List of modified\u002Fcreated files\n   - Tests: List of test files\n   - Commits: Commit hashes\n   - Notes: Implementation notes\n3. Recalculate statistics: completion percentages, phase status\n4. Update TODO.md: Check boxes for completed features\n5. Report feature tracker changes\n\n### Step 7: Report results and next steps\n\nGenerate comprehensive execution summary report:\n\n- **Tasks completed**: X\u002FY\n- **Tests added**: N\n- **Files modified**: [list]\n- **Validation results**: Table of all gates (PASS\u002FFAIL status)\n- **Success criteria**: All verified\n- **Deferred items summary**: Count and GitHub issue numbers\n- **Feature tracker updates**: Features updated and percentages\n- **New gotchas discovered**: [documented for future reference]\n- **Recommendations**: Follow-up work or curated rule updates\n\nPrompt user for next action:\n- Commit changes (Recommended) → Run `\u002Fgit:commit`\n- Create work-order for follow-up → Run `\u002Fblueprint:work-order`\n- Capture patterns as curated rules → Run `\u002Fblueprint:curate-docs`\n- Continue to next PRP → Run `\u002Fblueprint:prp-execute [next]`\n- Done for now → Exit\n\n## Agentic Optimizations\n\n| Context | Command |\n|---------|---------|\n| Check PRP exists | `test -f docs\u002Fprps\u002F${1}.md && echo \"EXISTS\" \\|\\| echo \"MISSING\"` |\n| Extract confidence | `head -50 docs\u002Fprps\u002F${1}.md \\| grep -m1 \"^confidence:\" \\| sed 's\u002F^[^:]*:[[:space:]]*\u002F\u002F'` |\n| List all PRPs | `ls docs\u002Fprps\u002F*.md 2>\u002Fdev\u002Fnull \\| xargs basename -s .md` |\n| Check feature tracker | `test -f docs\u002Fblueprint\u002Ffeature-tracker.json && echo \"YES\" \\|\\| echo \"NO\"` |\n| Fast validation | Run validation gates in parallel when possible |\n\n---\n\nFor detailed validation gate definitions, deferred items workflow, error handling procedures, and agent team coordination, see [REFERENCE.md](REFERENCE.md).\n",{"args":45,"name":5,"created":46,"modified":47,"reviewed":48,"description":7,"allowed-tools":49,"argument-hint":50},"[prp-name]",1765843200000,1793750400000,1788307200000,"Read, Write, Edit, Glob, Bash, Task, AskUserQuestion","Name of PRP to execute (e.g., feature-auth-oauth2)","main","9d783554148f9c8a9c55a486b480760d3da673e6","blueprint-plugin\u002Fskills\u002Fblueprint-prp-execute",6,"https:\u002F\u002Fgithub.com\u002Flaurigates\u002Fclaude-plugins","https:\u002F\u002Fgithub.com\u002Flaurigates","Linux enthusiast, cloud engineer, neovim addict, electronics hobbyist.","2026-11-12 03:43:32",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add laurigates\u002Fclaude-plugins --skill blueprint-prp-execute",{"tool":65,"command":66},"bunx","bunx skills add laurigates\u002Fclaude-plugins --skill blueprint-prp-execute",{"tool":68,"command":69},"pnpm","pnpm dlx skills add laurigates\u002Fclaude-plugins --skill blueprint-prp-execute","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flaurigates\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fblueprint-plugin\u002Fskills\u002Fblueprint-prp-execute\u002FSKILL.md",true,[73],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"REFERENCE.md","REFERENCE","参考文档",14468,"https:\u002F\u002Fgithub.com\u002Flaurigates\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fblueprint-plugin\u002Fskills\u002Fblueprint-prp-execute\u002FREFERENCE.md",[80,107,126,142,165,194],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":91,"publishedAt":40},"01M70PFHMH9ADY0CRE6047Y4B2","kitty-show-image","Show the user an image with a note on what to judge, via a file send or a labelled kitty tab. Use when the user must see an image, or icat fails with no \u002Fdev\u002Ftty.","https:\u002F\u002Fgithub.com\u002Flaurigates\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fkitty-plugin\u002Fskills\u002Fkitty-show-image\u002FSKILL.md",[86],{"categoryNo":87,"categoryName":88,"taxonomyType":89,"taxonomyTypeDesc":90},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[92,93,94,95,96,97,98,99,100,101,37,27,35,102,103,104,105,106,22,33],"show","kitty show image","image","kitty","show image","ls","get","send","open","dev","file","text","with","xdg","via",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":40},"01M70PFEN18HKQ4RCQ1VPGMPTB","kitty-session-persistence","Snapshot and restore kitty terminal sessions on macOS. Use when surviving WindowServer hangs without losing tabs, configuring snapshots, or restoring after a force-reboot.","https:\u002F\u002Fgithub.com\u002Flaurigates\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fkitty-plugin\u002Fskills\u002Fkitty-session-persistence\u002FSKILL.md",[],[95,114,115,116,117,118,27,35,119,120,121,22,33,26,25,122,123,124,125,37],"kitty session persistence","session","persistence","false","snapshots","uname","reboot","terminal","snapshot","macos","sessions","restore",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":40},"01M70PFC77XGXCVQ1543VGZHYR","kitty-remote-control","Safe kitty remote control from an agent — read panes with kitty @ ls\u002Fget-text, notify, and never mutate the live terminal unasked. Use when running inside kitty.","https:\u002F\u002Fgithub.com\u002Flaurigates\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fkitty-plugin\u002Fskills\u002Fkitty-remote-control\u002FSKILL.md",[],[133,134,95,135,136,97,137,138,98,139,140,37,27,141,35,103,104,121,22,33],"kitty remote control","remote","control","remote control","running","never","panes","notify","query",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":40},"01M70P6WVMCT5JG4SACTM69AF9","docs-reference-check","Dangling doc-reference gate: flag markdown naming repo paths or relative links that no longer exist. Use when docs cite moved\u002Fdeleted files, or wiring a doc-drift lint.","https:\u002F\u002Fgithub.com\u002Flaurigates\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fdocumentation-plugin\u002Fskills\u002Fdocs-reference-check\u002FSKILL.md",[],[149,150,151,152,153,154,155,156,157,158,37,27,35,159,102,160,161,162,163,164],"docs reference check","check","reference check","reference","docs","links","python3","repo","files","auto","drift","lint","wiring","chezmoi","references","cp",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":180,"publishedAt":40},"01M6C6NDE7DAQGNWSF22J5CJ0Z","youtube-upload","Upload a video to YouTube via the Data API v3 and edit its title, description, tags or thumbnail afterwards. Use when publishing or retitling a YouTube video.","https:\u002F\u002Fgithub.com\u002Flaurigates\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fyoutube-plugin\u002Fskills\u002Fyoutube-upload\u002FSKILL.md",[171,174,175],{"categoryNo":172,"categoryName":173,"taxonomyType":89,"taxonomyTypeDesc":90},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":87,"categoryName":88,"taxonomyType":89,"taxonomyTypeDesc":90},{"categoryNo":176,"categoryName":177,"taxonomyType":178,"taxonomyTypeDesc":179},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[181,182,183,184,155,34,33,185,25,186,187,188,37,35,102,189,190,27,191,192,193,106,22],"youtube upload","upload","youtube","Video","uv run","publishing","data","uv","api","v3","tags","id","title",{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":198,"categories":199,"keywords":203,"publishedAt":40},"01M6C6NABWW1X58KJJM4F6GQMQ","youtube-studio-share","Share a private YouTube video with a whole Google Workspace organization by scripting YouTube Studio in the browser. Use when a video must be org-only.","https:\u002F\u002Fgithub.com\u002Flaurigates\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fyoutube-plugin\u002Fskills\u002Fyoutube-studio-share\u002FSKILL.md",[200],{"categoryNo":201,"categoryName":202,"taxonomyType":89,"taxonomyTypeDesc":90},"01JBSEEDCAT000000000000023","Skill与智能体开发",[204,205,206,207,183,184,208,209,210,211,212,33,213,214,215,216,37,217,27,104,218,22],"youtube studio share","share","youtube studio","studio","browser","javascript","scripting","google workspace","workspace","tool","google","only","MCP","chrome","organization"]