[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CD1RNQMP612EPPZP1JY24T":3,"skill-same:01M6CD1RNQMP612EPPZP1JY24T":91},{"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":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":14,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":44,"install":45,"resources":58},"01M6CD1RNQMP612EPPZP1JY24T","planner",null,"Interactive planning and execution for complex tasks. Use when breaking down multi-step projects (planning) or executing approved plans through delegation (execution). Planning creates milestones with specifications; execution delegates to specialized agents.","loriensleafs\u002Fbrain","loriensleafs","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F315385?v=4","01M6CCYZETMCJPTHNS258YRCBC","Peter Kloss","01M6CCYZK25T8516A39S9PCJT7",0,"MIT","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fplanner\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28],"tasks","planning","delegation","execution","architect","projects","specialized","interactive","implementer","use","2026-11-10 10:12:30",false,"---\nname: planner\ndescription: Interactive planning and execution for complex tasks. Use when breaking down multi-step projects (planning) or executing approved plans through delegation (execution). Planning creates milestones with specifications; execution delegates to specialized agents.\nlicense: MIT\nagents: [planner, architect, implementer]\nmodel: claude-opus-4-5\nmetadata:\n  version: 1.0.0\n  timelessness: high\n---\n\n# Planner Skill\n\n## Purpose\n\nTwo workflows for complex tasks:\n\n1. **Planning workflow** (planner.ts): Create and review implementation plans\n2. **Execution workflow** (executor.ts): Execute approved plans through delegation\n\n## Invocation Routing\n\n**Invoke planner.ts** when user asks to:\n\n- \"plan\", \"design\", \"architect\" a feature\n- \"review\" an existing plan\n- Break down a complex task into milestones\n\n**Invoke executor.ts** when user asks to:\n\n- \"execute\", \"implement\", \"run\" a plan\n- \"resume\" or \"continue\" execution\n- Provides a plan file path for implementation\n\n---\n\n## When to Use\n\nUse the planner skill when the task has:\n\n- Multiple milestones with dependencies\n- Architectural decisions requiring documentation\n- Migration steps that need coordination\n- Complexity that benefits from forced reflection pauses\n\n## When to Skip\n\nSkip the planner skill when the task is:\n\n- Single-step with obvious implementation\n- A quick fix or minor change\n- Already well-specified by the user\n\n---\n\n## Scripts\n\n| Script | Purpose |\n|--------|---------|\n| `scripts\u002Fplanner.ts` | Planning and review workflow with step-based state management |\n| `scripts\u002Fexecutor.ts` | Execution workflow for approved plans with milestone delegation |\n\n## Triggers\n\n| Trigger Phrase | Operation |\n|----------------|-----------|\n| `plan this feature` | planner.ts (planning phase) |\n| `create implementation plan` | planner.ts (planning phase) |\n| `review the plan and pick up next item` | executor.ts (execution phase) |\n| `execute the plan at plans\u002FX.md` | executor.ts (execution phase) |\n| `resume execution` | executor.ts (continue from last step) |\n\n---\n\n## Anti-Patterns\n\n| Avoid | Why | Instead |\n|-------|-----|---------|\n| Skipping review phase after planning | Misses quality\u002Ftemporal issues | Always run review steps 1-2 before execution |\n| Starting execution without \u002Fclear | Context pollution from planning | User should \u002Fclear before execution workflow |\n| Manually following workflow steps | Script manages state and transitions | Run the script and follow its output |\n| Planning single-step tasks | Overhead exceeds benefit | Implement directly without planner |\n| Editing plan during execution | Creates drift between plan and actions | Return to planning phase for changes |\n\n---\n\n## Verification\n\nAfter planning:\n\n- [ ] Plan file written to specified path\n- [ ] Review phase completed (both TW and QR steps)\n- [ ] Review verdict is PASS or PASS_WITH_CONCERNS\n\nAfter execution:\n\n- [ ] All milestones marked complete\n- [ ] Post-implementation QR passed\n- [ ] Documentation step completed\n- [ ] Retrospective generated\n\n---\n\n## Process\n\n### Planning Overview\n\n```text\nPLANNING PHASE (steps 1-N)\n    |\n    v\nWrite plan to file\n    |\n    v\nREVIEW PHASE (steps 1-2)\n    |-- Step 1: @agent-technical-writer (plan-annotation)\n    |-- Step 2: @agent-quality-reviewer (plan-review)\n    v\nAPPROVED --> Execution workflow\n```\n\n### Planning Preconditions\n\nBefore invoking step 1, you MUST have:\n\n1. **Plan file path** - If user did not specify, ASK before proceeding\n2. **Clear problem statement** - What needs to be accomplished\n\n### Planning Invocation\n\n```bash\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fplanner.ts \\\n  --step-number 1 \\\n  --total-steps \u003Cestimated_steps> \\\n  --thoughts \"\u003Cyour thinking about the problem>\"\n```\n\n### Planning Arguments\n\n| Argument        | Description                                      |\n| --------------- | ------------------------------------------------ |\n| `--phase`       | Workflow phase: `planning` (default) or `review` |\n| `--step-number` | Current step (starts at 1)                       |\n| `--total-steps` | Estimated total steps for this phase             |\n| `--thoughts`    | Your thinking, findings, and progress            |\n\n### Planning Steps\n\n1. Confirm preconditions (plan file path, problem statement)\n2. Invoke step 1 immediately\n3. Complete REQUIRED ACTIONS from output\n4. Invoke next step with your thoughts\n5. Repeat until `STATUS: phase_complete`\n6. Write plan to file using format below\n\n## Phase Transition: Planning to Review\n\nWhen planning phase completes, the script outputs an explicit `ACTION REQUIRED`\nmarker:\n\n```text\n============================================\n>>> ACTION REQUIRED: INVOKE REVIEW PHASE \u003C\u003C\u003C\n============================================\n```\n\n**You MUST invoke the review phase before proceeding to execution.**\n\nThe review phase ensures:\n\n- Temporally contaminated comments are fixed (via @agent-technical-writer)\n- Code snippets have WHY comments (via @agent-technical-writer)\n- Plan is validated for production risks (via @agent-quality-reviewer)\n- Documentation needs are identified\n\n## Review Phase\n\nAfter writing the plan file, transition to review phase:\n\n```bash\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fplanner.ts \\\n  --phase review \\\n  --step-number 1 \\\n  --total-steps 2 \\\n  --thoughts \"Plan written to [path\u002Fto\u002Fplan.md]\"\n```\n\n### Review Step 1: Technical Writer\n\nDelegate to @agent-technical-writer with mode: `plan-annotation`\n\n### Review Step 2: Quality Reviewer\n\nDelegate to @agent-quality-reviewer with mode: `plan-review`\n\n### After Review\n\n- **PASS \u002F PASS_WITH_CONCERNS**: Ready for execution workflow\n- **NEEDS_CHANGES**: Return to planning phase to address issues\n\n---\n\n## Execution Workflow (executor.ts)\n\n### Execution Overview\n\n```text\nStep 1: Execution Planning\n    |\n    v\nStep 2: Reconciliation (conditional, if prior work signaled)\n    |\n    v\nStep 3: Milestone Execution (repeat until all complete)\n    |\n    v\nStep 4: Post-Implementation QR\n    |\n    v\nQR issues? --YES--> Step 5: Issue Resolution --> delegate fixes --> Step 4\n    |\n    NO\n    v\nStep 6: Documentation\n    |\n    v\nStep 7: Retrospective\n```\n\n### Execution Preconditions\n\nBefore invoking step 1, you MUST have:\n\n1. **Approved plan file** - Plan that passed review phase\n2. **Clear context window** - User should \u002Fclear before execution\n\n### Execution Invocation\n\n```bash\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fexecutor.ts \\\n  --plan-file PATH \\\n  --step-number 1 \\\n  --total-steps 7 \\\n  --thoughts \"\u003Cuser's request and context>\"\n```\n\n### Execution Arguments\n\n| Argument        | Description                      |\n| --------------- | -------------------------------- |\n| `--plan-file`   | Path to the approved plan file   |\n| `--step-number` | Current step (1-7)               |\n| `--total-steps` | Always 7 for executor            |\n| `--thoughts`    | Your current thinking and status |\n\n## Execution Steps\n\n| Step | Name                   | Purpose                                       |\n| ---- | ---------------------- | --------------------------------------------- |\n| 1    | Execution Planning     | Analyze plan, detect reconciliation, strategy |\n| 2    | Reconciliation         | (conditional) Validate existing code vs plan  |\n| 3    | Milestone Execution    | Delegate to agents, run tests (repeat)        |\n| 4    | Post-Implementation QR | Quality review of implemented code            |\n| 5    | Issue Resolution       | (conditional) Present issues, collect fixes   |\n| 6    | Documentation          | TW pass for CLAUDE.md, README.md              |\n| 7    | Retrospective          | Present execution summary                     |\n\nNote: Step 3 may be re-invoked multiple times until all milestones complete.\nStep 4 may loop back through step 5 until QR passes.\n\n---\n\n## Resources\n\n| Resource                              | Purpose                                            |\n| ------------------------------------- | -------------------------------------------------- |\n| `resources\u002Fplan-format.md`            | Plan template (injected at planning completion)    |\n| `resources\u002Fdiff-format.md`            | Authoritative specification for code change format |\n| `resources\u002Ftemporal-contamination.md` | Detecting\u002Ffixing temporally contaminated comments  |\n| `resources\u002Fdefault-conventions.md`    | Default conventions when project docs are silent   |\n\nNote: Execution guidance is embedded directly in `scripts\u002Fexecutor.ts` (not in\nseparate resource files) since it's only used by that script.\n\n---\n\n## Quick Reference\n\n```bash\n# === PLANNING WORKFLOW ===\n\n# Start planning\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fplanner.ts --step-number 1 --total-steps 4 --thoughts \"...\"\n\n# Continue planning\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fplanner.ts --step-number 2 --total-steps 4 --thoughts \"...\"\n\n# Start review (after plan written)\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fplanner.ts --phase review --step-number 1 --total-steps 2 \\\n  --thoughts \"Plan at plans\u002Ffeature.md\"\n\n# Continue review\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fplanner.ts --phase review --step-number 2 --total-steps 2 \\\n  --thoughts \"TW done, ready for QR\"\n\n# === EXECUTION WORKFLOW ===\n\n# Start execution\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fexecutor.ts --plan-file plans\u002Ffeature.md --step-number 1 \\\n  --total-steps 7 --thoughts \"Execute the feature plan\"\n\n# Continue milestone execution\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fexecutor.ts --plan-file plans\u002Ffeature.md --step-number 3 \\\n  --total-steps 7 --thoughts \"Completed M1, M2. Executing M3...\"\n\n# After QR passes\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fexecutor.ts --plan-file plans\u002Ffeature.md --step-number 6 \\\n  --total-steps 7 --thoughts \"QR passed. Running documentation.\"\n\n# Generate retrospective\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fexecutor.ts --plan-file plans\u002Ffeature.md --step-number 7 \\\n  --total-steps 7 --thoughts \"Execution complete. Generating retrospective.\"\n```\n","# Planner Skill\n\n## Purpose\n\nTwo workflows for complex tasks:\n\n1. **Planning workflow** (planner.ts): Create and review implementation plans\n2. **Execution workflow** (executor.ts): Execute approved plans through delegation\n\n## Invocation Routing\n\n**Invoke planner.ts** when user asks to:\n\n- \"plan\", \"design\", \"architect\" a feature\n- \"review\" an existing plan\n- Break down a complex task into milestones\n\n**Invoke executor.ts** when user asks to:\n\n- \"execute\", \"implement\", \"run\" a plan\n- \"resume\" or \"continue\" execution\n- Provides a plan file path for implementation\n\n---\n\n## When to Use\n\nUse the planner skill when the task has:\n\n- Multiple milestones with dependencies\n- Architectural decisions requiring documentation\n- Migration steps that need coordination\n- Complexity that benefits from forced reflection pauses\n\n## When to Skip\n\nSkip the planner skill when the task is:\n\n- Single-step with obvious implementation\n- A quick fix or minor change\n- Already well-specified by the user\n\n---\n\n## Scripts\n\n| Script | Purpose |\n|--------|---------|\n| `scripts\u002Fplanner.ts` | Planning and review workflow with step-based state management |\n| `scripts\u002Fexecutor.ts` | Execution workflow for approved plans with milestone delegation |\n\n## Triggers\n\n| Trigger Phrase | Operation |\n|----------------|-----------|\n| `plan this feature` | planner.ts (planning phase) |\n| `create implementation plan` | planner.ts (planning phase) |\n| `review the plan and pick up next item` | executor.ts (execution phase) |\n| `execute the plan at plans\u002FX.md` | executor.ts (execution phase) |\n| `resume execution` | executor.ts (continue from last step) |\n\n---\n\n## Anti-Patterns\n\n| Avoid | Why | Instead |\n|-------|-----|---------|\n| Skipping review phase after planning | Misses quality\u002Ftemporal issues | Always run review steps 1-2 before execution |\n| Starting execution without \u002Fclear | Context pollution from planning | User should \u002Fclear before execution workflow |\n| Manually following workflow steps | Script manages state and transitions | Run the script and follow its output |\n| Planning single-step tasks | Overhead exceeds benefit | Implement directly without planner |\n| Editing plan during execution | Creates drift between plan and actions | Return to planning phase for changes |\n\n---\n\n## Verification\n\nAfter planning:\n\n- [ ] Plan file written to specified path\n- [ ] Review phase completed (both TW and QR steps)\n- [ ] Review verdict is PASS or PASS_WITH_CONCERNS\n\nAfter execution:\n\n- [ ] All milestones marked complete\n- [ ] Post-implementation QR passed\n- [ ] Documentation step completed\n- [ ] Retrospective generated\n\n---\n\n## Process\n\n### Planning Overview\n\n```text\nPLANNING PHASE (steps 1-N)\n    |\n    v\nWrite plan to file\n    |\n    v\nREVIEW PHASE (steps 1-2)\n    |-- Step 1: @agent-technical-writer (plan-annotation)\n    |-- Step 2: @agent-quality-reviewer (plan-review)\n    v\nAPPROVED --> Execution workflow\n```\n\n### Planning Preconditions\n\nBefore invoking step 1, you MUST have:\n\n1. **Plan file path** - If user did not specify, ASK before proceeding\n2. **Clear problem statement** - What needs to be accomplished\n\n### Planning Invocation\n\n```bash\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fplanner.ts \\\n  --step-number 1 \\\n  --total-steps \u003Cestimated_steps> \\\n  --thoughts \"\u003Cyour thinking about the problem>\"\n```\n\n### Planning Arguments\n\n| Argument        | Description                                      |\n| --------------- | ------------------------------------------------ |\n| `--phase`       | Workflow phase: `planning` (default) or `review` |\n| `--step-number` | Current step (starts at 1)                       |\n| `--total-steps` | Estimated total steps for this phase             |\n| `--thoughts`    | Your thinking, findings, and progress            |\n\n### Planning Steps\n\n1. Confirm preconditions (plan file path, problem statement)\n2. Invoke step 1 immediately\n3. Complete REQUIRED ACTIONS from output\n4. Invoke next step with your thoughts\n5. Repeat until `STATUS: phase_complete`\n6. Write plan to file using format below\n\n## Phase Transition: Planning to Review\n\nWhen planning phase completes, the script outputs an explicit `ACTION REQUIRED`\nmarker:\n\n```text\n============================================\n>>> ACTION REQUIRED: INVOKE REVIEW PHASE \u003C\u003C\u003C\n============================================\n```\n\n**You MUST invoke the review phase before proceeding to execution.**\n\nThe review phase ensures:\n\n- Temporally contaminated comments are fixed (via @agent-technical-writer)\n- Code snippets have WHY comments (via @agent-technical-writer)\n- Plan is validated for production risks (via @agent-quality-reviewer)\n- Documentation needs are identified\n\n## Review Phase\n\nAfter writing the plan file, transition to review phase:\n\n```bash\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fplanner.ts \\\n  --phase review \\\n  --step-number 1 \\\n  --total-steps 2 \\\n  --thoughts \"Plan written to [path\u002Fto\u002Fplan.md]\"\n```\n\n### Review Step 1: Technical Writer\n\nDelegate to @agent-technical-writer with mode: `plan-annotation`\n\n### Review Step 2: Quality Reviewer\n\nDelegate to @agent-quality-reviewer with mode: `plan-review`\n\n### After Review\n\n- **PASS \u002F PASS_WITH_CONCERNS**: Ready for execution workflow\n- **NEEDS_CHANGES**: Return to planning phase to address issues\n\n---\n\n## Execution Workflow (executor.ts)\n\n### Execution Overview\n\n```text\nStep 1: Execution Planning\n    |\n    v\nStep 2: Reconciliation (conditional, if prior work signaled)\n    |\n    v\nStep 3: Milestone Execution (repeat until all complete)\n    |\n    v\nStep 4: Post-Implementation QR\n    |\n    v\nQR issues? --YES--> Step 5: Issue Resolution --> delegate fixes --> Step 4\n    |\n    NO\n    v\nStep 6: Documentation\n    |\n    v\nStep 7: Retrospective\n```\n\n### Execution Preconditions\n\nBefore invoking step 1, you MUST have:\n\n1. **Approved plan file** - Plan that passed review phase\n2. **Clear context window** - User should \u002Fclear before execution\n\n### Execution Invocation\n\n```bash\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fexecutor.ts \\\n  --plan-file PATH \\\n  --step-number 1 \\\n  --total-steps 7 \\\n  --thoughts \"\u003Cuser's request and context>\"\n```\n\n### Execution Arguments\n\n| Argument        | Description                      |\n| --------------- | -------------------------------- |\n| `--plan-file`   | Path to the approved plan file   |\n| `--step-number` | Current step (1-7)               |\n| `--total-steps` | Always 7 for executor            |\n| `--thoughts`    | Your current thinking and status |\n\n## Execution Steps\n\n| Step | Name                   | Purpose                                       |\n| ---- | ---------------------- | --------------------------------------------- |\n| 1    | Execution Planning     | Analyze plan, detect reconciliation, strategy |\n| 2    | Reconciliation         | (conditional) Validate existing code vs plan  |\n| 3    | Milestone Execution    | Delegate to agents, run tests (repeat)        |\n| 4    | Post-Implementation QR | Quality review of implemented code            |\n| 5    | Issue Resolution       | (conditional) Present issues, collect fixes   |\n| 6    | Documentation          | TW pass for CLAUDE.md, README.md              |\n| 7    | Retrospective          | Present execution summary                     |\n\nNote: Step 3 may be re-invoked multiple times until all milestones complete.\nStep 4 may loop back through step 5 until QR passes.\n\n---\n\n## Resources\n\n| Resource                              | Purpose                                            |\n| ------------------------------------- | -------------------------------------------------- |\n| `resources\u002Fplan-format.md`            | Plan template (injected at planning completion)    |\n| `resources\u002Fdiff-format.md`            | Authoritative specification for code change format |\n| `resources\u002Ftemporal-contamination.md` | Detecting\u002Ffixing temporally contaminated comments  |\n| `resources\u002Fdefault-conventions.md`    | Default conventions when project docs are silent   |\n\nNote: Execution guidance is embedded directly in `scripts\u002Fexecutor.ts` (not in\nseparate resource files) since it's only used by that script.\n\n---\n\n## Quick Reference\n\n```bash\n# === PLANNING WORKFLOW ===\n\n# Start planning\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fplanner.ts --step-number 1 --total-steps 4 --thoughts \"...\"\n\n# Continue planning\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fplanner.ts --step-number 2 --total-steps 4 --thoughts \"...\"\n\n# Start review (after plan written)\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fplanner.ts --phase review --step-number 1 --total-steps 2 \\\n  --thoughts \"Plan at plans\u002Ffeature.md\"\n\n# Continue review\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fplanner.ts --phase review --step-number 2 --total-steps 2 \\\n  --thoughts \"TW done, ready for QR\"\n\n# === EXECUTION WORKFLOW ===\n\n# Start execution\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fexecutor.ts --plan-file plans\u002Ffeature.md --step-number 1 \\\n  --total-steps 7 --thoughts \"Execute the feature plan\"\n\n# Continue milestone execution\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fexecutor.ts --plan-file plans\u002Ffeature.md --step-number 3 \\\n  --total-steps 7 --thoughts \"Completed M1, M2. Executing M3...\"\n\n# After QR passes\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fexecutor.ts --plan-file plans\u002Ffeature.md --step-number 6 \\\n  --total-steps 7 --thoughts \"QR passed. Running documentation.\"\n\n# Generate retrospective\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fexecutor.ts --plan-file plans\u002Ffeature.md --step-number 7 \\\n  --total-steps 7 --thoughts \"Execution complete. Generating retrospective.\"\n```\n",{"name":5,"model":34,"agents":35,"license":15,"metadata":36,"description":7},"claude-opus-4-5",[5,23,27],{"version":37,"timelessness":38},"1.0.0","high","main","2bd10cb7ca989f88dbf338b57957763718eda59b","templates\u002Fskills\u002Fplanner","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain","https:\u002F\u002Fgithub.com\u002Floriensleafs","2026-03-11 23:51:59",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add loriensleafs\u002Fbrain --skill planner",{"tool":51,"command":52},"bunx","bunx skills add loriensleafs\u002Fbrain --skill planner",{"tool":54,"command":55},"pnpm","pnpm dlx skills add loriensleafs\u002Fbrain --skill planner","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fplanner\u002FSKILL.md",true,[59,65,69,73,77,81,87],{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002FDEVELOPMENT.md","REFERENCE","参考文档",3945,"https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fplanner\u002Freferences\u002FDEVELOPMENT.md",{"path":66,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":67,"sourceHtmlUrl":68},"resources\u002Fdefault-conventions.md",3845,"https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fplanner\u002Fresources\u002Fdefault-conventions.md",{"path":70,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":71,"sourceHtmlUrl":72},"resources\u002Fdiff-format.md",8053,"https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fplanner\u002Fresources\u002Fdiff-format.md",{"path":74,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":75,"sourceHtmlUrl":76},"resources\u002Fplan-format.md",6247,"https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fplanner\u002Fresources\u002Fplan-format.md",{"path":78,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":79,"sourceHtmlUrl":80},"resources\u002Ftemporal-contamination.md",6182,"https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fplanner\u002Fresources\u002Ftemporal-contamination.md",{"path":82,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":85,"sourceHtmlUrl":86},"scripts\u002Fexecutor.ts","SCRIPT","脚本",22787,"https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fplanner\u002Fscripts\u002Fexecutor.ts",{"path":88,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":89,"sourceHtmlUrl":90},"scripts\u002Fplanner.ts",23378,"https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fplanner\u002Fscripts\u002Fplanner.ts",[92,106,123,146,167,191],{"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":29},"01M6CD3KHDHPR633RVP95G4XWN","validation-authority","Treat upstream validators as authoritative. Align local config to them. Use when validation fails unexpectedly, before modifying validator behavior, or when tempted to change upstream tool code.","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fvalidation-authority\u002FSKILL.md",[],[99,100,101,28,27,102,103,23,104,105],"validation authority","validation","config","behavior","tool","code","change",{"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":29},"01M6CD3H29Q8FWN9YETT8YVQTS","using-brain-memory","Guidance for using Brain semantic memory effectively. Applies Zettelkasten atomic note principles with observations and relations. Use when deciding whether to query or create notes, structuring note content, or understanding the semantic knowledge graph.","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fusing-forgetful-memory\u002FSKILL.md",[],[113,114,115,116,117,118,119,28,120,121,122],"using brain memory","memory","content","create","notes","graph","guidance","context","knowledge","knowledge graph",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":29},"01M6CD3E2KTTMNSWXRJAAZA7D1","threat-modeling","Structured security analysis using OWASP Four-Question Framework and STRIDE methodology. Generates threat matrices with risk ratings, mitigations, and prioritization. Use for attack surface analysis, security architecture review, or when asking what can go wrong.","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fthreat-modeling\u002FSKILL.md",[],[130,131,132,28,133,23,134,135,136,137,138,139,140,141,142,143,144,145],"threat","threat modeling","prioritization","question","architecture review","stride","analysis","risk","owasp","methodology","framework","security analysis","architecture","security","go","review",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":157,"publishedAt":29},"01M6CD3BC6G0Q2MDNW6X51XHBQ","taste-lints","Custom lints with agent-readable remediation instructions. Enforces taste invariants (file size, naming conventions, structured logging, complexity) and surfaces errors that agents can act on directly. Use when writing or reviewing code to catch style violations early.","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Ftaste-lints\u002FSKILL.md",[152],{"categoryNo":153,"categoryName":154,"taxonomyType":155,"taxonomyTypeDesc":156},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[158,27,159,160,28,161,162,163,164,165,104,166],"taste lints","surfaces","complexity","instructions","remediation","file","logging","qa","writing",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":29},"01M6CD37Z7VD22BH42TG0GM66V","style-enforcement","Validate code against style rules from .editorconfig, StyleCop.json, and Directory.Build.props. Detects line ending violations, naming convention issues, indentation problems, and charset mismatches across C#, Python, TypeScript, and JavaScript. Produces JSON reports for pre-commit hooks and CI pipelines.","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fstyle-enforcement\u002FSKILL.md",[],[174,175,176,177,178,179,27,180,181,182,183,184,165,185,104,186,187,188,189,190],"style enforcement","enforcement","ci","pipelines","directory","hooks","Rules","json","pre-commit","editorconfig","reports","issues","validate","commit","javascript","python","typescript",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":197,"publishedAt":29},"01M6CD35JW73TPMCZBF9DTDEE8","steering-matcher","Match file paths against steering file glob patterns to determine applicable steering guidance. Use when orchestrator needs to inject context-aware guidance based on files being modified.","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fsteering-matcher\u002FSKILL.md",[],[198,28,199,200,120,201,119,163],"steering matcher","files","haiku","orchestrator"]