[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CCZMHYV5NM20RZNX9BWA7P":3,"skill-same:01M6CCZMHYV5NM20RZNX9BWA7P":82},{"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":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":14,"repositoryHtmlUrl":54,"repositoryHomepageUrl":6,"ownerHtmlUrl":55,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":56,"install":57,"resources":69},"01M6CCZMHYV5NM20RZNX9BWA7P","analyze",null,"Systematic multi-step codebase analysis producing prioritized findings with file-line evidence. Covers architecture reviews, security assessments, and code quality evaluations through guided exploration, investigation planning, and synthesis.","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\u002Fanalyze\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"security","architecture","code quality","code","planning","file","analysis","investigation","Bash","quality","grep","read","orchestrator","evidence","Synthesis","2026-11-10 10:12:30",false,"---\nname: analyze\ndescription: Systematic multi-step codebase analysis producing prioritized findings with file-line evidence. Covers architecture reviews, security assessments, and code quality evaluations through guided exploration, investigation planning, and synthesis.\nlicense: MIT\nagents:\n  - analyst\n  - orchestrator\nuser-invocable: true\nallowed-tools:\n  - Read\n  - Grep\n  - Glob\n  - Bash\n  - Agent\nmodel: claude-opus-4-6[1m]\nmetadata:\n  version: 1.1.0\n  timelessness: 8\u002F10\n---\n\n# Analyze Skill\n\nWhen this skill activates, IMMEDIATELY invoke the script. The script IS the workflow. Do NOT explore the codebase first.\n\n## Triggers\n\n- `analyze this codebase` - architecture and quality focus\n- `review code quality` - quality focus\n- `run security assessment` - security focus\n- `architecture review of this system` - architecture focus\n- `find code smells` - quality focus\n\n## Quick Reference\n\n| Input               | Focus                                 | Minimum Steps |\n| ------------------- | ------------------------------------- | ------------- |\n| Architecture review | Structure, dependencies, layering     | 6             |\n| Security assessment | Input validation, auth, data handling | 7-9           |\n| Code quality        | Duplication, complexity, test gaps    | 6-7           |\n| Broad investigation | All dimensions                        | 9-12          |\n\n---\n\n## Security\n\nWhen using the `Bash` tool, all arguments containing variable or user-provided input **MUST** be quoted to prevent command injection vulnerabilities. Refer to the repository style guide on Command Injection Prevention (CWE-78).\n\n**WRONG**: `grep $PATTERN \u002Fsome\u002Fpath`\n**CORRECT**: `grep -- \"$PATTERN\" \u002Fsome\u002Fpath`\n\n---\n\n## When to Use\n\nUse this skill when:\n\n- Investigation spans multiple files or components\n- Analysis requires structured multi-step exploration\n- Findings need prioritization by severity with file:line evidence\n\nUse direct code reading instead when:\n\n- Checking a single file or function\n- The question has a known, specific location\n- A quick grep or symbol search answers the question\n\n---\n\n## Scripts\n\n| Script               | Purpose                                                                   | Exit Codes                 |\n| -------------------- | ------------------------------------------------------------------------- | -------------------------- |\n| `scripts\u002Fanalyze.ts` | Multi-step guided analysis with exploration, investigation, and synthesis | 0=success, 1=invalid input |\n\n### Invocation\n\n```bash\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fanalyze.ts \\\n  --step-number 1 \\\n  --total-steps 6 \\\n  --thoughts \"Starting analysis. User request: \u003Cdescribe what user asked to analyze>\"\n```\n\n| Argument        | Required | Description                               |\n| --------------- | -------- | ----------------------------------------- |\n| `--step-number` | Yes      | Current step (starts at 1)                |\n| `--total-steps` | Yes      | Minimum 6; adjust as script instructs     |\n| `--thoughts`    | Yes      | Accumulated state from all previous steps |\n\n---\n\n## Process\n\nThe script outputs REQUIRED ACTIONS at each step. Follow them exactly.\n\n### Phase 1: Exploration (Step 1)\n\nDelegate to Explore agent(s). The script determines scope and parallelism. Wait for all agents, then re-invoke `${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fanalyze.ts` with `--step-number 1`, including the Explore results in `--thoughts`.\n\n### Phase 2: Focus Selection (Step 2)\n\nClassify investigation areas by dimension (architecture, performance, security, quality). Assign priorities P1-P3. Estimate total steps.\n\n### Phase 3: Investigation Planning (Step 3)\n\nCommit to specific files, questions, and hypotheses per focus area. This creates a contract verified in the verification phase.\n\n### Phase 4: Deep Analysis (Steps 4 to N-2)\n\nExecute the investigation plan. Read files, collect evidence with file:line references and quoted code. Trace root causes across files.\n\n### Phase 5: Verification (Step N-1)\n\nAudit completeness against step 3 commitments. Identify gaps. If gaps exist, increase total-steps and return to deep analysis.\n\n### Phase 6: Synthesis (Step N)\n\nConsolidate verified findings by severity (critical, high, medium, low). Identify systemic patterns. Produce prioritized action plan.\n\n---\n\n## Example Sequence\n\n```bash\n# Step 1: Start, script instructs you to explore first\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fanalyze.ts --step-number 1 --total-steps 6 \\\n  --thoughts \"Starting analysis of auth system\"\n\n# [Follow REQUIRED ACTIONS: delegate to Explore agent, wait for results]\n\n# Step 1 again with explore results\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fanalyze.ts --step-number 1 --total-steps 6 \\\n  --thoughts \"Explore found: Flask app, SQLAlchemy, auth\u002F dir...\"\n\n# Step 2+: Continue following script output\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fanalyze.ts --step-number 2 --total-steps 7 \\\n  --thoughts \"[accumulated state from step 1] Focus: security P1, quality P2\"\n```\n\n---\n\n## Anti-Patterns\n\n| Avoid                                             | Why                                   | Instead                                       |\n| ------------------------------------------------- | ------------------------------------- | --------------------------------------------- |\n| Exploring the codebase before invoking the script | Script orchestrates exploration order | Run step 1 immediately, let script direct you |\n| Skipping the Explore agent delegation             | Misses broad codebase context         | Follow step 1 REQUIRED ACTIONS to delegate    |\n| Passing empty thoughts to later steps             | Loses accumulated context             | Include all findings from previous steps      |\n| Reducing total-steps below 6                      | Skips verification and synthesis      | Keep minimum 6, increase as script directs    |\n| Reporting findings without file:line evidence     | Unverifiable claims                   | Always cite specific locations                |\n\n---\n\n## Verification\n\nAfter execution:\n\n- [ ] All priority areas investigated with file-level evidence\n- [ ] Findings include severity classification (critical\u002Fhigh\u002Fmedium\u002Flow)\n- [ ] Each finding has specific file:line references\n- [ ] Synthesis step completed with prioritized recommendations\n- [ ] No investigation areas left unexplored from the plan\n","# Analyze Skill\n\nWhen this skill activates, IMMEDIATELY invoke the script. The script IS the workflow. Do NOT explore the codebase first.\n\n## Triggers\n\n- `analyze this codebase` - architecture and quality focus\n- `review code quality` - quality focus\n- `run security assessment` - security focus\n- `architecture review of this system` - architecture focus\n- `find code smells` - quality focus\n\n## Quick Reference\n\n| Input               | Focus                                 | Minimum Steps |\n| ------------------- | ------------------------------------- | ------------- |\n| Architecture review | Structure, dependencies, layering     | 6             |\n| Security assessment | Input validation, auth, data handling | 7-9           |\n| Code quality        | Duplication, complexity, test gaps    | 6-7           |\n| Broad investigation | All dimensions                        | 9-12          |\n\n---\n\n## Security\n\nWhen using the `Bash` tool, all arguments containing variable or user-provided input **MUST** be quoted to prevent command injection vulnerabilities. Refer to the repository style guide on Command Injection Prevention (CWE-78).\n\n**WRONG**: `grep $PATTERN \u002Fsome\u002Fpath`\n**CORRECT**: `grep -- \"$PATTERN\" \u002Fsome\u002Fpath`\n\n---\n\n## When to Use\n\nUse this skill when:\n\n- Investigation spans multiple files or components\n- Analysis requires structured multi-step exploration\n- Findings need prioritization by severity with file:line evidence\n\nUse direct code reading instead when:\n\n- Checking a single file or function\n- The question has a known, specific location\n- A quick grep or symbol search answers the question\n\n---\n\n## Scripts\n\n| Script               | Purpose                                                                   | Exit Codes                 |\n| -------------------- | ------------------------------------------------------------------------- | -------------------------- |\n| `scripts\u002Fanalyze.ts` | Multi-step guided analysis with exploration, investigation, and synthesis | 0=success, 1=invalid input |\n\n### Invocation\n\n```bash\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fanalyze.ts \\\n  --step-number 1 \\\n  --total-steps 6 \\\n  --thoughts \"Starting analysis. User request: \u003Cdescribe what user asked to analyze>\"\n```\n\n| Argument        | Required | Description                               |\n| --------------- | -------- | ----------------------------------------- |\n| `--step-number` | Yes      | Current step (starts at 1)                |\n| `--total-steps` | Yes      | Minimum 6; adjust as script instructs     |\n| `--thoughts`    | Yes      | Accumulated state from all previous steps |\n\n---\n\n## Process\n\nThe script outputs REQUIRED ACTIONS at each step. Follow them exactly.\n\n### Phase 1: Exploration (Step 1)\n\nDelegate to Explore agent(s). The script determines scope and parallelism. Wait for all agents, then re-invoke `${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fanalyze.ts` with `--step-number 1`, including the Explore results in `--thoughts`.\n\n### Phase 2: Focus Selection (Step 2)\n\nClassify investigation areas by dimension (architecture, performance, security, quality). Assign priorities P1-P3. Estimate total steps.\n\n### Phase 3: Investigation Planning (Step 3)\n\nCommit to specific files, questions, and hypotheses per focus area. This creates a contract verified in the verification phase.\n\n### Phase 4: Deep Analysis (Steps 4 to N-2)\n\nExecute the investigation plan. Read files, collect evidence with file:line references and quoted code. Trace root causes across files.\n\n### Phase 5: Verification (Step N-1)\n\nAudit completeness against step 3 commitments. Identify gaps. If gaps exist, increase total-steps and return to deep analysis.\n\n### Phase 6: Synthesis (Step N)\n\nConsolidate verified findings by severity (critical, high, medium, low). Identify systemic patterns. Produce prioritized action plan.\n\n---\n\n## Example Sequence\n\n```bash\n# Step 1: Start, script instructs you to explore first\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fanalyze.ts --step-number 1 --total-steps 6 \\\n  --thoughts \"Starting analysis of auth system\"\n\n# [Follow REQUIRED ACTIONS: delegate to Explore agent, wait for results]\n\n# Step 1 again with explore results\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fanalyze.ts --step-number 1 --total-steps 6 \\\n  --thoughts \"Explore found: Flask app, SQLAlchemy, auth\u002F dir...\"\n\n# Step 2+: Continue following script output\nbun run ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fanalyze.ts --step-number 2 --total-steps 7 \\\n  --thoughts \"[accumulated state from step 1] Focus: security P1, quality P2\"\n```\n\n---\n\n## Anti-Patterns\n\n| Avoid                                             | Why                                   | Instead                                       |\n| ------------------------------------------------- | ------------------------------------- | --------------------------------------------- |\n| Exploring the codebase before invoking the script | Script orchestrates exploration order | Run step 1 immediately, let script direct you |\n| Skipping the Explore agent delegation             | Misses broad codebase context         | Follow step 1 REQUIRED ACTIONS to delegate    |\n| Passing empty thoughts to later steps             | Loses accumulated context             | Include all findings from previous steps      |\n| Reducing total-steps below 6                      | Skips verification and synthesis      | Keep minimum 6, increase as script directs    |\n| Reporting findings without file:line evidence     | Unverifiable claims                   | Always cite specific locations                |\n\n---\n\n## Verification\n\nAfter execution:\n\n- [ ] All priority areas investigated with file-level evidence\n- [ ] Findings include severity classification (critical\u002Fhigh\u002Fmedium\u002Flow)\n- [ ] Each finding has specific file:line references\n- [ ] Synthesis step completed with prioritized recommendations\n- [ ] No investigation areas left unexplored from the plan\n",{"name":5,"model":39,"agents":40,"license":15,"metadata":42,"description":7,"allowed-tools":45,"user-invocable":50},"claude-opus-4-6[1m]",[41,31],"analyst",{"version":43,"timelessness":44},"1.1.0","8\u002F10",[46,47,48,27,49],"Read","Grep","Glob","Agent",true,"main","2bd10cb7ca989f88dbf338b57957763718eda59b","templates\u002Fskills\u002Fanalyze","https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain","https:\u002F\u002Fgithub.com\u002Floriensleafs","2026-03-11 23:51:59",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":50},[59,62,65],{"tool":60,"command":61},"npx","npx skills add loriensleafs\u002Fbrain --skill analyze",{"tool":63,"command":64},"bunx","bunx skills add loriensleafs\u002Fbrain --skill analyze",{"tool":66,"command":67},"pnpm","pnpm dlx skills add loriensleafs\u002Fbrain --skill analyze","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fanalyze\u002FSKILL.md",[70,76],{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002FDEVELOPMENT.md","REFERENCE","参考文档",2443,"https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fanalyze\u002Freferences\u002FDEVELOPMENT.md",{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"scripts\u002Fanalyze.ts","SCRIPT","脚本",21522,"https:\u002F\u002Fgithub.com\u002Floriensleafs\u002Fbrain\u002Fblob\u002Fmain\u002Ftemplates\u002Fskills\u002Fanalyze\u002Fscripts\u002Fanalyze.ts",[83,99,116,136,156,180],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":34},"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",[],[90,91,92,93,94,95,96,97,22,98],"validation authority","validation","config","use","implementer","behavior","tool","architect","change",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":34},"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",[],[106,107,108,109,110,111,112,93,113,114,115],"using brain memory","memory","content","create","notes","graph","guidance","context","knowledge","knowledge graph",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":34},"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",[],[123,124,125,93,126,97,127,128,25,129,130,131,132,133,20,19,134,135],"threat","threat modeling","prioritization","question","architecture review","stride","risk","owasp","methodology","framework","security analysis","go","review",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":147,"publishedAt":34},"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",[142],{"categoryNo":143,"categoryName":144,"taxonomyType":145,"taxonomyTypeDesc":146},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[148,94,149,150,93,151,152,24,153,154,22,155],"taste lints","surfaces","complexity","instructions","remediation","logging","qa","writing",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":34},"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",[],[163,164,165,166,167,168,94,169,170,171,172,173,154,174,22,175,176,177,178,179],"style enforcement","enforcement","ci","pipelines","directory","hooks","Rules","json","pre-commit","editorconfig","reports","issues","validate","commit","javascript","python","typescript",{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":186,"publishedAt":34},"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",[],[187,93,188,189,113,31,112,24],"steering matcher","files","haiku"]