[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BGA11SF40C0R50R2G900BE":3,"skill-same:01M7BGA11SF40C0R50R2G900BE":58},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7BGA11SF40C0R50R2G900BE","rules-distill",null,"Scan skills to extract cross-cutting principles and distill them into rules — append, revise, or create new rule files","YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-Everything-claude-code\u002Fskills\u002Frules-distill\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: rules-distill\ndescription: \"Scan skills to extract cross-cutting principles and distill them into rules — append, revise, or create new rule files\"\norigin: ECC\n---\n\n# Rules Distill\n\nScan installed skills, extract cross-cutting principles that appear in multiple skills, and distill them into rules — appending to existing rule files, revising outdated content, or creating new rule files.\n\nApplies the \"deterministic collection + LLM judgment\" principle: scripts collect facts exhaustively, then an LLM cross-reads the full context and produces verdicts.\n\n## When to Use\n\n- Periodic rules maintenance (monthly or after installing new skills)\n- After a skill-stocktake reveals patterns that should be rules\n- When rules feel incomplete relative to the skills being used\n\n## How It Works\n\nThe rules distillation process follows three phases:\n\n### Phase 1: Inventory (Deterministic Collection)\n\n#### 1a. Collect skill inventory\n\n```bash\nbash ~\u002F.claude\u002Fskills\u002Frules-distill\u002Fscripts\u002Fscan-skills.sh\n```\n\n#### 1b. Collect rules index\n\n```bash\nbash ~\u002F.claude\u002Fskills\u002Frules-distill\u002Fscripts\u002Fscan-rules.sh\n```\n\n#### 1c. Present to user\n\n```\nRules Distillation — Phase 1: Inventory\n────────────────────────────────────────\nSkills: {N} files scanned\nRules:  {M} files ({K} headings indexed)\n\nProceeding to cross-read analysis...\n```\n\n### Phase 2: Cross-read, Match & Verdict (LLM Judgment)\n\nExtraction and matching are unified in a single pass. Rules files are small enough (~800 lines total) that the full text can be provided to the LLM — no grep pre-filtering needed.\n\n#### Batching\n\nGroup skills into **thematic clusters** based on their descriptions. Analyze each cluster in a subagent with the full rules text.\n\n#### Cross-batch Merge\n\nAfter all batches complete, merge candidates across batches:\n- Deduplicate candidates with the same or overlapping principles\n- Re-check the \"2+ skills\" requirement using evidence from **all** batches combined — a principle found in 1 skill per batch but 2+ skills total is valid\n\n#### Subagent Prompt\n\nLaunch a general-purpose Agent with the following prompt:\n\n````\nYou are an analyst who cross-reads skills to extract principles that should be promoted to rules.\n\n## Input\n- Skills: {full text of skills in this batch}\n- Existing rules: {full text of all rule files}\n\n## Extraction Criteria\n\nInclude a candidate ONLY if ALL of these are true:\n\n1. **Appears in 2+ skills**: Principles found in only one skill should stay in that skill\n2. **Actionable behavior change**: Can be written as \"do X\" or \"don't do Y\" — not \"X is important\"\n3. **Clear violation risk**: What goes wrong if this principle is ignored (1 sentence)\n4. **Not already in rules**: Check the full rules text — including concepts expressed in different words\n\n## Matching & Verdict\n\nFor each candidate, compare against the full rules text and assign a verdict:\n\n- **Append**: Add to an existing section of an existing rule file\n- **Revise**: Existing rule content is inaccurate or insufficient — propose a correction\n- **New Section**: Add a new section to an existing rule file\n- **New File**: Create a new rule file\n- **Already Covered**: Sufficiently covered in existing rules (even if worded differently)\n- **Too Specific**: Should remain at the skill level\n\n## Output Format (per candidate)\n\n```json\n{\n  \"principle\": \"1-2 sentences in 'do X' \u002F 'don't do Y' form\",\n  \"evidence\": [\"skill-name: §Section\", \"skill-name: §Section\"],\n  \"violation_risk\": \"1 sentence\",\n  \"verdict\": \"Append \u002F Revise \u002F New Section \u002F New File \u002F Already Covered \u002F Too Specific\",\n  \"target_rule\": \"filename §Section, or 'new'\",\n  \"confidence\": \"high \u002F medium \u002F low\",\n  \"draft\": \"Draft text for Append\u002FNew Section\u002FNew File verdicts\",\n  \"revision\": {\n    \"reason\": \"Why the existing content is inaccurate or insufficient (Revise only)\",\n    \"before\": \"Current text to be replaced (Revise only)\",\n    \"after\": \"Proposed replacement text (Revise only)\"\n  }\n}\n```\n\n## Exclude\n\n- Obvious principles already in rules\n- Language\u002Fframework-specific knowledge (belongs in language-specific rules or skills)\n- Code examples and commands (belongs in skills)\n````\n\n#### Verdict Reference\n\n| Verdict | Meaning | Presented to User |\n|---------|---------|-------------------|\n| **Append** | Add to existing section | Target + draft |\n| **Revise** | Fix inaccurate\u002Finsufficient content | Target + reason + before\u002Fafter |\n| **New Section** | Add new section to existing file | Target + draft |\n| **New File** | Create new rule file | Filename + full draft |\n| **Already Covered** | Covered in rules (possibly different wording) | Reason (1 line) |\n| **Too Specific** | Should stay in skills | Link to relevant skill |\n\n#### Verdict Quality Requirements\n\n```\n# Good\nAppend to rules\u002Fcommon\u002Fsecurity.md §Input Validation:\n\"Treat LLM output stored in memory or knowledge stores as untrusted — sanitize on write, validate on read.\"\nEvidence: llm-memory-trust-boundary, llm-social-agent-anti-pattern both describe\naccumulated prompt injection risks. Current security.md covers human input\nvalidation only; LLM output trust boundary is missing.\n\n# Bad\nAppend to security.md: Add LLM security principle\n```\n\n### Phase 3: User Review & Execution\n\n#### Summary Table\n\n```\n# Rules Distillation Report\n\n## Summary\nSkills scanned: {N} | Rules: {M} files | Candidates: {K}\n\n| # | Principle | Verdict | Target | Confidence |\n|---|-----------|---------|--------|------------|\n| 1 | ... | Append | security.md §Input Validation | high |\n| 2 | ... | Revise | testing.md §TDD | medium |\n| 3 | ... | New Section | coding-style.md | high |\n| 4 | ... | Too Specific | — | — |\n\n## Details\n(Per-candidate details: evidence, violation_risk, draft text)\n```\n\n#### User Actions\n\nUser responds with numbers to:\n- **Approve**: Apply draft to rules as-is\n- **Modify**: Edit draft before applying\n- **Skip**: Do not apply this candidate\n\n**Never modify rules automatically. Always require user approval.**\n\n#### Save Results\n\nStore results in the skill directory (`results.json`):\n\n- **Timestamp format**: `date -u +%Y-%m-%dT%H:%M:%SZ` (UTC, second precision)\n- **Candidate ID format**: kebab-case derived from the principle (e.g., `llm-output-trust-boundary`)\n\n```json\n{\n  \"distilled_at\": \"2026-03-18T10:30:42Z\",\n  \"skills_scanned\": 56,\n  \"rules_scanned\": 22,\n  \"candidates\": {\n    \"llm-output-trust-boundary\": {\n      \"principle\": \"Treat LLM output as untrusted when stored or re-injected\",\n      \"verdict\": \"Append\",\n      \"target\": \"rules\u002Fcommon\u002Fsecurity.md\",\n      \"evidence\": [\"llm-memory-trust-boundary\", \"llm-social-agent-anti-pattern\"],\n      \"status\": \"applied\"\n    },\n    \"iteration-bounds\": {\n      \"principle\": \"Define explicit stop conditions for all iteration loops\",\n      \"verdict\": \"New Section\",\n      \"target\": \"rules\u002Fcommon\u002Fcoding-style.md\",\n      \"evidence\": [\"iterative-retrieval\", \"continuous-agent-loop\", \"agent-harness-construction\"],\n      \"status\": \"skipped\"\n    }\n  }\n}\n```\n\n## Example\n\n### End-to-end run\n\n```\n$ \u002Frules-distill\n\nRules Distillation — Phase 1: Inventory\n────────────────────────────────────────\nSkills: 56 files scanned\nRules:  22 files (75 headings indexed)\n\nProceeding to cross-read analysis...\n\n[Subagent analysis: Batch 1 (agent\u002Fmeta skills) ...]\n[Subagent analysis: Batch 2 (coding\u002Fpattern skills) ...]\n[Cross-batch merge: 2 duplicates removed, 1 cross-batch candidate promoted]\n\n# Rules Distillation Report\n\n## Summary\nSkills scanned: 56 | Rules: 22 files | Candidates: 4\n\n| # | Principle | Verdict | Target | Confidence |\n|---|-----------|---------|--------|------------|\n| 1 | LLM output: normalize, type-check, sanitize before reuse | New Section | coding-style.md | high |\n| 2 | Define explicit stop conditions for iteration loops | New Section | coding-style.md | high |\n| 3 | Compact context at phase boundaries, not mid-task | Append | performance.md §Context Window | high |\n| 4 | Separate business logic from I\u002FO framework types | New Section | patterns.md | high |\n\n## Details\n\n### 1. LLM Output Validation\nVerdict: New Section in coding-style.md\nEvidence: parallel-subagent-batch-merge, llm-social-agent-anti-pattern, llm-memory-trust-boundary\nViolation risk: Format drift, type mismatch, or syntax errors in LLM output crash downstream processing\nDraft:\n  ## LLM Output Validation\n  Normalize, type-check, and sanitize LLM output before reuse...\n  See skill: parallel-subagent-batch-merge, llm-memory-trust-boundary\n\n[... details for candidates 2-4 ...]\n\nApprove, modify, or skip each candidate by number:\n> User: Approve 1, 3. Skip 2, 4.\n\n✓ Applied: coding-style.md §LLM Output Validation\n✓ Applied: performance.md §Context Window Management\n✗ Skipped: Iteration Bounds\n✗ Skipped: Boundary Type Conversion\n\nResults saved to results.json\n```\n\n## Design Principles\n\n- **What, not How**: Extract principles (rules territory) only. Code examples and commands stay in skills.\n- **Link back**: Draft text should include `See skill: [name]` references so readers can find the detailed How.\n- **Deterministic collection, LLM judgment**: Scripts guarantee exhaustiveness; the LLM guarantees contextual understanding.\n- **Anti-abstraction safeguard**: The 3-layer filter (2+ skills evidence, actionable behavior test, violation risk) prevents overly abstract principles from entering rules.\n","# Rules Distill\n\nScan installed skills, extract cross-cutting principles that appear in multiple skills, and distill them into rules — appending to existing rule files, revising outdated content, or creating new rule files.\n\nApplies the \"deterministic collection + LLM judgment\" principle: scripts collect facts exhaustively, then an LLM cross-reads the full context and produces verdicts.\n\n## When to Use\n\n- Periodic rules maintenance (monthly or after installing new skills)\n- After a skill-stocktake reveals patterns that should be rules\n- When rules feel incomplete relative to the skills being used\n\n## How It Works\n\nThe rules distillation process follows three phases:\n\n### Phase 1: Inventory (Deterministic Collection)\n\n#### 1a. Collect skill inventory\n\n```bash\nbash ~\u002F.claude\u002Fskills\u002Frules-distill\u002Fscripts\u002Fscan-skills.sh\n```\n\n#### 1b. Collect rules index\n\n```bash\nbash ~\u002F.claude\u002Fskills\u002Frules-distill\u002Fscripts\u002Fscan-rules.sh\n```\n\n#### 1c. Present to user\n\n```\nRules Distillation — Phase 1: Inventory\n────────────────────────────────────────\nSkills: {N} files scanned\nRules:  {M} files ({K} headings indexed)\n\nProceeding to cross-read analysis...\n```\n\n### Phase 2: Cross-read, Match & Verdict (LLM Judgment)\n\nExtraction and matching are unified in a single pass. Rules files are small enough (~800 lines total) that the full text can be provided to the LLM — no grep pre-filtering needed.\n\n#### Batching\n\nGroup skills into **thematic clusters** based on their descriptions. Analyze each cluster in a subagent with the full rules text.\n\n#### Cross-batch Merge\n\nAfter all batches complete, merge candidates across batches:\n- Deduplicate candidates with the same or overlapping principles\n- Re-check the \"2+ skills\" requirement using evidence from **all** batches combined — a principle found in 1 skill per batch but 2+ skills total is valid\n\n#### Subagent Prompt\n\nLaunch a general-purpose Agent with the following prompt:\n\n````\nYou are an analyst who cross-reads skills to extract principles that should be promoted to rules.\n\n## Input\n- Skills: {full text of skills in this batch}\n- Existing rules: {full text of all rule files}\n\n## Extraction Criteria\n\nInclude a candidate ONLY if ALL of these are true:\n\n1. **Appears in 2+ skills**: Principles found in only one skill should stay in that skill\n2. **Actionable behavior change**: Can be written as \"do X\" or \"don't do Y\" — not \"X is important\"\n3. **Clear violation risk**: What goes wrong if this principle is ignored (1 sentence)\n4. **Not already in rules**: Check the full rules text — including concepts expressed in different words\n\n## Matching & Verdict\n\nFor each candidate, compare against the full rules text and assign a verdict:\n\n- **Append**: Add to an existing section of an existing rule file\n- **Revise**: Existing rule content is inaccurate or insufficient — propose a correction\n- **New Section**: Add a new section to an existing rule file\n- **New File**: Create a new rule file\n- **Already Covered**: Sufficiently covered in existing rules (even if worded differently)\n- **Too Specific**: Should remain at the skill level\n\n## Output Format (per candidate)\n\n```json\n{\n  \"principle\": \"1-2 sentences in 'do X' \u002F 'don't do Y' form\",\n  \"evidence\": [\"skill-name: §Section\", \"skill-name: §Section\"],\n  \"violation_risk\": \"1 sentence\",\n  \"verdict\": \"Append \u002F Revise \u002F New Section \u002F New File \u002F Already Covered \u002F Too Specific\",\n  \"target_rule\": \"filename §Section, or 'new'\",\n  \"confidence\": \"high \u002F medium \u002F low\",\n  \"draft\": \"Draft text for Append\u002FNew Section\u002FNew File verdicts\",\n  \"revision\": {\n    \"reason\": \"Why the existing content is inaccurate or insufficient (Revise only)\",\n    \"before\": \"Current text to be replaced (Revise only)\",\n    \"after\": \"Proposed replacement text (Revise only)\"\n  }\n}\n```\n\n## Exclude\n\n- Obvious principles already in rules\n- Language\u002Fframework-specific knowledge (belongs in language-specific rules or skills)\n- Code examples and commands (belongs in skills)\n````\n\n#### Verdict Reference\n\n| Verdict | Meaning | Presented to User |\n|---------|---------|-------------------|\n| **Append** | Add to existing section | Target + draft |\n| **Revise** | Fix inaccurate\u002Finsufficient content | Target + reason + before\u002Fafter |\n| **New Section** | Add new section to existing file | Target + draft |\n| **New File** | Create new rule file | Filename + full draft |\n| **Already Covered** | Covered in rules (possibly different wording) | Reason (1 line) |\n| **Too Specific** | Should stay in skills | Link to relevant skill |\n\n#### Verdict Quality Requirements\n\n```\n# Good\nAppend to rules\u002Fcommon\u002Fsecurity.md §Input Validation:\n\"Treat LLM output stored in memory or knowledge stores as untrusted — sanitize on write, validate on read.\"\nEvidence: llm-memory-trust-boundary, llm-social-agent-anti-pattern both describe\naccumulated prompt injection risks. Current security.md covers human input\nvalidation only; LLM output trust boundary is missing.\n\n# Bad\nAppend to security.md: Add LLM security principle\n```\n\n### Phase 3: User Review & Execution\n\n#### Summary Table\n\n```\n# Rules Distillation Report\n\n## Summary\nSkills scanned: {N} | Rules: {M} files | Candidates: {K}\n\n| # | Principle | Verdict | Target | Confidence |\n|---|-----------|---------|--------|------------|\n| 1 | ... | Append | security.md §Input Validation | high |\n| 2 | ... | Revise | testing.md §TDD | medium |\n| 3 | ... | New Section | coding-style.md | high |\n| 4 | ... | Too Specific | — | — |\n\n## Details\n(Per-candidate details: evidence, violation_risk, draft text)\n```\n\n#### User Actions\n\nUser responds with numbers to:\n- **Approve**: Apply draft to rules as-is\n- **Modify**: Edit draft before applying\n- **Skip**: Do not apply this candidate\n\n**Never modify rules automatically. Always require user approval.**\n\n#### Save Results\n\nStore results in the skill directory (`results.json`):\n\n- **Timestamp format**: `date -u +%Y-%m-%dT%H:%M:%SZ` (UTC, second precision)\n- **Candidate ID format**: kebab-case derived from the principle (e.g., `llm-output-trust-boundary`)\n\n```json\n{\n  \"distilled_at\": \"2026-03-18T10:30:42Z\",\n  \"skills_scanned\": 56,\n  \"rules_scanned\": 22,\n  \"candidates\": {\n    \"llm-output-trust-boundary\": {\n      \"principle\": \"Treat LLM output as untrusted when stored or re-injected\",\n      \"verdict\": \"Append\",\n      \"target\": \"rules\u002Fcommon\u002Fsecurity.md\",\n      \"evidence\": [\"llm-memory-trust-boundary\", \"llm-social-agent-anti-pattern\"],\n      \"status\": \"applied\"\n    },\n    \"iteration-bounds\": {\n      \"principle\": \"Define explicit stop conditions for all iteration loops\",\n      \"verdict\": \"New Section\",\n      \"target\": \"rules\u002Fcommon\u002Fcoding-style.md\",\n      \"evidence\": [\"iterative-retrieval\", \"continuous-agent-loop\", \"agent-harness-construction\"],\n      \"status\": \"skipped\"\n    }\n  }\n}\n```\n\n## Example\n\n### End-to-end run\n\n```\n$ \u002Frules-distill\n\nRules Distillation — Phase 1: Inventory\n────────────────────────────────────────\nSkills: 56 files scanned\nRules:  22 files (75 headings indexed)\n\nProceeding to cross-read analysis...\n\n[Subagent analysis: Batch 1 (agent\u002Fmeta skills) ...]\n[Subagent analysis: Batch 2 (coding\u002Fpattern skills) ...]\n[Cross-batch merge: 2 duplicates removed, 1 cross-batch candidate promoted]\n\n# Rules Distillation Report\n\n## Summary\nSkills scanned: 56 | Rules: 22 files | Candidates: 4\n\n| # | Principle | Verdict | Target | Confidence |\n|---|-----------|---------|--------|------------|\n| 1 | LLM output: normalize, type-check, sanitize before reuse | New Section | coding-style.md | high |\n| 2 | Define explicit stop conditions for iteration loops | New Section | coding-style.md | high |\n| 3 | Compact context at phase boundaries, not mid-task | Append | performance.md §Context Window | high |\n| 4 | Separate business logic from I\u002FO framework types | New Section | patterns.md | high |\n\n## Details\n\n### 1. LLM Output Validation\nVerdict: New Section in coding-style.md\nEvidence: parallel-subagent-batch-merge, llm-social-agent-anti-pattern, llm-memory-trust-boundary\nViolation risk: Format drift, type mismatch, or syntax errors in LLM output crash downstream processing\nDraft:\n  ## LLM Output Validation\n  Normalize, type-check, and sanitize LLM output before reuse...\n  See skill: parallel-subagent-batch-merge, llm-memory-trust-boundary\n\n[... details for candidates 2-4 ...]\n\nApprove, modify, or skip each candidate by number:\n> User: Approve 1, 3. Skip 2, 4.\n\n✓ Applied: coding-style.md §LLM Output Validation\n✓ Applied: performance.md §Context Window Management\n✗ Skipped: Iteration Bounds\n✗ Skipped: Boundary Type Conversion\n\nResults saved to results.json\n```\n\n## Design Principles\n\n- **What, not How**: Extract principles (rules territory) only. Code examples and commands stay in skills.\n- **Link back**: Draft text should include `See skill: [name]` references so readers can find the detailed How.\n- **Deterministic collection, LLM judgment**: Scripts guarantee exhaustiveness; the LLM guarantees contextual understanding.\n- **Anti-abstraction safeguard**: The 3-layer filter (2+ skills evidence, actionable behavior test, violation risk) prevents overly abstract principles from entering rules.\n",{"name":5,"origin":24,"description":7},"ECC","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-AI-应用工具\u002FYYC3-AI-应用工具-Everything-claude-code\u002Fskills\u002Frules-distill",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill rules-distill",{"tool":40,"command":41},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill rules-distill",{"tool":43,"command":44},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill rules-distill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-Everything-claude-code\u002Fskills\u002Frules-distill\u002FSKILL.md",true,[48,54],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"scripts\u002Fscan-rules.sh","SCRIPT","脚本",1604,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-Everything-claude-code\u002Fskills\u002Frules-distill\u002Fscripts\u002Fscan-rules.sh",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"scripts\u002Fscan-skills.sh",3893,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-Everything-claude-code\u002Fskills\u002Frules-distill\u002Fscripts\u002Fscan-skills.sh",[59,66,73,80,87,94],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"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":86,"publishedAt":19},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]