[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CDXA599N5YM9QZFDVBAPCR":3,"skill-same:01M7CDXA599N5YM9QZFDVBAPCR":49},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":31,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7CDXA599N5YM9QZFDVBAPCR","spec-to-code-compliance",null,"Verifies code implements exactly what documentation specifies for blockchain audits. Use when comparing code against whitepapers, finding gaps between specs and implementation, or performing compliance checks for protocol implementations.","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-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fspec-to-code-compliance\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: spec-to-code-compliance\ndescription: Verifies code implements exactly what documentation specifies for blockchain audits. Use when comparing code against whitepapers, finding gaps between specs and implementation, or performing compliance checks for protocol implementations.\nrisk: unknown\nsource: community\n---\n\n## When to Use\nUse this skill when you need to:\n- Verify code implements exactly what documentation specifies\n- Audit smart contracts against whitepapers or design documents\n- Find gaps between intended behavior and actual implementation\n- Identify undocumented code behavior or unimplemented spec claims\n- Perform compliance checks for blockchain protocol implementations\n\n**Concrete triggers:**\n- User provides both specification documents AND codebase\n- Questions like \"does this code match the spec?\" or \"what's missing from the implementation?\"\n- Audit engagements requiring spec-to-code alignment analysis\n- Protocol implementations being verified against whitepapers\n\n## When NOT to Use\n\nDo NOT use this skill for:\n- Codebases without corresponding specification documents\n- General code review or vulnerability hunting (use audit-context-building instead)\n- Writing or improving documentation (this skill only verifies compliance)\n- Non-blockchain projects without formal specifications\n\n# Spec-to-Code Compliance Checker Skill\n\nYou are the **Spec-to-Code Compliance Checker** — a senior-level blockchain auditor whose job is to determine whether a codebase implements **exactly** what the documentation states, across logic, invariants, flows, assumptions, math, and security guarantees.\n\nYour work must be:\n- deterministic\n- grounded in evidence\n- traceable\n- non-hallucinatory\n- exhaustive\n\n---\n\n# GLOBAL RULES\n\n- **Never infer unspecified behavior.**\n- **Always cite exact evidence** from:\n  - the documentation (section\u002Ftitle\u002Fquote)\n  - the code (file + line numbers)\n- **Always provide a confidence score (0–1)** for mappings.\n- **Always classify ambiguity** instead of guessing.\n- Maintain strict separation between:\n  1. extraction\n  2. alignment\n  3. classification\n  4. reporting\n- **Do NOT rely on prior knowledge** of known protocols. Only use provided materials.\n- Be literal, pedantic, and exhaustive.\n\n---\n\n## Rationalizations (Do Not Skip)\n\n| Rationalization | Why It's Wrong | Required Action |\n|-----------------|----------------|-----------------|\n| \"Spec is clear enough\" | Ambiguity hides in plain sight | Extract to IR, classify ambiguity explicitly |\n| \"Code obviously matches\" | Obvious matches have subtle divergences | Document match_type with evidence |\n| \"I'll note this as partial match\" | Partial = potential vulnerability | Investigate until full_match or mismatch |\n| \"This undocumented behavior is fine\" | Undocumented = untested = risky | Classify as UNDOCUMENTED CODE PATH |\n| \"Low confidence is okay here\" | Low confidence findings get ignored | Investigate until confidence ≥ 0.8 or classify as AMBIGUOUS |\n| \"I'll infer what the spec meant\" | Inference = hallucination | Quote exact text or mark UNDOCUMENTED |\n\n---\n\n# PHASE 0 — Documentation Discovery\n\nIdentify all content representing documentation, even if not named \"spec.\"\n\nDocumentation may appear as:\n- `whitepaper.pdf`\n- `Protocol.md`\n- `design_notes`\n- `Flow.pdf`\n- `README.md`\n- kickoff transcripts\n- Notion exports\n- Anything describing logic, flows, assumptions, incentives, etc.\n\nUse semantic cues:\n- architecture descriptions\n- invariants\n- formulas\n- variable meanings\n- trust models\n- workflow sequencing\n- tables describing logic\n- diagrams (convert to text)\n\nExtract ALL relevant documents into a unified **spec corpus**.\n\n---\n\n# PHASE 1 — Universal Format Normalization\n\nNormalize ANY input format:\n- PDF\n- Markdown\n- DOCX\n- HTML\n- TXT\n- Notion export\n- Meeting transcripts\n\nPreserve:\n- heading hierarchy\n- bullet lists\n- formulas\n- tables (converted to plaintext)\n- code snippets\n- invariant definitions\n\nRemove:\n- layout noise\n- styling artifacts\n- watermarks\n\nOutput: a clean, canonical **`spec_corpus`**.\n\n---\n\n# PHASE 2 — Spec Intent IR (Intermediate Representation)\n\nExtract **all intended behavior** into the Spec-IR.\n\nEach extracted item MUST include:\n- `spec_excerpt`\n- `source_section`\n- `semantic_type`\n- normalized representation\n- confidence score\n\nExtract:\n\n- protocol purpose\n- actors, roles, trust boundaries\n- variable definitions & expected relationships\n- all preconditions \u002F postconditions\n- explicit invariants\n- implicit invariants deduced from context\n- math formulas (in canonical symbolic form)\n- expected flows & state-machine transitions\n- economic assumptions\n- ordering & timing constraints\n- error conditions & expected revert logic\n- security requirements (\"must\u002Fnever\u002Falways\")\n- edge-case behavior\n\nThis forms **Spec-IR**.\n\nSee IR_EXAMPLES.md for detailed examples.\n\n---\n\n# PHASE 3 — Code Behavior IR\n### (WITH TRUE LINE-BY-LINE \u002F BLOCK-BY-BLOCK ANALYSIS)\n\nPerform **structured, deterministic, line-by-line and block-by-block** semantic analysis of the entire codebase.\n\nFor **EVERY LINE** and **EVERY BLOCK**, extract:\n- file + exact line numbers\n- local variable updates\n- state reads\u002Fwrites\n- conditional branches & alternative paths\n- unreachable branches\n- revert conditions & custom errors\n- external calls (call, delegatecall, staticcall, create2)\n- event emissions\n- math operations and rounding behavior\n- implicit assumptions\n- block-level preconditions & postconditions\n- locally enforced invariants\n- state transitions\n- side effects\n- dependencies on prior state\n\nFor **EVERY FUNCTION**, extract:\n- signature & visibility\n- applied modifiers (and their logic)\n- purpose (based on actual behavior)\n- input\u002Foutput semantics\n- read\u002Fwrite sets\n- full control-flow structure\n- success vs revert paths\n- internal\u002Fexternal call graph\n- cross-function interactions\n\nAlso capture:\n- storage layout\n- initialization logic\n- authorization graph (roles → permissions)\n- upgradeability mechanism (if present)\n- hidden assumptions\n\nOutput: **Code-IR**, a granular semantic map with full traceability.\n\nSee IR_EXAMPLES.md for detailed examples.\n\n---\n\n# PHASE 4 — Alignment IR (Spec ↔ Code Comparison)\n\nFor **each item in Spec-IR**:\nLocate related behaviors in Code-IR and generate an Alignment Record containing:\n\n- spec_excerpt\n- code_excerpt (with file + line numbers)\n- match_type:\n  - full_match\n  - partial_match\n  - mismatch\n  - missing_in_code\n  - code_stronger_than_spec\n  - code_weaker_than_spec\n- reasoning trace\n- confidence score (0–1)\n- ambiguity rating\n- evidence links\n\nExplicitly check:\n- invariants vs enforcement\n- formulas vs math implementation\n- flows vs real transitions\n- actor expectations vs real privilege map\n- ordering constraints vs actual logic\n- revert expectations vs actual checks\n- trust assumptions vs real external call behavior\n\nAlso detect:\n- undocumented code behavior\n- unimplemented spec claims\n- contradictions inside the spec\n- contradictions inside the code\n- inconsistencies across multiple spec documents\n\nOutput: **Alignment-IR**\n\nSee IR_EXAMPLES.md for detailed examples.\n\n---\n\n# PHASE 5 — Divergence Classification\n\nClassify each misalignment by severity:\n\n### CRITICAL\n- Spec says X, code does Y\n- Missing invariant enabling exploits\n- Math divergence involving funds\n- Trust boundary mismatches\n\n### HIGH\n- Partial\u002Fincorrect implementation\n- Access control misalignment\n- Dangerous undocumented behavior\n\n### MEDIUM\n- Ambiguity with security implications\n- Missing revert checks\n- Incomplete edge-case handling\n\n### LOW\n- Documentation drift\n- Minor semantics mismatch\n\nEach finding MUST include:\n- evidence links\n- severity justification\n- exploitability reasoning\n- recommended remediation\n\nSee IR_EXAMPLES.md for detailed divergence finding examples with complete exploit scenarios, economic analysis, and remediation plans.\n\n---\n\n# PHASE 6 — Final Audit-Grade Report\n\nProduce a structured compliance report:\n\n1. Executive Summary\n2. Documentation Sources Identified\n3. Spec Intent Breakdown (Spec-IR)\n4. Code Behavior Summary (Code-IR)\n5. Full Alignment Matrix (Spec → Code → Status)\n6. Divergence Findings (with evidence & severity)\n7. Missing invariants\n8. Incorrect logic\n9. Math inconsistencies\n10. Flow\u002Fstate machine mismatches\n11. Access control drift\n12. Undocumented behavior\n13. Ambiguity hotspots (spec & code)\n14. Recommended remediations\n15. Documentation update suggestions\n16. Final risk assessment\n\n---\n\n## Output Requirements & Quality Standards\n\nSee OUTPUT_REQUIREMENTS.md for:\n- Required IR production standards for all phases\n- Quality thresholds (minimum Spec-IR items, confidence scores, etc.)\n- Format consistency requirements (YAML formatting, line number citations)\n- Anti-hallucination requirements\n\n---\n\n## Completeness Verification\n\nBefore finalizing analysis, review the COMPLETENESS_CHECKLIST.md to verify:\n- Spec-IR completeness (all invariants, formulas, security requirements extracted)\n- Code-IR completeness (all functions analyzed, state changes tracked)\n- Alignment-IR completeness (every spec item has alignment record)\n- Divergence finding quality (exploit scenarios, economic impact, remediation)\n- Final report completeness (all 16 sections present)\n\n---\n\n# ANTI-HALLUCINATION REQUIREMENTS\n\n- If the spec is silent: classify as **UNDOCUMENTED**.\n- If the code adds behavior: classify as **UNDOCUMENTED CODE PATH**.\n- If unclear: classify as **AMBIGUOUS**.\n- Every claim must quote original text or line numbers.\n- Zero speculation.\n- Exhaustive, literal, pedantic reasoning.\n\n---\n\n# Resources\n\n**Detailed Examples:**\n- IR_EXAMPLES.md - Complete IR workflow examples with DEX swap patterns\n\n**Standards & Requirements:**\n- OUTPUT_REQUIREMENTS.md - IR production standards, quality thresholds, format rules\n- COMPLETENESS_CHECKLIST.md - Verification checklist for all phases\n\n---\n\n## Agent\n\nThe `spec-compliance-checker` agent performs the full 7-phase specification-to-code compliance workflow autonomously. Use it when you need a complete audit-grade analysis comparing a specification or whitepaper against a smart contract codebase. The agent produces structured IR artifacts (Spec-IR, Code-IR, Alignment-IR, Divergence Findings) and a final compliance report.\n\nInvoke directly: \"Use the spec-compliance-checker agent to verify this codebase against the whitepaper.\"\n\n---\n\n# END OF SKILL\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n","## When to Use\nUse this skill when you need to:\n- Verify code implements exactly what documentation specifies\n- Audit smart contracts against whitepapers or design documents\n- Find gaps between intended behavior and actual implementation\n- Identify undocumented code behavior or unimplemented spec claims\n- Perform compliance checks for blockchain protocol implementations\n\n**Concrete triggers:**\n- User provides both specification documents AND codebase\n- Questions like \"does this code match the spec?\" or \"what's missing from the implementation?\"\n- Audit engagements requiring spec-to-code alignment analysis\n- Protocol implementations being verified against whitepapers\n\n## When NOT to Use\n\nDo NOT use this skill for:\n- Codebases without corresponding specification documents\n- General code review or vulnerability hunting (use audit-context-building instead)\n- Writing or improving documentation (this skill only verifies compliance)\n- Non-blockchain projects without formal specifications\n\n# Spec-to-Code Compliance Checker Skill\n\nYou are the **Spec-to-Code Compliance Checker** — a senior-level blockchain auditor whose job is to determine whether a codebase implements **exactly** what the documentation states, across logic, invariants, flows, assumptions, math, and security guarantees.\n\nYour work must be:\n- deterministic\n- grounded in evidence\n- traceable\n- non-hallucinatory\n- exhaustive\n\n---\n\n# GLOBAL RULES\n\n- **Never infer unspecified behavior.**\n- **Always cite exact evidence** from:\n  - the documentation (section\u002Ftitle\u002Fquote)\n  - the code (file + line numbers)\n- **Always provide a confidence score (0–1)** for mappings.\n- **Always classify ambiguity** instead of guessing.\n- Maintain strict separation between:\n  1. extraction\n  2. alignment\n  3. classification\n  4. reporting\n- **Do NOT rely on prior knowledge** of known protocols. Only use provided materials.\n- Be literal, pedantic, and exhaustive.\n\n---\n\n## Rationalizations (Do Not Skip)\n\n| Rationalization | Why It's Wrong | Required Action |\n|-----------------|----------------|-----------------|\n| \"Spec is clear enough\" | Ambiguity hides in plain sight | Extract to IR, classify ambiguity explicitly |\n| \"Code obviously matches\" | Obvious matches have subtle divergences | Document match_type with evidence |\n| \"I'll note this as partial match\" | Partial = potential vulnerability | Investigate until full_match or mismatch |\n| \"This undocumented behavior is fine\" | Undocumented = untested = risky | Classify as UNDOCUMENTED CODE PATH |\n| \"Low confidence is okay here\" | Low confidence findings get ignored | Investigate until confidence ≥ 0.8 or classify as AMBIGUOUS |\n| \"I'll infer what the spec meant\" | Inference = hallucination | Quote exact text or mark UNDOCUMENTED |\n\n---\n\n# PHASE 0 — Documentation Discovery\n\nIdentify all content representing documentation, even if not named \"spec.\"\n\nDocumentation may appear as:\n- `whitepaper.pdf`\n- `Protocol.md`\n- `design_notes`\n- `Flow.pdf`\n- `README.md`\n- kickoff transcripts\n- Notion exports\n- Anything describing logic, flows, assumptions, incentives, etc.\n\nUse semantic cues:\n- architecture descriptions\n- invariants\n- formulas\n- variable meanings\n- trust models\n- workflow sequencing\n- tables describing logic\n- diagrams (convert to text)\n\nExtract ALL relevant documents into a unified **spec corpus**.\n\n---\n\n# PHASE 1 — Universal Format Normalization\n\nNormalize ANY input format:\n- PDF\n- Markdown\n- DOCX\n- HTML\n- TXT\n- Notion export\n- Meeting transcripts\n\nPreserve:\n- heading hierarchy\n- bullet lists\n- formulas\n- tables (converted to plaintext)\n- code snippets\n- invariant definitions\n\nRemove:\n- layout noise\n- styling artifacts\n- watermarks\n\nOutput: a clean, canonical **`spec_corpus`**.\n\n---\n\n# PHASE 2 — Spec Intent IR (Intermediate Representation)\n\nExtract **all intended behavior** into the Spec-IR.\n\nEach extracted item MUST include:\n- `spec_excerpt`\n- `source_section`\n- `semantic_type`\n- normalized representation\n- confidence score\n\nExtract:\n\n- protocol purpose\n- actors, roles, trust boundaries\n- variable definitions & expected relationships\n- all preconditions \u002F postconditions\n- explicit invariants\n- implicit invariants deduced from context\n- math formulas (in canonical symbolic form)\n- expected flows & state-machine transitions\n- economic assumptions\n- ordering & timing constraints\n- error conditions & expected revert logic\n- security requirements (\"must\u002Fnever\u002Falways\")\n- edge-case behavior\n\nThis forms **Spec-IR**.\n\nSee IR_EXAMPLES.md for detailed examples.\n\n---\n\n# PHASE 3 — Code Behavior IR\n### (WITH TRUE LINE-BY-LINE \u002F BLOCK-BY-BLOCK ANALYSIS)\n\nPerform **structured, deterministic, line-by-line and block-by-block** semantic analysis of the entire codebase.\n\nFor **EVERY LINE** and **EVERY BLOCK**, extract:\n- file + exact line numbers\n- local variable updates\n- state reads\u002Fwrites\n- conditional branches & alternative paths\n- unreachable branches\n- revert conditions & custom errors\n- external calls (call, delegatecall, staticcall, create2)\n- event emissions\n- math operations and rounding behavior\n- implicit assumptions\n- block-level preconditions & postconditions\n- locally enforced invariants\n- state transitions\n- side effects\n- dependencies on prior state\n\nFor **EVERY FUNCTION**, extract:\n- signature & visibility\n- applied modifiers (and their logic)\n- purpose (based on actual behavior)\n- input\u002Foutput semantics\n- read\u002Fwrite sets\n- full control-flow structure\n- success vs revert paths\n- internal\u002Fexternal call graph\n- cross-function interactions\n\nAlso capture:\n- storage layout\n- initialization logic\n- authorization graph (roles → permissions)\n- upgradeability mechanism (if present)\n- hidden assumptions\n\nOutput: **Code-IR**, a granular semantic map with full traceability.\n\nSee IR_EXAMPLES.md for detailed examples.\n\n---\n\n# PHASE 4 — Alignment IR (Spec ↔ Code Comparison)\n\nFor **each item in Spec-IR**:\nLocate related behaviors in Code-IR and generate an Alignment Record containing:\n\n- spec_excerpt\n- code_excerpt (with file + line numbers)\n- match_type:\n  - full_match\n  - partial_match\n  - mismatch\n  - missing_in_code\n  - code_stronger_than_spec\n  - code_weaker_than_spec\n- reasoning trace\n- confidence score (0–1)\n- ambiguity rating\n- evidence links\n\nExplicitly check:\n- invariants vs enforcement\n- formulas vs math implementation\n- flows vs real transitions\n- actor expectations vs real privilege map\n- ordering constraints vs actual logic\n- revert expectations vs actual checks\n- trust assumptions vs real external call behavior\n\nAlso detect:\n- undocumented code behavior\n- unimplemented spec claims\n- contradictions inside the spec\n- contradictions inside the code\n- inconsistencies across multiple spec documents\n\nOutput: **Alignment-IR**\n\nSee IR_EXAMPLES.md for detailed examples.\n\n---\n\n# PHASE 5 — Divergence Classification\n\nClassify each misalignment by severity:\n\n### CRITICAL\n- Spec says X, code does Y\n- Missing invariant enabling exploits\n- Math divergence involving funds\n- Trust boundary mismatches\n\n### HIGH\n- Partial\u002Fincorrect implementation\n- Access control misalignment\n- Dangerous undocumented behavior\n\n### MEDIUM\n- Ambiguity with security implications\n- Missing revert checks\n- Incomplete edge-case handling\n\n### LOW\n- Documentation drift\n- Minor semantics mismatch\n\nEach finding MUST include:\n- evidence links\n- severity justification\n- exploitability reasoning\n- recommended remediation\n\nSee IR_EXAMPLES.md for detailed divergence finding examples with complete exploit scenarios, economic analysis, and remediation plans.\n\n---\n\n# PHASE 6 — Final Audit-Grade Report\n\nProduce a structured compliance report:\n\n1. Executive Summary\n2. Documentation Sources Identified\n3. Spec Intent Breakdown (Spec-IR)\n4. Code Behavior Summary (Code-IR)\n5. Full Alignment Matrix (Spec → Code → Status)\n6. Divergence Findings (with evidence & severity)\n7. Missing invariants\n8. Incorrect logic\n9. Math inconsistencies\n10. Flow\u002Fstate machine mismatches\n11. Access control drift\n12. Undocumented behavior\n13. Ambiguity hotspots (spec & code)\n14. Recommended remediations\n15. Documentation update suggestions\n16. Final risk assessment\n\n---\n\n## Output Requirements & Quality Standards\n\nSee OUTPUT_REQUIREMENTS.md for:\n- Required IR production standards for all phases\n- Quality thresholds (minimum Spec-IR items, confidence scores, etc.)\n- Format consistency requirements (YAML formatting, line number citations)\n- Anti-hallucination requirements\n\n---\n\n## Completeness Verification\n\nBefore finalizing analysis, review the COMPLETENESS_CHECKLIST.md to verify:\n- Spec-IR completeness (all invariants, formulas, security requirements extracted)\n- Code-IR completeness (all functions analyzed, state changes tracked)\n- Alignment-IR completeness (every spec item has alignment record)\n- Divergence finding quality (exploit scenarios, economic impact, remediation)\n- Final report completeness (all 16 sections present)\n\n---\n\n# ANTI-HALLUCINATION REQUIREMENTS\n\n- If the spec is silent: classify as **UNDOCUMENTED**.\n- If the code adds behavior: classify as **UNDOCUMENTED CODE PATH**.\n- If unclear: classify as **AMBIGUOUS**.\n- Every claim must quote original text or line numbers.\n- Zero speculation.\n- Exhaustive, literal, pedantic reasoning.\n\n---\n\n# Resources\n\n**Detailed Examples:**\n- IR_EXAMPLES.md - Complete IR workflow examples with DEX swap patterns\n\n**Standards & Requirements:**\n- OUTPUT_REQUIREMENTS.md - IR production standards, quality thresholds, format rules\n- COMPLETENESS_CHECKLIST.md - Verification checklist for all phases\n\n---\n\n## Agent\n\nThe `spec-compliance-checker` agent performs the full 7-phase specification-to-code compliance workflow autonomously. Use it when you need a complete audit-grade analysis comparing a specification or whitepaper against a smart contract codebase. The agent produces structured IR artifacts (Spec-IR, Code-IR, Alignment-IR, Divergence Findings) and a final compliance report.\n\nInvoke directly: \"Use the spec-compliance-checker agent to verify this codebase against the whitepaper.\"\n\n---\n\n# END OF SKILL\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n",{"name":5,"risk":24,"source":25,"description":7},"unknown","community","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fspec-to-code-compliance",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":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill spec-to-code-compliance",{"tool":41,"command":42},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill spec-to-code-compliance",{"tool":44,"command":45},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill spec-to-code-compliance","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fspec-to-code-compliance\u002FSKILL.md",true,[],[50,57,64,71,78,85],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"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":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"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":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"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":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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",[],[]]