[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BYMVVHBHESQPW10XS7SSEN":3,"skill-same:01M7BYMVVHBHESQPW10XS7SSEN":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},"01M7BYMVVHBHESQPW10XS7SSEN","audit-context-building",null,"Enables ultra-granular, line-by-line code analysis to build deep architectural context before vulnerability or bug finding.","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-claude\u002Fskills\u002Faudit-context-building\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: audit-context-building\ndescription: Enables ultra-granular, line-by-line code analysis to build deep architectural context before vulnerability or bug finding.\nrisk: unknown\nsource: community\n---\n\n# Deep Context Builder Skill (Ultra-Granular Pure Context Mode)\n\n## 1. Purpose\n\nThis skill governs **how Claude thinks** during the context-building phase of an audit.\n\nWhen active, Claude will:\n- Perform **line-by-line \u002F block-by-block** code analysis by default.\n- Apply **First Principles**, **5 Whys**, and **5 Hows** at micro scale.\n- Continuously link insights → functions → modules → entire system.\n- Maintain a stable, explicit mental model that evolves with new evidence.\n- Identify invariants, assumptions, flows, and reasoning hazards.\n\nThis skill defines a structured analysis format (see Example: Function Micro-Analysis below) and runs **before** the vulnerability-hunting phase.\n\n---\n\n## When to Use\nUse when:\n- Deep comprehension is needed before bug or vulnerability discovery.\n- You want bottom-up understanding instead of high-level guessing.\n- Reducing hallucinations, contradictions, and context loss is critical.\n- Preparing for security auditing, architecture review, or threat modeling.\n\nDo **not** use for:\n- Vulnerability findings\n- Fix recommendations\n- Exploit reasoning\n- Severity\u002Fimpact rating\n\n---\n\n## 3. How This Skill Behaves\n\nWhen active, Claude will:\n- Default to **ultra-granular analysis** of each block and line.\n- Apply micro-level First Principles, 5 Whys, and 5 Hows.\n- Build and refine a persistent global mental model.\n- Update earlier assumptions when contradicted (\"Earlier I thought X; now Y.\").\n- Periodically anchor summaries to maintain stable context.\n- Avoid speculation; express uncertainty explicitly when needed.\n\nGoal: **deep, accurate understanding**, not conclusions.\n\n---\n\n## Rationalizations (Do Not Skip)\n\n| Rationalization | Why It's Wrong | Required Action |\n|-----------------|----------------|-----------------|\n| \"I get the gist\" | Gist-level understanding misses edge cases | Line-by-line analysis required |\n| \"This function is simple\" | Simple functions compose into complex bugs | Apply 5 Whys anyway |\n| \"I'll remember this invariant\" | You won't. Context degrades. | Write it down explicitly |\n| \"External call is probably fine\" | External = adversarial until proven otherwise | Jump into code or model as hostile |\n| \"I can skip this helper\" | Helpers contain assumptions that propagate | Trace the full call chain |\n| \"This is taking too long\" | Rushed context = hallucinated vulnerabilities later | Slow is fast |\n\n---\n\n## 4. Phase 1 — Initial Orientation (Bottom-Up Scan)\n\nBefore deep analysis, Claude performs a minimal mapping:\n\n1. Identify major modules\u002Ffiles\u002Fcontracts.\n2. Note obvious public\u002Fexternal entrypoints.\n3. Identify likely actors (users, owners, relayers, oracles, other contracts).\n4. Identify important storage variables, dicts, state structs, or cells.\n5. Build a preliminary structure without assuming behavior.\n\nThis establishes anchors for detailed analysis.\n\n---\n\n## 5. Phase 2 — Ultra-Granular Function Analysis (Default Mode)\n\nEvery non-trivial function receives full micro analysis.\n\n### 5.1 Per-Function Microstructure Checklist\n\nFor each function:\n\n1. **Purpose**\n   - Why the function exists and its role in the system.\n\n2. **Inputs & Assumptions**\n   - Parameters and implicit inputs (state, sender, env).\n   - Preconditions and constraints.\n\n3. **Outputs & Effects**\n   - Return values.\n   - State\u002Fstorage writes.\n   - Events\u002Fmessages.\n   - External interactions.\n\n4. **Block-by-Block \u002F Line-by-Line Analysis**\n   For each logical block:\n   - What it does.\n   - Why it appears here (ordering logic).\n   - What assumptions it relies on.\n   - What invariants it establishes or maintains.\n   - What later logic depends on it.\n\n   Apply per-block:\n   - **First Principles**\n   - **5 Whys**\n   - **5 Hows**\n\n---\n\n### 5.2 Cross-Function & External Flow Analysis\n*(Full Integration of Jump-Into-External-Code Rule)*\n\nWhen encountering calls, **continue the same micro-first analysis across boundaries.**\n\n#### Internal Calls\n- Jump into the callee immediately.\n- Perform block-by-block analysis of relevant code.\n- Track flow of data, assumptions, and invariants:\n  caller → callee → return → caller.\n- Note if callee logic behaves differently in this specific call context.\n\n#### External Calls — Two Cases\n\n**Case A — External Call to a Contract Whose Code Exists in the Codebase**\nTreat as an internal call:\n- Jump into the target contract\u002Ffunction.\n- Continue block-by-block micro-analysis.\n- Propagate invariants and assumptions seamlessly.\n- Consider edge cases based on the *actual* code, not a black-box guess.\n\n**Case B — External Call Without Available Code (True External \u002F Black Box)**\nAnalyze as adversarial:\n- Describe payload\u002Fvalue\u002Fgas or parameters sent.\n- Identify assumptions about the target.\n- Consider all outcomes:\n  - revert\n  - incorrect\u002Fstrange return values\n  - unexpected state changes\n  - misbehavior\n  - reentrancy (if applicable)\n\n#### Continuity Rule\nTreat the entire call chain as **one continuous execution flow**.\nNever reset context.\nAll invariants, assumptions, and data dependencies must propagate across calls.\n\n---\n\n### 5.3 Complete Analysis Example\n\nSee FUNCTION_MICRO_ANALYSIS_EXAMPLE.md for a complete walkthrough demonstrating:\n- Full micro-analysis of a DEX swap function\n- Application of First Principles, 5 Whys, and 5 Hows\n- Block-by-block analysis with invariants and assumptions\n- Cross-function dependency mapping\n- Risk analysis for external interactions\n\nThis example demonstrates the level of depth and structure required for all analyzed functions.\n\n---\n\n### 5.4 Output Requirements\n\nWhen performing ultra-granular analysis, Claude MUST structure output following the format defined in OUTPUT_REQUIREMENTS.md.\n\nKey requirements:\n- **Purpose** (2-3 sentences minimum)\n- **Inputs & Assumptions** (all parameters, preconditions, trust assumptions)\n- **Outputs & Effects** (returns, state writes, external calls, events, postconditions)\n- **Block-by-Block Analysis** (What, Why here, Assumptions, First Principles\u002F5 Whys\u002F5 Hows)\n- **Cross-Function Dependencies** (internal calls, external calls with risk analysis, shared state)\n\nQuality thresholds:\n- Minimum 3 invariants per function\n- Minimum 5 assumptions documented\n- Minimum 3 risk considerations for external interactions\n- At least 1 First Principles application\n- At least 3 combined 5 Whys\u002F5 Hows applications\n\n---\n\n### 5.5 Completeness Checklist\n\nBefore concluding micro-analysis of a function, verify against the COMPLETENESS_CHECKLIST.md:\n\n- **Structural Completeness**: All required sections present (Purpose, Inputs, Outputs, Block-by-Block, Dependencies)\n- **Content Depth**: Minimum thresholds met (invariants, assumptions, risk analysis, First Principles)\n- **Continuity & Integration**: Cross-references, propagated assumptions, invariant couplings\n- **Anti-Hallucination**: Line number citations, no vague statements, evidence-based claims\n\nAnalysis is complete when all checklist items are satisfied and no unresolved \"unclear\" items remain.\n\n---\n\n## 6. Phase 3 — Global System Understanding\n\nAfter sufficient micro-analysis:\n\n1. **State & Invariant Reconstruction**\n   - Map reads\u002Fwrites of each state variable.\n   - Derive multi-function and multi-module invariants.\n\n2. **Workflow Reconstruction**\n   - Identify end-to-end flows (deposit, withdraw, lifecycle, upgrades).\n   - Track how state transforms across these flows.\n   - Record assumptions that persist across steps.\n\n3. **Trust Boundary Mapping**\n   - Actor → entrypoint → behavior.\n   - Identify untrusted input paths.\n   - Privilege changes and implicit role expectations.\n\n4. **Complexity & Fragility Clustering**\n   - Functions with many assumptions.\n   - High branching logic.\n   - Multi-step dependencies.\n   - Coupled state changes across modules.\n\nThese clusters help guide the vulnerability-hunting phase.\n\n---\n\n## 7. Stability & Consistency Rules\n*(Anti-Hallucination, Anti-Contradiction)*\n\nClaude must:\n\n- **Never reshape evidence to fit earlier assumptions.**\n  When contradicted:\n  - Update the model.\n  - State the correction explicitly.\n\n- **Periodically anchor key facts**\n  Summarize core:\n  - invariants\n  - state relationships\n  - actor roles\n  - workflows\n\n- **Avoid vague guesses**\n  Use:\n  - \"Unclear; need to inspect X.\"\n  instead of:\n  - \"It probably…\"\n\n- **Cross-reference constantly**\n  Connect new insights to previous state, flows, and invariants to maintain global coherence.\n\n---\n\n## 8. Subagent Usage\n\nClaude may spawn subagents for:\n- Dense or complex functions.\n- Long data-flow or control-flow chains.\n- Cryptographic \u002F mathematical logic.\n- Complex state machines.\n- Multi-module workflow reconstruction.\n\nUse the **`function-analyzer`** agent for per-function deep analysis.\nIt follows the full microstructure checklist, cross-function flow\nrules, and quality thresholds defined in this skill, and enforces\nthe pure-context-building constraint.\n\nSubagents must:\n- Follow the same micro-first rules.\n- Return summaries that Claude integrates into its global model.\n\n---\n\n## 9. Relationship to Other Phases\n\nThis skill runs **before**:\n- Vulnerability discovery\n- Classification \u002F triage\n- Report writing\n- Impact modeling\n- Exploit reasoning\n\nIt exists solely to build:\n- Deep understanding\n- Stable context\n- System-level clarity\n\n---\n\n## 10. Non-Goals\n\nWhile active, Claude should NOT:\n- Identify vulnerabilities\n- Propose fixes\n- Generate proofs-of-concept\n- Model exploits\n- Assign severity or impact\n\nThis is **pure context building** only.\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","# Deep Context Builder Skill (Ultra-Granular Pure Context Mode)\n\n## 1. Purpose\n\nThis skill governs **how Claude thinks** during the context-building phase of an audit.\n\nWhen active, Claude will:\n- Perform **line-by-line \u002F block-by-block** code analysis by default.\n- Apply **First Principles**, **5 Whys**, and **5 Hows** at micro scale.\n- Continuously link insights → functions → modules → entire system.\n- Maintain a stable, explicit mental model that evolves with new evidence.\n- Identify invariants, assumptions, flows, and reasoning hazards.\n\nThis skill defines a structured analysis format (see Example: Function Micro-Analysis below) and runs **before** the vulnerability-hunting phase.\n\n---\n\n## When to Use\nUse when:\n- Deep comprehension is needed before bug or vulnerability discovery.\n- You want bottom-up understanding instead of high-level guessing.\n- Reducing hallucinations, contradictions, and context loss is critical.\n- Preparing for security auditing, architecture review, or threat modeling.\n\nDo **not** use for:\n- Vulnerability findings\n- Fix recommendations\n- Exploit reasoning\n- Severity\u002Fimpact rating\n\n---\n\n## 3. How This Skill Behaves\n\nWhen active, Claude will:\n- Default to **ultra-granular analysis** of each block and line.\n- Apply micro-level First Principles, 5 Whys, and 5 Hows.\n- Build and refine a persistent global mental model.\n- Update earlier assumptions when contradicted (\"Earlier I thought X; now Y.\").\n- Periodically anchor summaries to maintain stable context.\n- Avoid speculation; express uncertainty explicitly when needed.\n\nGoal: **deep, accurate understanding**, not conclusions.\n\n---\n\n## Rationalizations (Do Not Skip)\n\n| Rationalization | Why It's Wrong | Required Action |\n|-----------------|----------------|-----------------|\n| \"I get the gist\" | Gist-level understanding misses edge cases | Line-by-line analysis required |\n| \"This function is simple\" | Simple functions compose into complex bugs | Apply 5 Whys anyway |\n| \"I'll remember this invariant\" | You won't. Context degrades. | Write it down explicitly |\n| \"External call is probably fine\" | External = adversarial until proven otherwise | Jump into code or model as hostile |\n| \"I can skip this helper\" | Helpers contain assumptions that propagate | Trace the full call chain |\n| \"This is taking too long\" | Rushed context = hallucinated vulnerabilities later | Slow is fast |\n\n---\n\n## 4. Phase 1 — Initial Orientation (Bottom-Up Scan)\n\nBefore deep analysis, Claude performs a minimal mapping:\n\n1. Identify major modules\u002Ffiles\u002Fcontracts.\n2. Note obvious public\u002Fexternal entrypoints.\n3. Identify likely actors (users, owners, relayers, oracles, other contracts).\n4. Identify important storage variables, dicts, state structs, or cells.\n5. Build a preliminary structure without assuming behavior.\n\nThis establishes anchors for detailed analysis.\n\n---\n\n## 5. Phase 2 — Ultra-Granular Function Analysis (Default Mode)\n\nEvery non-trivial function receives full micro analysis.\n\n### 5.1 Per-Function Microstructure Checklist\n\nFor each function:\n\n1. **Purpose**\n   - Why the function exists and its role in the system.\n\n2. **Inputs & Assumptions**\n   - Parameters and implicit inputs (state, sender, env).\n   - Preconditions and constraints.\n\n3. **Outputs & Effects**\n   - Return values.\n   - State\u002Fstorage writes.\n   - Events\u002Fmessages.\n   - External interactions.\n\n4. **Block-by-Block \u002F Line-by-Line Analysis**\n   For each logical block:\n   - What it does.\n   - Why it appears here (ordering logic).\n   - What assumptions it relies on.\n   - What invariants it establishes or maintains.\n   - What later logic depends on it.\n\n   Apply per-block:\n   - **First Principles**\n   - **5 Whys**\n   - **5 Hows**\n\n---\n\n### 5.2 Cross-Function & External Flow Analysis\n*(Full Integration of Jump-Into-External-Code Rule)*\n\nWhen encountering calls, **continue the same micro-first analysis across boundaries.**\n\n#### Internal Calls\n- Jump into the callee immediately.\n- Perform block-by-block analysis of relevant code.\n- Track flow of data, assumptions, and invariants:\n  caller → callee → return → caller.\n- Note if callee logic behaves differently in this specific call context.\n\n#### External Calls — Two Cases\n\n**Case A — External Call to a Contract Whose Code Exists in the Codebase**\nTreat as an internal call:\n- Jump into the target contract\u002Ffunction.\n- Continue block-by-block micro-analysis.\n- Propagate invariants and assumptions seamlessly.\n- Consider edge cases based on the *actual* code, not a black-box guess.\n\n**Case B — External Call Without Available Code (True External \u002F Black Box)**\nAnalyze as adversarial:\n- Describe payload\u002Fvalue\u002Fgas or parameters sent.\n- Identify assumptions about the target.\n- Consider all outcomes:\n  - revert\n  - incorrect\u002Fstrange return values\n  - unexpected state changes\n  - misbehavior\n  - reentrancy (if applicable)\n\n#### Continuity Rule\nTreat the entire call chain as **one continuous execution flow**.\nNever reset context.\nAll invariants, assumptions, and data dependencies must propagate across calls.\n\n---\n\n### 5.3 Complete Analysis Example\n\nSee FUNCTION_MICRO_ANALYSIS_EXAMPLE.md for a complete walkthrough demonstrating:\n- Full micro-analysis of a DEX swap function\n- Application of First Principles, 5 Whys, and 5 Hows\n- Block-by-block analysis with invariants and assumptions\n- Cross-function dependency mapping\n- Risk analysis for external interactions\n\nThis example demonstrates the level of depth and structure required for all analyzed functions.\n\n---\n\n### 5.4 Output Requirements\n\nWhen performing ultra-granular analysis, Claude MUST structure output following the format defined in OUTPUT_REQUIREMENTS.md.\n\nKey requirements:\n- **Purpose** (2-3 sentences minimum)\n- **Inputs & Assumptions** (all parameters, preconditions, trust assumptions)\n- **Outputs & Effects** (returns, state writes, external calls, events, postconditions)\n- **Block-by-Block Analysis** (What, Why here, Assumptions, First Principles\u002F5 Whys\u002F5 Hows)\n- **Cross-Function Dependencies** (internal calls, external calls with risk analysis, shared state)\n\nQuality thresholds:\n- Minimum 3 invariants per function\n- Minimum 5 assumptions documented\n- Minimum 3 risk considerations for external interactions\n- At least 1 First Principles application\n- At least 3 combined 5 Whys\u002F5 Hows applications\n\n---\n\n### 5.5 Completeness Checklist\n\nBefore concluding micro-analysis of a function, verify against the COMPLETENESS_CHECKLIST.md:\n\n- **Structural Completeness**: All required sections present (Purpose, Inputs, Outputs, Block-by-Block, Dependencies)\n- **Content Depth**: Minimum thresholds met (invariants, assumptions, risk analysis, First Principles)\n- **Continuity & Integration**: Cross-references, propagated assumptions, invariant couplings\n- **Anti-Hallucination**: Line number citations, no vague statements, evidence-based claims\n\nAnalysis is complete when all checklist items are satisfied and no unresolved \"unclear\" items remain.\n\n---\n\n## 6. Phase 3 — Global System Understanding\n\nAfter sufficient micro-analysis:\n\n1. **State & Invariant Reconstruction**\n   - Map reads\u002Fwrites of each state variable.\n   - Derive multi-function and multi-module invariants.\n\n2. **Workflow Reconstruction**\n   - Identify end-to-end flows (deposit, withdraw, lifecycle, upgrades).\n   - Track how state transforms across these flows.\n   - Record assumptions that persist across steps.\n\n3. **Trust Boundary Mapping**\n   - Actor → entrypoint → behavior.\n   - Identify untrusted input paths.\n   - Privilege changes and implicit role expectations.\n\n4. **Complexity & Fragility Clustering**\n   - Functions with many assumptions.\n   - High branching logic.\n   - Multi-step dependencies.\n   - Coupled state changes across modules.\n\nThese clusters help guide the vulnerability-hunting phase.\n\n---\n\n## 7. Stability & Consistency Rules\n*(Anti-Hallucination, Anti-Contradiction)*\n\nClaude must:\n\n- **Never reshape evidence to fit earlier assumptions.**\n  When contradicted:\n  - Update the model.\n  - State the correction explicitly.\n\n- **Periodically anchor key facts**\n  Summarize core:\n  - invariants\n  - state relationships\n  - actor roles\n  - workflows\n\n- **Avoid vague guesses**\n  Use:\n  - \"Unclear; need to inspect X.\"\n  instead of:\n  - \"It probably…\"\n\n- **Cross-reference constantly**\n  Connect new insights to previous state, flows, and invariants to maintain global coherence.\n\n---\n\n## 8. Subagent Usage\n\nClaude may spawn subagents for:\n- Dense or complex functions.\n- Long data-flow or control-flow chains.\n- Cryptographic \u002F mathematical logic.\n- Complex state machines.\n- Multi-module workflow reconstruction.\n\nUse the **`function-analyzer`** agent for per-function deep analysis.\nIt follows the full microstructure checklist, cross-function flow\nrules, and quality thresholds defined in this skill, and enforces\nthe pure-context-building constraint.\n\nSubagents must:\n- Follow the same micro-first rules.\n- Return summaries that Claude integrates into its global model.\n\n---\n\n## 9. Relationship to Other Phases\n\nThis skill runs **before**:\n- Vulnerability discovery\n- Classification \u002F triage\n- Report writing\n- Impact modeling\n- Exploit reasoning\n\nIt exists solely to build:\n- Deep understanding\n- Stable context\n- System-level clarity\n\n---\n\n## 10. Non-Goals\n\nWhile active, Claude should NOT:\n- Identify vulnerabilities\n- Propose fixes\n- Generate proofs-of-concept\n- Model exploits\n- Assign severity or impact\n\nThis is **pure context building** only.\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-claude\u002Fskills\u002Faudit-context-building",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 audit-context-building",{"tool":41,"command":42},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill audit-context-building",{"tool":44,"command":45},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill audit-context-building","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-claude\u002Fskills\u002Faudit-context-building\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",[],[]]