[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-anthropics-mcp-integration-zh-CN":3,"guides-for-anthropics-mcp-integration":718,"similar-k17396ckc9fxz5v38nvjc1v18d86m9ta-zh-CN":719},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":245,"isFallback":242,"parentExtension":250,"providers":313,"relations":317,"repo":318,"tags":716,"workflow":717},1778675383815.6492,"k17396ckc9fxz5v38nvjc1v18d86m9ta",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"This skill should be used when the user asks to \"add MCP server\", \"integrate MCP\", \"configure MCP in plugin\", \"use .mcp.json\", \"set up Model Context Protocol\", \"connect external service\", mentions \"${CLAUDE_PLUGIN_ROOT} with MCP\", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.",{"claudeCode":12},"anthropics/claude-code","mcp-integration","https://github.com/anthropics/claude-code",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":226,"workflow":243},1778675785808.1084,"kn7evpm7fyzc1s99gd5dbajt0586n98h","en",{"checks":20,"evaluatedAt":193,"extensionSummary":194,"features":195,"nonGoals":201,"promptVersionExtension":205,"promptVersionScoring":206,"purpose":207,"rationale":208,"score":209,"summary":210,"tags":211,"targetMarket":219,"tier":220,"useCases":221},[21,26,29,32,36,39,44,48,51,54,59,63,66,70,73,76,79,82,85,88,92,96,100,104,108,111,115,118,122,125,128,131,134,137,140,144,148,151,154,158,161,164,167,170,174,177,180,183,186,190],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of integrating Model Context Protocol (MCP) servers into Claude Code plugins for external service integration, referencing specific user requests and keywords.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill provides comprehensive guidance on configuring and using various MCP server types (stdio, SSE, HTTP, WebSocket) and authentication methods, which goes beyond basic LLM capabilities and offers significant value over simple prompting.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill covers the complete lifecycle of MCP integration, including configuration, server types, authentication, tool usage, testing, and debugging, making it ready for use in production workflows.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses exclusively on the integration of Model Context Protocol (MCP) servers within Claude Code plugins, covering its configuration, types, and usage without straying into unrelated domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The provided description accurately reflects the skill's purpose and capabilities, detailing how to integrate MCP servers into Claude Code plugins and covering various server types and configuration methods.",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","This skill itself does not expose tools directly but guides the user on how to configure and use tools provided by MCP servers. Therefore, the check for scoped tools is not applicable.",{"category":45,"check":46,"severity":24,"summary":47},"Documentation","Configuration & parameter reference","The documentation provides comprehensive details on MCP server configuration methods, types, environment variable expansion, tool naming conventions, and authentication patterns, including examples and best practices.",{"category":33,"check":49,"severity":42,"summary":50},"Tool naming","This skill does not define its own tools; it explains how to use tools provided by MCP servers, which have a distinct naming convention described within the documentation.",{"category":33,"check":52,"severity":42,"summary":53},"Minimal I/O surface","As a documentation and guidance skill, it does not expose tools with input/output schemas in the traditional sense.",{"category":55,"check":56,"severity":57,"summary":58},"License","License usability","warning","The LICENSE.md file contains '© Anthropic PBC. All rights reserved. Use is subject to Anthropic's [Commercial Terms of Service]', which is not a standard SPDX license and may impose non-permissive restrictions.",{"category":60,"check":61,"severity":24,"summary":62},"Maintenance","Commit recency","The repository was last updated on 2026-05-12, which is within the last 3 months.",{"category":60,"check":64,"severity":42,"summary":65},"Dependency Management","The skill itself does not appear to have third-party dependencies that require specific management beyond what is documented for the MCP servers it describes.",{"category":67,"check":68,"severity":24,"summary":69},"Security","Secret Management","The documentation strongly emphasizes using environment variables and secure methods for secrets and advises against hardcoding tokens or committing them, aligning with good secret management practices.",{"category":67,"check":71,"severity":24,"summary":72},"Injection","The skill provides guidance on secure integration, emphasizing treating external data as untrusted and securing MCP tool usage, implying adherence to safe data handling practices.",{"category":67,"check":74,"severity":24,"summary":75},"Transitive Supply-Chain Grenades","The skill focuses on configuration and best practices for MCP integration, and its documentation does not indicate any runtime fetching of external code or data that could introduce supply-chain risks.",{"category":67,"check":77,"severity":24,"summary":78},"Sandbox Isolation","The skill's focus is on configuration and guidance, not execution within the sandbox. It advises on secure practices for the MCP servers it describes, which indirectly supports sandbox isolation.",{"category":67,"check":80,"severity":24,"summary":81},"Sandbox escape primitives","As this skill primarily provides documentation and configuration guidance, it does not contain executable scripts or hooks that would present sandbox escape primitives.",{"category":67,"check":83,"severity":24,"summary":84},"Data Exfiltration","The skill's documentation promotes secure practices, including using environment variables for tokens and avoiding hardcoded credentials, which helps prevent data exfiltration.",{"category":67,"check":86,"severity":24,"summary":87},"Hidden Text Tricks","The bundled markdown files appear to be free of hidden steering tricks or obfuscated content.",{"category":89,"check":90,"severity":24,"summary":91},"Hooks","Opaque code execution","This skill consists of markdown documentation and does not involve any opaque code execution or obfuscated scripts.",{"category":93,"check":94,"severity":24,"summary":95},"Portability","Structural Assumption","The documentation correctly advises using `${CLAUDE_PLUGIN_ROOT}` for file paths, promoting portability and avoiding assumptions about user-specific project structures.",{"category":97,"check":98,"severity":57,"summary":99},"Trust","Issues Attention","In the last 90 days, 9462 issues were opened and 22831 were closed. The closure rate is approximately 71%, but the high volume of open issues suggests potential responsiveness concerns.",{"category":101,"check":102,"severity":24,"summary":103},"Versioning","Release Management","The skill frontmatter declares a `version: 0.1.0`, indicating a clear versioning signal.",{"category":105,"check":106,"severity":42,"summary":107},"Execution","Validation","This skill focuses on documentation and guidance for MCP integration, rather than executing code that requires input validation libraries.",{"category":67,"check":109,"severity":24,"summary":110},"Unguarded Destructive Operations","As a documentation skill, it does not perform any destructive operations.",{"category":112,"check":113,"severity":24,"summary":114},"Code Execution","Error Handling","The skill provides extensive guidance on error handling for MCP operations, including connection failures, tool call errors, and configuration errors, with actionable advice.",{"category":112,"check":116,"severity":42,"summary":117},"Logging","This skill is purely documentation and does not perform actions that would require local audit logging.",{"category":119,"check":120,"severity":42,"summary":121},"Compliance","GDPR","The skill's documentation does not indicate operations on personal data; it focuses on protocol configuration and integration.",{"category":119,"check":123,"severity":24,"summary":124},"Target market","The documentation for MCP integration is general and does not contain regional or jurisdictional logic, making it globally applicable.",{"category":93,"check":126,"severity":24,"summary":127},"Runtime stability","The skill focuses on configuration and guidance, using `${CLAUDE_PLUGIN_ROOT}` which promotes portability and avoids assumptions about specific runtimes or operating systems.",{"category":45,"check":129,"severity":24,"summary":130},"README","The README file provides a clear overview of Claude Code, installation instructions, and information about plugins and reporting bugs.",{"category":33,"check":132,"severity":42,"summary":133},"Tool surface size","This skill does not expose tools directly; it documents how to use MCP-provided tools.",{"category":40,"check":135,"severity":42,"summary":136},"Overlapping near-synonym tools","This skill does not define tools, so there are no overlapping near-synonym tools to evaluate.",{"category":45,"check":138,"severity":24,"summary":139},"Phantom features","All advertised capabilities within the skill's documentation, such as different MCP server types and authentication methods, have corresponding detailed explanations and configurations.",{"category":141,"check":142,"severity":24,"summary":143},"Install","Installation instruction","The README provides comprehensive installation instructions for Claude Code itself, and the SKILL.md details how to configure MCP servers within plugins, including `.mcp.json` examples.",{"category":145,"check":146,"severity":24,"summary":147},"Errors","Actionable error messages","The skill dedicates sections to 'Error Handling' and 'Troubleshooting' with detailed explanations of common issues and actionable remediation steps for MCP integration.",{"category":105,"check":149,"severity":42,"summary":150},"Pinned dependencies","This skill is documentation-based and does not bundle scripts with dependencies that require pinning.",{"category":33,"check":152,"severity":42,"summary":153},"Dry-run preview","This skill does not execute commands or send data outward, so a dry-run feature is not applicable.",{"category":155,"check":156,"severity":24,"summary":157},"Protocol","Idempotent retry & timeouts","The skill provides guidance on handling errors and suggests implementing retry logic, implicitly supporting idempotent operations and timeouts for MCP tool calls.",{"category":119,"check":159,"severity":42,"summary":160},"Telemetry opt-in","This skill is documentation-based and does not emit telemetry.",{"category":40,"check":162,"severity":24,"summary":163},"Precise Purpose","The skill's purpose is precisely defined, detailing when to use it (adding MCP servers, integration) and what it covers (guidance for Model Context Protocol servers), with specific keywords.",{"category":40,"check":165,"severity":24,"summary":166},"Concise Frontmatter","The frontmatter is concise, clearly stating the skill's name, version, and purpose with trigger phrases, adhering to density guidelines.",{"category":45,"check":168,"severity":24,"summary":169},"Concise Body","The SKILL.md body is well-structured and reasonably concise, delegating deeper material to `references/` files and examples, following progressive disclosure.",{"category":171,"check":172,"severity":24,"summary":173},"Context","Progressive Disclosure","The skill utilizes `references/` files for detailed information on server types, authentication, and tool usage, demonstrating effective progressive disclosure.",{"category":171,"check":175,"severity":42,"summary":176},"Forked exploration","This skill is documentation-based and does not involve deep exploration or code review that would necessitate `context: fork`.",{"category":22,"check":178,"severity":24,"summary":179},"Usage examples","The skill includes several detailed JSON examples for different MCP server configurations (stdio, SSE, HTTP) and demonstrates tool usage in command and agent contexts.",{"category":22,"check":181,"severity":24,"summary":182},"Edge cases","The skill addresses various failure modes, limitations, and debugging scenarios for MCP integration, providing recovery steps and troubleshooting guidance.",{"category":112,"check":184,"severity":24,"summary":185},"Tool Fallback","The skill documents how MCP servers are automatically started and mentions fallbacks implicitly through error handling guidance and the need for proper configuration, though explicit fallback mechanisms for MCP servers themselves are not detailed.",{"category":187,"check":188,"severity":24,"summary":189},"Safety","Halt on unexpected state","The skill emphasizes error handling and validation for MCP configurations and tool calls, implicitly guiding users to halt workflows on unexpected states and report errors.",{"category":93,"check":191,"severity":24,"summary":192},"Cross-skill coupling","The skill focuses solely on MCP integration and does not implicitly rely on other skills; it stands alone as a guide.",1778675785292,"This skill provides detailed documentation and examples for configuring and integrating various types of Model Context Protocol (MCP) servers within Claude Code plugins, covering stdio, SSE, HTTP, and WebSocket protocols, along with authentication methods and best practices.",[196,197,198,199,200],"Guidance on .mcp.json and plugin.json configuration","Detailed explanation of stdio, SSE, HTTP, and WebSocket MCP server types","Authentication patterns including OAuth, token-based, and environment variables","MCP tool naming conventions and usage in commands/agents","Best practices for security, error handling, and performance",[202,203,204],"Providing direct MCP server implementations","Handling the execution of MCP tools","Configuring Claude Code itself beyond plugin integration","3.0.0","4.4.0","To enable developers to seamlessly integrate external services and APIs into Claude Code plugins by providing comprehensive guidance on setting up and utilizing Model Context Protocol (MCP) servers.","The skill is well-documented, covers its scope comprehensively, and adheres to best practices for MCP integration. The license is a minor concern, and the high volume of issues on the main repository warrants a slight reduction in score.",90,"Comprehensive guidance for integrating Model Context Protocol (MCP) servers into Claude Code plugins.",[212,213,214,215,216,217,218],"mcp","protocol","integration","plugins","configuration","authentication","tools","global","community",[222,223,224,225],"Integrating external databases or APIs via MCP","Setting up custom MCP servers for plugins","Connecting to hosted cloud services using MCP","Configuring authentication for MCP server integrations",{"codeQuality":227,"collectedAt":229,"documentation":230,"maintenance":233,"security":240,"testCoverage":241},{"hasLockfile":228},false,1778675766679,{"descriptionLength":231,"readmeSize":232},438,2873,{"closedIssues90d":234,"forks":235,"hasChangelog":228,"manifestVersion":236,"openIssues90d":237,"pushedAt":238,"stars":239},22831,20310,"0.1.0",9462,1778620184000,123134,{"hasNpmPackage":228,"smitheryVerified":228},{"hasCi":242,"hasTests":228},true,{"updatedAt":244},1778675785808,{"basePath":246,"githubOwner":247,"githubRepo":248,"locale":18,"slug":13,"type":249},"plugins/plugin-dev/skills/mcp-integration","anthropics","claude-code","skill",{"_creationTime":251,"_id":252,"community":253,"display":254,"identity":259,"parentExtension":262,"providers":295,"relations":309,"tags":310,"workflow":311},1778675383815.6467,"k175f1rehwh7y2v5t5t0j9hxv586ndkq",{"reviewCount":8},{"description":255,"installMethods":256,"name":258,"sourceUrl":14},"Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.",{"claudeCode":257},"plugin-dev","Plugin Development Toolkit",{"basePath":260,"githubOwner":247,"githubRepo":248,"locale":18,"slug":257,"type":261},"plugins/plugin-dev","plugin",{"_creationTime":263,"_id":264,"community":265,"display":266,"identity":270,"providers":273,"relations":289,"tags":291,"workflow":292},1778675383815.6443,"k17ft5f5kw1crrqpbr5ez2tfx586mxk0",{"reviewCount":8},{"description":267,"installMethods":268,"name":269,"sourceUrl":14},"Bundled plugins for Claude Code including Agent SDK development tools, PR review toolkit, and commit workflows",{"claudeCode":12},"claude-code-plugins",{"basePath":271,"githubOwner":247,"githubRepo":248,"locale":18,"slug":248,"type":272},"","marketplace",{"evaluate":274,"extract":282},{"promptVersionExtension":275,"promptVersionScoring":206,"score":276,"tags":277,"targetMarket":219,"tier":220},"3.1.0",79,[248,215,278,279,280,281],"development","productivity","code-review","agent-sdk",{"commitSha":283,"marketplace":284,"plugin":287},"HEAD",{"name":269,"pluginCount":285,"version":286},13,"1.0.0",{"mcpCount":8,"provider":288,"skillCount":8},"classify",{"repoId":290},"kd7d2pdr9h079xr7vcg3zyy2nx86mab0",[281,248,280,278,215,279],{"evaluatedAt":293,"extractAt":294,"updatedAt":293},1778675396350,1778675383815,{"evaluate":296,"extract":305},{"promptVersionExtension":205,"promptVersionScoring":206,"score":297,"tags":298,"targetMarket":219,"tier":304},99,[299,248,300,301,302,212,303],"plugin-development","skills","agents","hooks","developer-tools","verified",{"commitSha":283,"license":306,"plugin":307},"MIT",{"mcpCount":8,"provider":288,"skillCount":308},7,{"parentExtensionId":264,"repoId":290},[301,248,303,302,212,299,300],{"evaluatedAt":312,"extractAt":294,"updatedAt":312},1778675571192,{"evaluate":314,"extract":316},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":315,"targetMarket":219,"tier":220},[212,213,214,215,216,217,218],{"commitSha":283},{"parentExtensionId":252,"repoId":290},{"_creationTime":319,"_id":290,"identity":320,"providers":321,"workflow":712},1778675378145.0718,{"githubOwner":247,"githubRepo":248,"sourceUrl":14},{"classify":322,"discover":705,"github":708},{"commitSha":283,"extensions":323},[324,337,353,365,375,390,401,418,429,461,471,484,506,523,534,546,553,561,582,609,637,654,676,695],{"basePath":271,"description":267,"displayName":269,"installMethods":325,"rationale":326,"selectedPaths":327,"source":336,"sourceLanguage":18,"type":272},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[328,331,333],{"path":329,"priority":330},".claude-plugin/marketplace.json","mandatory",{"path":332,"priority":330},"README.md",{"path":334,"priority":335},"LICENSE.md","high","rule",{"basePath":338,"description":339,"displayName":340,"installMethods":341,"rationale":342,"selectedPaths":343,"source":336,"sourceLanguage":18,"type":261},"plugins/agent-sdk-dev","Claude Agent SDK Development Plugin","agent-sdk-dev",{"claudeCode":340},"plugin manifest at plugins/agent-sdk-dev/.claude-plugin/plugin.json",[344,346,347,349,351],{"path":345,"priority":330},".claude-plugin/plugin.json",{"path":332,"priority":330},{"path":348,"priority":335},"agents/agent-sdk-verifier-py.md",{"path":350,"priority":335},"agents/agent-sdk-verifier-ts.md",{"path":352,"priority":335},"commands/new-sdk-app.md",{"basePath":354,"description":355,"displayName":356,"installMethods":357,"rationale":358,"selectedPaths":359,"source":336,"sourceLanguage":18,"type":261},"plugins/claude-opus-4-5-migration","Migrate your code and prompts from Sonnet 4.x and Opus 4.1 to Opus 4.5.","claude-opus-4-5-migration",{"claudeCode":356},"plugin manifest at plugins/claude-opus-4-5-migration/.claude-plugin/plugin.json",[360,361,362],{"path":345,"priority":330},{"path":332,"priority":330},{"path":363,"priority":364},"skills/claude-opus-4-5-migration/SKILL.md","medium",{"basePath":366,"description":367,"displayName":280,"installMethods":368,"rationale":369,"selectedPaths":370,"source":336,"sourceLanguage":18,"type":261},"plugins/code-review","Automated code review for pull requests using multiple specialized agents with confidence-based scoring",{"claudeCode":280},"plugin manifest at plugins/code-review/.claude-plugin/plugin.json",[371,372,373],{"path":345,"priority":330},{"path":332,"priority":330},{"path":374,"priority":335},"commands/code-review.md",{"basePath":376,"description":377,"displayName":378,"installMethods":379,"rationale":380,"selectedPaths":381,"source":336,"sourceLanguage":18,"type":261},"plugins/commit-commands","Streamline your git workflow with simple commands for committing, pushing, and creating pull requests","commit-commands",{"claudeCode":378},"plugin manifest at plugins/commit-commands/.claude-plugin/plugin.json",[382,383,384,386,388],{"path":345,"priority":330},{"path":332,"priority":330},{"path":385,"priority":335},"commands/clean_gone.md",{"path":387,"priority":335},"commands/commit-push-pr.md",{"path":389,"priority":335},"commands/commit.md",{"basePath":391,"description":392,"displayName":393,"installMethods":394,"rationale":395,"selectedPaths":396,"source":336,"sourceLanguage":18,"type":261},"plugins/explanatory-output-style","Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)","explanatory-output-style",{"claudeCode":393},"plugin manifest at plugins/explanatory-output-style/.claude-plugin/plugin.json",[397,398,399],{"path":345,"priority":330},{"path":332,"priority":330},{"path":400,"priority":335},"hooks/hooks.json",{"basePath":402,"description":403,"displayName":404,"installMethods":405,"rationale":406,"selectedPaths":407,"source":336,"sourceLanguage":18,"type":261},"plugins/feature-dev","Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review","feature-dev",{"claudeCode":404},"plugin manifest at plugins/feature-dev/.claude-plugin/plugin.json",[408,409,410,412,414,416],{"path":345,"priority":330},{"path":332,"priority":330},{"path":411,"priority":335},"agents/code-architect.md",{"path":413,"priority":335},"agents/code-explorer.md",{"path":415,"priority":335},"agents/code-reviewer.md",{"path":417,"priority":335},"commands/feature-dev.md",{"basePath":419,"description":420,"displayName":421,"installMethods":422,"rationale":423,"selectedPaths":424,"source":336,"sourceLanguage":18,"type":261},"plugins/frontend-design","Frontend design skill for UI/UX implementation","frontend-design",{"claudeCode":421},"plugin manifest at plugins/frontend-design/.claude-plugin/plugin.json",[425,426,427],{"path":345,"priority":330},{"path":332,"priority":330},{"path":428,"priority":364},"skills/frontend-design/SKILL.md",{"basePath":430,"description":431,"displayName":432,"installMethods":433,"rationale":434,"selectedPaths":435,"source":336,"sourceLanguage":18,"type":261},"plugins/hookify","Easily create hooks to prevent unwanted behaviors by analyzing conversation patterns","hookify",{"claudeCode":432},"plugin manifest at plugins/hookify/.claude-plugin/plugin.json",[436,437,438,440,442,444,446,448,450,452,453,455,457,459],{"path":345,"priority":330},{"path":332,"priority":330},{"path":439,"priority":364},"skills/writing-rules/SKILL.md",{"path":441,"priority":335},"agents/conversation-analyzer.md",{"path":443,"priority":335},"commands/configure.md",{"path":445,"priority":335},"commands/help.md",{"path":447,"priority":335},"commands/hookify.md",{"path":449,"priority":335},"commands/list.md",{"path":451,"priority":335},"hooks/__init__.py",{"path":400,"priority":335},{"path":454,"priority":335},"hooks/posttooluse.py",{"path":456,"priority":335},"hooks/pretooluse.py",{"path":458,"priority":335},"hooks/stop.py",{"path":460,"priority":335},"hooks/userpromptsubmit.py",{"basePath":462,"description":463,"displayName":464,"installMethods":465,"rationale":466,"selectedPaths":467,"source":336,"sourceLanguage":18,"type":261},"plugins/learning-output-style","Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style)","learning-output-style",{"claudeCode":464},"plugin manifest at plugins/learning-output-style/.claude-plugin/plugin.json",[468,469,470],{"path":345,"priority":330},{"path":332,"priority":330},{"path":400,"priority":335},{"basePath":260,"description":255,"displayName":257,"installMethods":472,"rationale":473,"selectedPaths":474,"source":336,"sourceLanguage":18,"type":261},{"claudeCode":257},"inline plugin source from marketplace.json at plugins/plugin-dev",[475,476,478,480,482],{"path":332,"priority":330},{"path":477,"priority":335},"agents/agent-creator.md",{"path":479,"priority":335},"agents/plugin-validator.md",{"path":481,"priority":335},"agents/skill-reviewer.md",{"path":483,"priority":335},"commands/create-plugin.md",{"basePath":485,"description":486,"displayName":487,"installMethods":488,"rationale":489,"selectedPaths":490,"source":336,"sourceLanguage":18,"type":261},"plugins/pr-review-toolkit","Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification","pr-review-toolkit",{"claudeCode":487},"plugin manifest at plugins/pr-review-toolkit/.claude-plugin/plugin.json",[491,492,493,494,496,498,500,502,504],{"path":345,"priority":330},{"path":332,"priority":330},{"path":415,"priority":335},{"path":495,"priority":335},"agents/code-simplifier.md",{"path":497,"priority":335},"agents/comment-analyzer.md",{"path":499,"priority":335},"agents/pr-test-analyzer.md",{"path":501,"priority":335},"agents/silent-failure-hunter.md",{"path":503,"priority":335},"agents/type-design-analyzer.md",{"path":505,"priority":335},"commands/review-pr.md",{"basePath":507,"description":508,"displayName":509,"installMethods":510,"rationale":511,"selectedPaths":512,"source":336,"sourceLanguage":18,"type":261},"plugins/ralph-wiggum","Implementation of the Ralph Wiggum technique - continuous self-referential AI loops for interactive iterative development. Run Claude in a while-true loop with the same prompt until task completion.","ralph-wiggum",{"claudeCode":509},"plugin manifest at plugins/ralph-wiggum/.claude-plugin/plugin.json",[513,514,515,517,518,520,521],{"path":345,"priority":330},{"path":332,"priority":330},{"path":516,"priority":335},"commands/cancel-ralph.md",{"path":445,"priority":335},{"path":519,"priority":335},"commands/ralph-loop.md",{"path":400,"priority":335},{"path":522,"priority":335},"hooks/stop-hook.sh",{"basePath":524,"description":525,"displayName":526,"installMethods":527,"rationale":528,"selectedPaths":529,"source":336,"sourceLanguage":18,"type":261},"plugins/security-guidance","Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns","security-guidance",{"claudeCode":526},"plugin manifest at plugins/security-guidance/.claude-plugin/plugin.json",[530,531,532],{"path":345,"priority":330},{"path":400,"priority":335},{"path":533,"priority":335},"hooks/security_reminder_hook.py",{"basePath":535,"description":536,"displayName":356,"installMethods":537,"rationale":538,"selectedPaths":539,"source":336,"sourceLanguage":18,"type":249},"plugins/claude-opus-4-5-migration/skills/claude-opus-4-5-migration","Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT migrate Haiku 4.5.",{"claudeCode":12},"SKILL.md frontmatter at plugins/claude-opus-4-5-migration/skills/claude-opus-4-5-migration/SKILL.md",[540,542,544],{"path":541,"priority":330},"SKILL.md",{"path":543,"priority":364},"references/effort.md",{"path":545,"priority":364},"references/prompt-snippets.md",{"basePath":547,"description":548,"displayName":421,"installMethods":549,"rationale":550,"selectedPaths":551,"source":336,"sourceLanguage":18,"type":249},"plugins/frontend-design/skills/frontend-design","Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.",{"claudeCode":12},"SKILL.md frontmatter at plugins/frontend-design/skills/frontend-design/SKILL.md",[552],{"path":541,"priority":330},{"basePath":554,"description":555,"displayName":556,"installMethods":557,"rationale":558,"selectedPaths":559,"source":336,"sourceLanguage":18,"type":249},"plugins/hookify/skills/writing-rules","This skill should be used when the user asks to \"create a hookify rule\", \"write a hook rule\", \"configure hookify\", \"add a hookify rule\", or needs guidance on hookify rule syntax and patterns.","writing-rules",{"claudeCode":12},"SKILL.md frontmatter at plugins/hookify/skills/writing-rules/SKILL.md",[560],{"path":541,"priority":330},{"basePath":562,"description":563,"displayName":564,"installMethods":565,"rationale":566,"selectedPaths":567,"source":336,"sourceLanguage":18,"type":249},"plugins/plugin-dev/skills/agent-development","This skill should be used when the user asks to \"create an agent\", \"add an agent\", \"write a subagent\", \"agent frontmatter\", \"when to use description\", \"agent examples\", \"agent tools\", \"agent colors\", \"autonomous agent\", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.","agent-development",{"claudeCode":12},"SKILL.md frontmatter at plugins/plugin-dev/skills/agent-development/SKILL.md",[568,569,572,574,576,578,580],{"path":541,"priority":330},{"path":570,"priority":571},"examples/agent-creation-prompt.md","low",{"path":573,"priority":571},"examples/complete-agent-examples.md",{"path":575,"priority":364},"references/agent-creation-system-prompt.md",{"path":577,"priority":364},"references/system-prompt-design.md",{"path":579,"priority":364},"references/triggering-examples.md",{"path":581,"priority":571},"scripts/validate-agent.sh",{"basePath":583,"description":584,"displayName":585,"installMethods":586,"rationale":587,"selectedPaths":588,"source":336,"sourceLanguage":18,"type":249},"plugins/plugin-dev/skills/command-development","This skill should be used when the user asks to \"create a slash command\", \"add a command\", \"write a custom command\", \"define command arguments\", \"use command frontmatter\", \"organize commands\", \"create command with file references\", \"interactive command\", \"use AskUserQuestion in command\", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.","command-development",{"claudeCode":12},"SKILL.md frontmatter at plugins/plugin-dev/skills/command-development/SKILL.md",[589,590,591,593,595,597,599,601,603,605,607],{"path":541,"priority":330},{"path":332,"priority":335},{"path":592,"priority":571},"examples/plugin-commands.md",{"path":594,"priority":571},"examples/simple-commands.md",{"path":596,"priority":364},"references/advanced-workflows.md",{"path":598,"priority":364},"references/documentation-patterns.md",{"path":600,"priority":364},"references/frontmatter-reference.md",{"path":602,"priority":364},"references/interactive-commands.md",{"path":604,"priority":364},"references/marketplace-considerations.md",{"path":606,"priority":364},"references/plugin-features-reference.md",{"path":608,"priority":364},"references/testing-strategies.md",{"basePath":610,"description":611,"displayName":612,"installMethods":613,"rationale":614,"selectedPaths":615,"source":336,"sourceLanguage":18,"type":249},"plugins/plugin-dev/skills/hook-development","This skill should be used when the user asks to \"create a hook\", \"add a PreToolUse/PostToolUse/Stop hook\", \"validate tool use\", \"implement prompt-based hooks\", \"use ${CLAUDE_PLUGIN_ROOT}\", \"set up event-driven automation\", \"block dangerous commands\", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.","hook-development",{"claudeCode":12},"SKILL.md frontmatter at plugins/plugin-dev/skills/hook-development/SKILL.md",[616,617,619,621,623,625,627,629,631,633,635],{"path":541,"priority":330},{"path":618,"priority":571},"examples/load-context.sh",{"path":620,"priority":571},"examples/validate-bash.sh",{"path":622,"priority":571},"examples/validate-write.sh",{"path":624,"priority":364},"references/advanced.md",{"path":626,"priority":364},"references/migration.md",{"path":628,"priority":364},"references/patterns.md",{"path":630,"priority":571},"scripts/README.md",{"path":632,"priority":571},"scripts/hook-linter.sh",{"path":634,"priority":571},"scripts/test-hook.sh",{"path":636,"priority":571},"scripts/validate-hook-schema.sh",{"basePath":246,"description":10,"displayName":13,"installMethods":638,"rationale":639,"selectedPaths":640,"source":336,"sourceLanguage":18,"type":249},{"claudeCode":12},"SKILL.md frontmatter at plugins/plugin-dev/skills/mcp-integration/SKILL.md",[641,642,644,646,648,650,652],{"path":541,"priority":330},{"path":643,"priority":571},"examples/http-server.json",{"path":645,"priority":571},"examples/sse-server.json",{"path":647,"priority":571},"examples/stdio-server.json",{"path":649,"priority":364},"references/authentication.md",{"path":651,"priority":364},"references/server-types.md",{"path":653,"priority":364},"references/tool-usage.md",{"basePath":655,"description":656,"displayName":657,"installMethods":658,"rationale":659,"selectedPaths":660,"source":336,"sourceLanguage":18,"type":249},"plugins/plugin-dev/skills/plugin-settings","This skill should be used when the user asks about \"plugin settings\", \"store plugin configuration\", \"user-configurable plugin\", \".local.md files\", \"plugin state files\", \"read YAML frontmatter\", \"per-project plugin settings\", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.","plugin-settings",{"claudeCode":12},"SKILL.md frontmatter at plugins/plugin-dev/skills/plugin-settings/SKILL.md",[661,662,664,666,668,670,672,674],{"path":541,"priority":330},{"path":663,"priority":571},"examples/create-settings-command.md",{"path":665,"priority":571},"examples/example-settings.md",{"path":667,"priority":571},"examples/read-settings-hook.sh",{"path":669,"priority":364},"references/parsing-techniques.md",{"path":671,"priority":364},"references/real-world-examples.md",{"path":673,"priority":571},"scripts/parse-frontmatter.sh",{"path":675,"priority":571},"scripts/validate-settings.sh",{"basePath":677,"description":678,"displayName":679,"installMethods":680,"rationale":681,"selectedPaths":682,"source":336,"sourceLanguage":18,"type":249},"plugins/plugin-dev/skills/plugin-structure","This skill should be used when the user asks to \"create a plugin\", \"scaffold a plugin\", \"understand plugin structure\", \"organize plugin components\", \"set up plugin.json\", \"use ${CLAUDE_PLUGIN_ROOT}\", \"add commands/agents/skills/hooks\", \"configure auto-discovery\", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.","plugin-structure",{"claudeCode":12},"SKILL.md frontmatter at plugins/plugin-dev/skills/plugin-structure/SKILL.md",[683,684,685,687,689,691,693],{"path":541,"priority":330},{"path":332,"priority":335},{"path":686,"priority":571},"examples/advanced-plugin.md",{"path":688,"priority":571},"examples/minimal-plugin.md",{"path":690,"priority":571},"examples/standard-plugin.md",{"path":692,"priority":364},"references/component-patterns.md",{"path":694,"priority":364},"references/manifest-reference.md",{"basePath":696,"description":697,"displayName":698,"installMethods":699,"rationale":700,"selectedPaths":701,"source":336,"sourceLanguage":18,"type":249},"plugins/plugin-dev/skills/skill-development","This skill should be used when the user wants to \"create a skill\", \"add a skill to plugin\", \"write a new skill\", \"improve skill description\", \"organize skill content\", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.","skill-development",{"claudeCode":12},"SKILL.md frontmatter at plugins/plugin-dev/skills/skill-development/SKILL.md",[702,703],{"path":541,"priority":330},{"path":704,"priority":364},"references/skill-creator-original.md",{"sources":706},[707],"manual",{"closedIssues90d":234,"description":709,"forks":235,"homepage":710,"openIssues90d":237,"pushedAt":238,"readmeSize":232,"stars":239,"topics":711},"Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.","https://code.claude.com/docs/en/overview",[],{"classifiedAt":713,"discoverAt":714,"extractAt":715,"githubAt":715,"updatedAt":713},1778675383497,1778675378145,1778675381570,[217,216,214,212,215,213,218],{"evaluatedAt":244,"extractAt":294,"updatedAt":244},[],[720,751,780,805,825,855],{"_creationTime":721,"_id":722,"community":723,"display":724,"identity":730,"providers":735,"relations":742,"tags":746,"workflow":747},1778694392532.535,"k17eqx1548qq4twnvaeg3h866d86nqem",{"reviewCount":8},{"description":725,"installMethods":726,"name":728,"sourceUrl":729},"指导用户配置关键的 MongoDB MCP 服务器选项。当用户已安装 MongoDB MCP 服务器但未配置必需的环境变量，或当他们询问连接到 MongoDB/Atlas 但未设置凭据时，请使用此技能。",{"claudeCode":727},"mongodb/agent-skills","mongodb-mcp-setup","https://github.com/mongodb/agent-skills",{"basePath":731,"githubOwner":732,"githubRepo":733,"locale":734,"slug":728,"type":249},"skills/mongodb-mcp-setup","mongodb","agent-skills","zh-CN",{"evaluate":736,"extract":741},{"promptVersionExtension":205,"promptVersionScoring":206,"score":737,"tags":738,"targetMarket":219,"tier":304},100,[732,212,216,739,217,740],"setup","cli",{"commitSha":283},{"parentExtensionId":743,"repoId":744,"translatedFrom":745},"k170hje3xzpy2mbkn00agzm38x86mkbz","kd74vahs1zbjqzqbert490xyrd86nfv5","k1798fc1hmtx3bmdgwyn3fet2d86mzt5",[217,740,216,212,732,739],{"evaluatedAt":748,"extractAt":749,"updatedAt":750},1778694262565,1778694149049,1778694392532,{"_creationTime":752,"_id":753,"community":754,"display":755,"identity":761,"providers":765,"relations":773,"tags":776,"workflow":777},1778695548458.336,"k17ekwjt5qesx1b7a0y4nkbxsn86mnge",{"reviewCount":8},{"description":756,"installMethods":757,"name":759,"sourceUrl":760},"Build a custom MCP (Model Context Protocol) server that exposes domain-specific tools to AI assistants. Covers server implementation in Node.js or R, tool definitions, transport configuration, and testing with Claude Code. Use when you need to expose custom functionality beyond what mcptools provides, when building specialized domain-specific AI integrations, or when wrapping existing APIs or services as MCP tools.\n",{"claudeCode":758},"pjt222/agent-almanac","build-custom-mcp-server","https://github.com/pjt222/agent-almanac",{"basePath":762,"githubOwner":763,"githubRepo":764,"locale":18,"slug":759,"type":249},"skills/build-custom-mcp-server","pjt222","agent-almanac",{"evaluate":766,"extract":772},{"promptVersionExtension":205,"promptVersionScoring":206,"score":737,"tags":767,"targetMarket":219,"tier":304},[212,768,769,770,771,213,214],"server","custom-tools","node-js","r",{"commitSha":283},{"parentExtensionId":774,"repoId":775},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[769,214,212,770,213,771,768],{"evaluatedAt":778,"extractAt":779,"updatedAt":778},1778696351782,1778695548458,{"_creationTime":781,"_id":782,"community":783,"display":784,"identity":789,"providers":793,"relations":798,"tags":801,"workflow":802},1778699234184.6174,"k174zww66m804nhr89ttra7r6d86nwyg",{"reviewCount":8},{"description":785,"installMethods":786,"name":739,"sourceUrl":788},"Use first for install/update routing — sends setup, doctor, or MCP requests to the correct OMC setup flow",{"claudeCode":787},"Yeachan-Heo/oh-my-claudecode","https://github.com/Yeachan-Heo/oh-my-claudecode",{"basePath":790,"githubOwner":791,"githubRepo":792,"locale":18,"slug":739,"type":249},"skills/setup","Yeachan-Heo","oh-my-claudecode",{"evaluate":794,"extract":797},{"promptVersionExtension":205,"promptVersionScoring":206,"score":737,"tags":795,"targetMarket":219,"tier":304},[739,796,216,740,212],"routing",{"commitSha":283},{"parentExtensionId":799,"repoId":800},"k17brg5egdw1jbncj1j4wfv3fh86n639","kd74zv63fryf9prygtq7gf4es986n22y",[740,216,212,796,739],{"evaluatedAt":803,"extractAt":804,"updatedAt":803},1778699724286,1778699234184,{"_creationTime":806,"_id":807,"community":808,"display":809,"identity":813,"providers":815,"relations":821,"tags":822,"workflow":823},1778699234184.6143,"k17cnx0m6a27fw52yvt4zsbsxh86nd1c",{"reviewCount":8},{"description":810,"installMethods":811,"name":812,"sourceUrl":788},"Configure popular MCP servers for enhanced agent capabilities",{"claudeCode":787},"mcp-setup",{"basePath":814,"githubOwner":791,"githubRepo":792,"locale":18,"slug":812,"type":249},"skills/mcp-setup",{"evaluate":816,"extract":820},{"promptVersionExtension":205,"promptVersionScoring":206,"score":737,"tags":817,"targetMarket":219,"tier":304},[212,216,740,818,819],"agent","tooling",{"commitSha":283},{"parentExtensionId":799,"repoId":800},[818,740,216,212,819],{"evaluatedAt":824,"extractAt":804,"updatedAt":824},1778699492025,{"_creationTime":826,"_id":827,"community":828,"display":829,"identity":835,"providers":840,"relations":846,"tags":850,"workflow":851},1778699611234.2175,"k17ea488ga99v5nwyye2ne7wp586ngz3",{"reviewCount":8},{"description":830,"installMethods":831,"name":833,"sourceUrl":834},"设置 Zapier MCP 并为您的 AI 助手添加工具。介绍 Zapier 的功能，引导完成身份验证，检测您的服务器模式，然后分支到正确的流程 — 总结健康设置，重新连接已损坏的身份验证，首次安装的入职流程，或在服务器缺失时的配置帮助。在入门、排查连接问题、添加新工具时，或当用户询问“我现在能做什么”、“我能用 Zapier 做些什么”、“展示 Zapier 插件的工作原理”、“什么是 Zapier MCP”、“Zapier 如何工作”或“谈谈 Zapier”时使用。",{"claudeCode":832},"zapier/zapier-mcp","Zapier 设置","https://github.com/zapier/zapier-mcp",{"basePath":836,"githubOwner":837,"githubRepo":838,"locale":734,"slug":839,"type":249},"plugins/zapier/skills/zapier-setup","zapier","zapier-mcp","zapier-setup",{"evaluate":841,"extract":844},{"promptVersionExtension":205,"promptVersionScoring":206,"score":297,"tags":842,"targetMarket":219,"tier":304},[837,212,214,739,217,843],"automation",{"commitSha":283,"license":845},"Apache-2.0",{"parentExtensionId":847,"repoId":848,"translatedFrom":849},"k170hhqj0rh7s07z1f86fh594586mmxw","kd72mhnpsgxe81n8vxnr1tdje186mdjt","k1716ts08smjg12r4p2b21kf0x86mhv8",[217,843,214,212,739,837],{"evaluatedAt":852,"extractAt":853,"updatedAt":854},1778699559593,1778699497437,1778699611234,{"_creationTime":856,"_id":857,"community":858,"display":859,"identity":865,"providers":869,"relations":877,"tags":881,"workflow":882},1778694990914.8232,"k170mmr549jkqghjyp3y2gxcr186nh6y",{"reviewCount":8},{"description":860,"installMethods":861,"name":863,"sourceUrl":864},"用于身份验证、用户注册、登录、密码恢复、OAuth 提供商、基于角色的访问控制或保护路由和函数。始终使用 `@netlify/identity`。切勿使用 `netlify-identity-widget` 或 `gotrue-js` — 它们已弃用。",{"claudeCode":862},"netlify/context-and-tools","netlify-identity","https://github.com/netlify/context-and-tools",{"basePath":866,"githubOwner":867,"githubRepo":868,"locale":734,"slug":863,"type":249},"skills/netlify-identity","netlify","context-and-tools",{"evaluate":870,"extract":876},{"promptVersionExtension":205,"promptVersionScoring":206,"score":737,"tags":871,"targetMarket":219,"tier":304},[217,867,872,873,874,875],"identity","javascript","typescript","api",{"commitSha":283},{"parentExtensionId":878,"repoId":879,"translatedFrom":880},"k1714spp30a0rvg5y3yjga772n86nmps","kd7b1ncy2zzzfws29grdt8heb986ntzq","k17f1596a2t00btq1hfksssg0s86n6ej",[875,217,872,873,867,874],{"evaluatedAt":883,"extractAt":884,"updatedAt":885},1778694839805,1778694599571,1778694990914]