[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-anthropics-hook-development-zh-CN":3,"guides-for-anthropics-hook-development":734,"similar-k17e0g15gees32t1rxjmdv50kh86nz1j-zh-CN":735},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":260,"isFallback":257,"parentExtension":266,"providers":328,"relations":333,"repo":334,"tags":732,"workflow":733},1778675383815.649,"k17e0g15gees32t1rxjmdv50kh86nz1j",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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.",{"claudeCode":12},"anthropics/claude-code","Hook Development","https://github.com/anthropics/claude-code",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":241,"workflow":258},1778675766362.5178,"kn74g6knnp09wc1x3pjw7q6xss86ng3d","en",{"checks":20,"evaluatedAt":191,"extensionSummary":192,"features":193,"nonGoals":199,"practices":203,"prerequisites":208,"promptVersionExtension":212,"promptVersionScoring":213,"purpose":214,"rationale":215,"score":216,"summary":217,"tags":218,"targetMarket":225,"tier":226,"useCases":227,"workflow":232},[21,26,29,32,36,39,44,48,51,54,58,62,65,69,72,75,78,81,84,87,91,95,99,103,107,110,113,117,121,124,127,130,132,134,137,141,145,149,152,156,159,162,165,168,172,175,178,181,184,188],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the extension's purpose: to guide users in creating and implementing Claude Code plugin hooks, focusing on prompt-based APIs and event-driven automation, addressing the problem of managing complex workflow logic.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers significant value over simple prompting by providing structured guidance, configuration formats, detailed examples, and security best practices for implementing hooks, which is beyond default Claude Code behavior.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The extension covers the complete lifecycle of hook development, from configuration and scripting to debugging and best practices, making it suitable for production workflows.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses solely on hook development for Claude Code plugins, covering configuration, types, events, and best practices without straying into unrelated domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The description accurately reflects the skill's capabilities, detailing specific hook types, events, and the focus on prompt-based APIs.",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","This check is not applicable as the extension is a skill providing guidance and documentation, not exposing specific tools or commands.",{"category":45,"check":46,"severity":24,"summary":47},"Documentation","Configuration & parameter reference","All hook configuration formats, event structures, input/output formats, environment variables, and matcher patterns are clearly documented with examples.",{"category":33,"check":49,"severity":42,"summary":50},"Tool naming","This check is not applicable as the extension does not expose user-facing tools or commands.",{"category":33,"check":52,"severity":42,"summary":53},"Minimal I/O surface","This check is not applicable as the extension is a skill providing guidance and documentation, not exposing specific tools or commands with parameter schemas.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The LICENSE.md file provides a clear copyright notice and links to Anthropic's Commercial Terms of Service, indicating an acceptable license for use.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The last commit was on 2026-05-12, which is within the last 3 months.",{"category":59,"check":63,"severity":42,"summary":64},"Dependency Management","The extension does not appear to use third-party dependencies that would require specific management.",{"category":66,"check":67,"severity":42,"summary":68},"Security","Secret Management","The extension provides guidance on hook development and does not handle or expose secrets.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The documentation emphasizes input validation and quoting variables in scripts to prevent injection, and the utility scripts actively check for these issues.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The documentation explicitly warns against runtime downloads and remote execution, promoting the use of bundled scripts and `${CLAUDE_PLUGIN_ROOT}` for portability and security.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The documentation stresses using `${CLAUDE_PLUGIN_ROOT}` for portability and advises against hardcoded paths or modifying files outside the project, aligning with sandbox principles.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","The documentation and examples promote safe scripting practices, with no indication of detached processes or deny-retry loops that could lead to sandbox escapes.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The documentation provides security best practices, including warnings against logging sensitive information and emphasizing input validation, which inherently mitigates data exfiltration risks.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The provided documentation and scripts are free of hidden steering tricks, using standard printable ASCII and expected Unicode characters.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","The extension promotes the use of readable bash scripts and clear JSON configurations, with utility scripts like `hook-linter.sh` available to check for obfuscation.",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","The skill strongly advocates for using `${CLAUDE_PLUGIN_ROOT}` and `$CLAUDE_PROJECT_DIR` for path references, mitigating assumptions about user project structure.",{"category":96,"check":97,"severity":24,"summary":98},"Trust","Issues Attention","While issue counts are high, the closure rate is strong (22831 closed / 9462 open), indicating active maintenance.",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","A `version: 0.1.0` is declared in the SKILL.md frontmatter, providing a clear signal of release management.",{"category":104,"check":105,"severity":24,"summary":106},"Code Execution","Validation","The documentation and provided utility scripts strongly emphasize input validation for both JSON configurations and bash scripts, promoting the use of tools like `jq` and robust shell scripting practices.",{"category":66,"check":108,"severity":24,"summary":109},"Unguarded Destructive Operations","The security best practices section explicitly warns against destructive operations and promotes validation hooks, ensuring that such actions are guarded.",{"category":104,"check":111,"severity":24,"summary":112},"Error Handling","The documentation details proper error handling with exit codes (0 for success, 2 for blocking errors) and emphasizes writing messages to stderr, promoting fail-closed behavior.",{"category":104,"check":114,"severity":115,"summary":116},"Logging","info","While the extension doesn't directly perform logging, it provides examples of how to implement audit logging for hook actions using bash scripts.",{"category":118,"check":119,"severity":42,"summary":120},"Compliance","GDPR","The extension provides guidance on hook development and does not inherently operate on personal data.",{"category":118,"check":122,"severity":24,"summary":123},"Target market","The extension's content is universally applicable to Claude Code users regardless of their geographical location, hence 'global' is appropriate.",{"category":92,"check":125,"severity":24,"summary":126},"Runtime stability","The extension promotes using portable paths with `${CLAUDE_PLUGIN_ROOT}` and standard bash scripting, ensuring cross-platform compatibility and graceful fallback via clear error messages.",{"category":45,"check":128,"severity":24,"summary":129},"README","The SKILL.md frontmatter description serves as an effective README, clearly stating the extension's purpose.",{"category":33,"check":131,"severity":42,"summary":43},"Tool surface size",{"category":40,"check":133,"severity":42,"summary":50},"Overlapping near-synonym tools",{"category":45,"check":135,"severity":24,"summary":136},"Phantom features","All advertised capabilities, such as different hook types, configuration formats, and security practices, are thoroughly documented and exemplified within the SKILL.md and its references.",{"category":138,"check":139,"severity":42,"summary":140},"Install","Installation instruction","This extension is a skill loaded directly by Claude Code and does not require separate installation steps or authentication setup beyond the Claude Code environment itself.",{"category":142,"check":143,"severity":24,"summary":144},"Errors","Actionable error messages","The documentation and examples consistently show how to provide actionable error messages, including exit codes and `systemMessage` fields, to guide the user and Claude.",{"category":146,"check":147,"severity":42,"summary":148},"Execution","Pinned dependencies","The extension relies on the Claude Code runtime environment and bash, and does not introduce external dependencies that would require pinning.",{"category":33,"check":150,"severity":42,"summary":151},"Dry-run preview","This check is not applicable as the extension provides guidance and documentation on hooks, rather than performing state-changing operations itself.",{"category":153,"check":154,"severity":24,"summary":155},"Protocol","Idempotent retry & timeouts","The documentation explicitly discusses setting appropriate timeouts for hooks and emphasizes designing hooks for independence due to parallel execution, which indirectly supports robust protocol design.",{"category":118,"check":157,"severity":42,"summary":158},"Telemetry opt-in","The extension provides guidance on hook development and does not emit telemetry itself.",{"category":40,"check":160,"severity":24,"summary":161},"Precise Purpose","The description precisely names the artifact (Claude Code plugin hooks) and the user intent (create, validate, implement, set up event-driven automation), with clear triggers and boundaries.",{"category":40,"check":163,"severity":24,"summary":164},"Concise Frontmatter","The frontmatter is concise, dense, and self-contained, providing core capability and trigger phrases within the character limit.",{"category":45,"check":166,"severity":24,"summary":167},"Concise Body","The main SKILL.md body is well-structured and under 500 lines, delegating deeper material to `references/` files.",{"category":169,"check":170,"severity":24,"summary":171},"Context","Progressive Disclosure","The skill utilizes `references/` and `examples/` directories for progressive disclosure, keeping the main SKILL.md concise while providing access to detailed patterns and scripts.",{"category":169,"check":173,"severity":42,"summary":174},"Forked exploration","This skill provides guidance and documentation, not deep exploration, so the `context: fork` setting is not applicable.",{"category":22,"check":176,"severity":24,"summary":177},"Usage examples","The extension includes numerous ready-to-use examples for hook configurations, scripts, and patterns, demonstrating input, invocation, and expected outcomes.",{"category":22,"check":179,"severity":24,"summary":180},"Edge cases","The documentation addresses edge cases like temporarily active hooks, configuration-driven hooks, and provides examples of error handling for malformed input and path safety.",{"category":104,"check":182,"severity":42,"summary":183},"Tool Fallback","This check is not applicable as the extension does not rely on external tools or MCP servers; it guides the development of hooks that run within the Claude Code environment.",{"category":185,"check":186,"severity":24,"summary":187},"Safety","Halt on unexpected state","The documentation emphasizes robust error handling and validation, encouraging hooks to halt execution with clear reports on unexpected states or inputs.",{"category":92,"check":189,"severity":24,"summary":190},"Cross-skill coupling","The skill is self-contained, providing guidance on developing independent hooks. It suggests referencing sibling skills explicitly if needed, rather than creating implicit dependencies.",1778675766250,"This skill provides extensive documentation, examples, and best practices for developing event-driven automation scripts (hooks) within Claude Code plugins. It covers prompt-based and command hooks, configuration formats, security considerations, and debugging utilities.",[194,195,196,197,198],"Guidance on prompt-based and command hooks","Explanation of hook types, events, and configuration","Security best practices for hook development","Debugging utilities and testing strategies","Examples for common hook patterns and scenarios",[200,201,202],"Providing specific hook scripts to copy-paste without understanding","Handling the core logic of external tools or services","Replacing the need for fundamental bash or prompt engineering knowledge",[204,205,206,207],"Security validation","Test enforcement","Context loading","Code quality checks",[209,210,211],"Claude Code environment","Basic understanding of bash scripting (for command hooks)","Basic understanding of prompt engineering (for prompt hooks)","3.0.0","4.4.0","To guide users in creating robust and secure event-driven automation hooks for Claude Code plugins, enabling advanced workflow control and validation.","Excellent documentation and robust security/portability guidance make this a top-tier skill. Minor notes on logging best practices are the only area not fully covered, but do not detract from overall quality.",99,"Comprehensive and well-documented skill for implementing Claude Code plugin hooks.",[219,220,221,222,223,224],"hooks","automation","plugin-development","bash","prompt-engineering","security","global","verified",[228,229,230,231],"Implementing validation for tool use (PreToolUse, PostToolUse)","Setting up event-driven automation for the development lifecycle","Blocking dangerous commands or sensitive file operations","Loading project context and environment variables at session start",[233,234,235,236,237,238,239,240],"Identify events to hook into","Choose between prompt-based or command hooks","Write hook configuration in `hooks/hooks.json`","Create hook scripts (for command hooks)","Use portable paths (`${CLAUDE_PLUGIN_ROOT}`)","Validate configuration and scripts","Test hooks thoroughly","Implement hooks in Claude Code and test with `--debug`",{"codeQuality":242,"collectedAt":244,"documentation":245,"maintenance":248,"security":255,"testCoverage":256},{"hasLockfile":243},false,1778675749047,{"descriptionLength":246,"readmeSize":247},525,2873,{"closedIssues90d":249,"forks":250,"hasChangelog":243,"manifestVersion":251,"openIssues90d":252,"pushedAt":253,"stars":254},22831,20310,"0.1.0",9462,1778620184000,123134,{"hasNpmPackage":243,"smitheryVerified":243},{"hasCi":257,"hasTests":243},true,{"updatedAt":259},1778675766362,{"basePath":261,"githubOwner":262,"githubRepo":263,"locale":18,"slug":264,"type":265},"plugins/plugin-dev/skills/hook-development","anthropics","claude-code","hook-development","skill",{"_creationTime":267,"_id":268,"community":269,"display":270,"identity":275,"parentExtension":278,"providers":313,"relations":324,"tags":325,"workflow":326},1778675383815.6467,"k175f1rehwh7y2v5t5t0j9hxv586ndkq",{"reviewCount":8},{"description":271,"installMethods":272,"name":274,"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":273},"plugin-dev","Plugin Development Toolkit",{"basePath":276,"githubOwner":262,"githubRepo":263,"locale":18,"slug":273,"type":277},"plugins/plugin-dev","plugin",{"_creationTime":279,"_id":280,"community":281,"display":282,"identity":286,"providers":289,"relations":307,"tags":309,"workflow":310},1778675383815.6443,"k17ft5f5kw1crrqpbr5ez2tfx586mxk0",{"reviewCount":8},{"description":283,"installMethods":284,"name":285,"sourceUrl":14},"Bundled plugins for Claude Code including Agent SDK development tools, PR review toolkit, and commit workflows",{"claudeCode":12},"claude-code-plugins",{"basePath":287,"githubOwner":262,"githubRepo":263,"locale":18,"slug":263,"type":288},"","marketplace",{"evaluate":290,"extract":300},{"promptVersionExtension":291,"promptVersionScoring":213,"score":292,"tags":293,"targetMarket":225,"tier":299},"3.1.0",79,[263,294,295,296,297,298],"plugins","development","productivity","code-review","agent-sdk","community",{"commitSha":301,"marketplace":302,"plugin":305},"HEAD",{"name":285,"pluginCount":303,"version":304},13,"1.0.0",{"mcpCount":8,"provider":306,"skillCount":8},"classify",{"repoId":308},"kd7d2pdr9h079xr7vcg3zyy2nx86mab0",[298,263,297,295,294,296],{"evaluatedAt":311,"extractAt":312,"updatedAt":311},1778675396350,1778675383815,{"evaluate":314,"extract":320},{"promptVersionExtension":212,"promptVersionScoring":213,"score":216,"tags":315,"targetMarket":225,"tier":226},[221,263,316,317,219,318,319],"skills","agents","mcp","developer-tools",{"commitSha":301,"license":321,"plugin":322},"MIT",{"mcpCount":8,"provider":306,"skillCount":323},7,{"parentExtensionId":280,"repoId":308},[317,263,319,219,318,221,316],{"evaluatedAt":327,"extractAt":312,"updatedAt":327},1778675571192,{"evaluate":329,"extract":331},{"promptVersionExtension":212,"promptVersionScoring":213,"score":216,"tags":330,"targetMarket":225,"tier":226},[219,220,221,222,223,224],{"commitSha":301,"license":332},"commercial-terms",{"parentExtensionId":268,"repoId":308},{"_creationTime":335,"_id":308,"identity":336,"providers":337,"workflow":728},1778675378145.0718,{"githubOwner":262,"githubRepo":263,"sourceUrl":14},{"classify":338,"discover":721,"github":724},{"commitSha":301,"extensions":339},[340,353,369,381,391,406,417,434,445,477,487,500,522,539,550,562,569,577,598,625,650,670,692,711],{"basePath":287,"description":283,"displayName":285,"installMethods":341,"rationale":342,"selectedPaths":343,"source":352,"sourceLanguage":18,"type":288},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[344,347,349],{"path":345,"priority":346},".claude-plugin/marketplace.json","mandatory",{"path":348,"priority":346},"README.md",{"path":350,"priority":351},"LICENSE.md","high","rule",{"basePath":354,"description":355,"displayName":356,"installMethods":357,"rationale":358,"selectedPaths":359,"source":352,"sourceLanguage":18,"type":277},"plugins/agent-sdk-dev","Claude Agent SDK Development Plugin","agent-sdk-dev",{"claudeCode":356},"plugin manifest at plugins/agent-sdk-dev/.claude-plugin/plugin.json",[360,362,363,365,367],{"path":361,"priority":346},".claude-plugin/plugin.json",{"path":348,"priority":346},{"path":364,"priority":351},"agents/agent-sdk-verifier-py.md",{"path":366,"priority":351},"agents/agent-sdk-verifier-ts.md",{"path":368,"priority":351},"commands/new-sdk-app.md",{"basePath":370,"description":371,"displayName":372,"installMethods":373,"rationale":374,"selectedPaths":375,"source":352,"sourceLanguage":18,"type":277},"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":372},"plugin manifest at plugins/claude-opus-4-5-migration/.claude-plugin/plugin.json",[376,377,378],{"path":361,"priority":346},{"path":348,"priority":346},{"path":379,"priority":380},"skills/claude-opus-4-5-migration/SKILL.md","medium",{"basePath":382,"description":383,"displayName":297,"installMethods":384,"rationale":385,"selectedPaths":386,"source":352,"sourceLanguage":18,"type":277},"plugins/code-review","Automated code review for pull requests using multiple specialized agents with confidence-based scoring",{"claudeCode":297},"plugin manifest at plugins/code-review/.claude-plugin/plugin.json",[387,388,389],{"path":361,"priority":346},{"path":348,"priority":346},{"path":390,"priority":351},"commands/code-review.md",{"basePath":392,"description":393,"displayName":394,"installMethods":395,"rationale":396,"selectedPaths":397,"source":352,"sourceLanguage":18,"type":277},"plugins/commit-commands","Streamline your git workflow with simple commands for committing, pushing, and creating pull requests","commit-commands",{"claudeCode":394},"plugin manifest at plugins/commit-commands/.claude-plugin/plugin.json",[398,399,400,402,404],{"path":361,"priority":346},{"path":348,"priority":346},{"path":401,"priority":351},"commands/clean_gone.md",{"path":403,"priority":351},"commands/commit-push-pr.md",{"path":405,"priority":351},"commands/commit.md",{"basePath":407,"description":408,"displayName":409,"installMethods":410,"rationale":411,"selectedPaths":412,"source":352,"sourceLanguage":18,"type":277},"plugins/explanatory-output-style","Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)","explanatory-output-style",{"claudeCode":409},"plugin manifest at plugins/explanatory-output-style/.claude-plugin/plugin.json",[413,414,415],{"path":361,"priority":346},{"path":348,"priority":346},{"path":416,"priority":351},"hooks/hooks.json",{"basePath":418,"description":419,"displayName":420,"installMethods":421,"rationale":422,"selectedPaths":423,"source":352,"sourceLanguage":18,"type":277},"plugins/feature-dev","Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review","feature-dev",{"claudeCode":420},"plugin manifest at plugins/feature-dev/.claude-plugin/plugin.json",[424,425,426,428,430,432],{"path":361,"priority":346},{"path":348,"priority":346},{"path":427,"priority":351},"agents/code-architect.md",{"path":429,"priority":351},"agents/code-explorer.md",{"path":431,"priority":351},"agents/code-reviewer.md",{"path":433,"priority":351},"commands/feature-dev.md",{"basePath":435,"description":436,"displayName":437,"installMethods":438,"rationale":439,"selectedPaths":440,"source":352,"sourceLanguage":18,"type":277},"plugins/frontend-design","Frontend design skill for UI/UX implementation","frontend-design",{"claudeCode":437},"plugin manifest at plugins/frontend-design/.claude-plugin/plugin.json",[441,442,443],{"path":361,"priority":346},{"path":348,"priority":346},{"path":444,"priority":380},"skills/frontend-design/SKILL.md",{"basePath":446,"description":447,"displayName":448,"installMethods":449,"rationale":450,"selectedPaths":451,"source":352,"sourceLanguage":18,"type":277},"plugins/hookify","Easily create hooks to prevent unwanted behaviors by analyzing conversation patterns","hookify",{"claudeCode":448},"plugin manifest at plugins/hookify/.claude-plugin/plugin.json",[452,453,454,456,458,460,462,464,466,468,469,471,473,475],{"path":361,"priority":346},{"path":348,"priority":346},{"path":455,"priority":380},"skills/writing-rules/SKILL.md",{"path":457,"priority":351},"agents/conversation-analyzer.md",{"path":459,"priority":351},"commands/configure.md",{"path":461,"priority":351},"commands/help.md",{"path":463,"priority":351},"commands/hookify.md",{"path":465,"priority":351},"commands/list.md",{"path":467,"priority":351},"hooks/__init__.py",{"path":416,"priority":351},{"path":470,"priority":351},"hooks/posttooluse.py",{"path":472,"priority":351},"hooks/pretooluse.py",{"path":474,"priority":351},"hooks/stop.py",{"path":476,"priority":351},"hooks/userpromptsubmit.py",{"basePath":478,"description":479,"displayName":480,"installMethods":481,"rationale":482,"selectedPaths":483,"source":352,"sourceLanguage":18,"type":277},"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":480},"plugin manifest at plugins/learning-output-style/.claude-plugin/plugin.json",[484,485,486],{"path":361,"priority":346},{"path":348,"priority":346},{"path":416,"priority":351},{"basePath":276,"description":271,"displayName":273,"installMethods":488,"rationale":489,"selectedPaths":490,"source":352,"sourceLanguage":18,"type":277},{"claudeCode":273},"inline plugin source from marketplace.json at plugins/plugin-dev",[491,492,494,496,498],{"path":348,"priority":346},{"path":493,"priority":351},"agents/agent-creator.md",{"path":495,"priority":351},"agents/plugin-validator.md",{"path":497,"priority":351},"agents/skill-reviewer.md",{"path":499,"priority":351},"commands/create-plugin.md",{"basePath":501,"description":502,"displayName":503,"installMethods":504,"rationale":505,"selectedPaths":506,"source":352,"sourceLanguage":18,"type":277},"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":503},"plugin manifest at plugins/pr-review-toolkit/.claude-plugin/plugin.json",[507,508,509,510,512,514,516,518,520],{"path":361,"priority":346},{"path":348,"priority":346},{"path":431,"priority":351},{"path":511,"priority":351},"agents/code-simplifier.md",{"path":513,"priority":351},"agents/comment-analyzer.md",{"path":515,"priority":351},"agents/pr-test-analyzer.md",{"path":517,"priority":351},"agents/silent-failure-hunter.md",{"path":519,"priority":351},"agents/type-design-analyzer.md",{"path":521,"priority":351},"commands/review-pr.md",{"basePath":523,"description":524,"displayName":525,"installMethods":526,"rationale":527,"selectedPaths":528,"source":352,"sourceLanguage":18,"type":277},"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":525},"plugin manifest at plugins/ralph-wiggum/.claude-plugin/plugin.json",[529,530,531,533,534,536,537],{"path":361,"priority":346},{"path":348,"priority":346},{"path":532,"priority":351},"commands/cancel-ralph.md",{"path":461,"priority":351},{"path":535,"priority":351},"commands/ralph-loop.md",{"path":416,"priority":351},{"path":538,"priority":351},"hooks/stop-hook.sh",{"basePath":540,"description":541,"displayName":542,"installMethods":543,"rationale":544,"selectedPaths":545,"source":352,"sourceLanguage":18,"type":277},"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":542},"plugin manifest at plugins/security-guidance/.claude-plugin/plugin.json",[546,547,548],{"path":361,"priority":346},{"path":416,"priority":351},{"path":549,"priority":351},"hooks/security_reminder_hook.py",{"basePath":551,"description":552,"displayName":372,"installMethods":553,"rationale":554,"selectedPaths":555,"source":352,"sourceLanguage":18,"type":265},"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",[556,558,560],{"path":557,"priority":346},"SKILL.md",{"path":559,"priority":380},"references/effort.md",{"path":561,"priority":380},"references/prompt-snippets.md",{"basePath":563,"description":564,"displayName":437,"installMethods":565,"rationale":566,"selectedPaths":567,"source":352,"sourceLanguage":18,"type":265},"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",[568],{"path":557,"priority":346},{"basePath":570,"description":571,"displayName":572,"installMethods":573,"rationale":574,"selectedPaths":575,"source":352,"sourceLanguage":18,"type":265},"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",[576],{"path":557,"priority":346},{"basePath":578,"description":579,"displayName":580,"installMethods":581,"rationale":582,"selectedPaths":583,"source":352,"sourceLanguage":18,"type":265},"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",[584,585,588,590,592,594,596],{"path":557,"priority":346},{"path":586,"priority":587},"examples/agent-creation-prompt.md","low",{"path":589,"priority":587},"examples/complete-agent-examples.md",{"path":591,"priority":380},"references/agent-creation-system-prompt.md",{"path":593,"priority":380},"references/system-prompt-design.md",{"path":595,"priority":380},"references/triggering-examples.md",{"path":597,"priority":587},"scripts/validate-agent.sh",{"basePath":599,"description":600,"displayName":601,"installMethods":602,"rationale":603,"selectedPaths":604,"source":352,"sourceLanguage":18,"type":265},"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",[605,606,607,609,611,613,615,617,619,621,623],{"path":557,"priority":346},{"path":348,"priority":351},{"path":608,"priority":587},"examples/plugin-commands.md",{"path":610,"priority":587},"examples/simple-commands.md",{"path":612,"priority":380},"references/advanced-workflows.md",{"path":614,"priority":380},"references/documentation-patterns.md",{"path":616,"priority":380},"references/frontmatter-reference.md",{"path":618,"priority":380},"references/interactive-commands.md",{"path":620,"priority":380},"references/marketplace-considerations.md",{"path":622,"priority":380},"references/plugin-features-reference.md",{"path":624,"priority":380},"references/testing-strategies.md",{"basePath":261,"description":10,"displayName":264,"installMethods":626,"rationale":627,"selectedPaths":628,"source":352,"sourceLanguage":18,"type":265},{"claudeCode":12},"SKILL.md frontmatter at plugins/plugin-dev/skills/hook-development/SKILL.md",[629,630,632,634,636,638,640,642,644,646,648],{"path":557,"priority":346},{"path":631,"priority":587},"examples/load-context.sh",{"path":633,"priority":587},"examples/validate-bash.sh",{"path":635,"priority":587},"examples/validate-write.sh",{"path":637,"priority":380},"references/advanced.md",{"path":639,"priority":380},"references/migration.md",{"path":641,"priority":380},"references/patterns.md",{"path":643,"priority":587},"scripts/README.md",{"path":645,"priority":587},"scripts/hook-linter.sh",{"path":647,"priority":587},"scripts/test-hook.sh",{"path":649,"priority":587},"scripts/validate-hook-schema.sh",{"basePath":651,"description":652,"displayName":653,"installMethods":654,"rationale":655,"selectedPaths":656,"source":352,"sourceLanguage":18,"type":265},"plugins/plugin-dev/skills/mcp-integration","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.","mcp-integration",{"claudeCode":12},"SKILL.md frontmatter at plugins/plugin-dev/skills/mcp-integration/SKILL.md",[657,658,660,662,664,666,668],{"path":557,"priority":346},{"path":659,"priority":587},"examples/http-server.json",{"path":661,"priority":587},"examples/sse-server.json",{"path":663,"priority":587},"examples/stdio-server.json",{"path":665,"priority":380},"references/authentication.md",{"path":667,"priority":380},"references/server-types.md",{"path":669,"priority":380},"references/tool-usage.md",{"basePath":671,"description":672,"displayName":673,"installMethods":674,"rationale":675,"selectedPaths":676,"source":352,"sourceLanguage":18,"type":265},"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",[677,678,680,682,684,686,688,690],{"path":557,"priority":346},{"path":679,"priority":587},"examples/create-settings-command.md",{"path":681,"priority":587},"examples/example-settings.md",{"path":683,"priority":587},"examples/read-settings-hook.sh",{"path":685,"priority":380},"references/parsing-techniques.md",{"path":687,"priority":380},"references/real-world-examples.md",{"path":689,"priority":587},"scripts/parse-frontmatter.sh",{"path":691,"priority":587},"scripts/validate-settings.sh",{"basePath":693,"description":694,"displayName":695,"installMethods":696,"rationale":697,"selectedPaths":698,"source":352,"sourceLanguage":18,"type":265},"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",[699,700,701,703,705,707,709],{"path":557,"priority":346},{"path":348,"priority":351},{"path":702,"priority":587},"examples/advanced-plugin.md",{"path":704,"priority":587},"examples/minimal-plugin.md",{"path":706,"priority":587},"examples/standard-plugin.md",{"path":708,"priority":380},"references/component-patterns.md",{"path":710,"priority":380},"references/manifest-reference.md",{"basePath":712,"description":713,"displayName":714,"installMethods":715,"rationale":716,"selectedPaths":717,"source":352,"sourceLanguage":18,"type":265},"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",[718,719],{"path":557,"priority":346},{"path":720,"priority":380},"references/skill-creator-original.md",{"sources":722},[723],"manual",{"closedIssues90d":249,"description":725,"forks":250,"homepage":726,"openIssues90d":252,"pushedAt":253,"readmeSize":247,"stars":254,"topics":727},"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":729,"discoverAt":730,"extractAt":731,"githubAt":731,"updatedAt":729},1778675383497,1778675378145,1778675381570,[220,222,219,221,223,224],{"evaluatedAt":259,"extractAt":312,"updatedAt":259},[],[736,765,797,825,846,875],{"_creationTime":737,"_id":738,"community":739,"display":740,"identity":746,"providers":750,"relations":758,"tags":761,"workflow":762},1778696595410.5671,"k17anj41t8hgk7k78wc98gw6a186n8ks",{"reviewCount":8},{"description":741,"installMethods":742,"name":744,"sourceUrl":745},"Prevent destructive operations using Claude Code hooks. Three modes — cautious (warn on dangerous commands), lockdown (restrict edits to one directory), and clear (remove restrictions). Uses PreToolUse matchers for Bash, Edit, and Write.",{"claudeCode":743},"rohitg00/pro-workflow","safe-mode","https://github.com/rohitg00/pro-workflow",{"basePath":747,"githubOwner":748,"githubRepo":749,"locale":18,"slug":744,"type":265},"skills/safe-mode","rohitg00","pro-workflow",{"evaluate":751,"extract":757},{"promptVersionExtension":212,"promptVersionScoring":213,"score":752,"tags":753,"targetMarket":225,"tier":226},100,[224,754,755,756,219],"guardrails","operations","code-quality",{"commitSha":301},{"parentExtensionId":759,"repoId":760},"k17fxtjcfh5gvxdrhv2dmgn1t986mdhv","kd7am4e918eq98hrd9s31jm4vs86nn0b",[756,754,219,755,224],{"evaluatedAt":763,"extractAt":764,"updatedAt":763},1778696971063,1778696595410,{"_creationTime":766,"_id":767,"community":768,"display":769,"identity":775,"providers":780,"relations":790,"tags":793,"workflow":794},1778699234184.6157,"k177tdbfgqmwhtaqv771f2ych586nne9",{"reviewCount":8},{"description":770,"installMethods":771,"name":773,"sourceUrl":774},"Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions",{"claudeCode":772},"Yeachan-Heo/oh-my-claudecode","Project Session Manager","https://github.com/Yeachan-Heo/oh-my-claudecode",{"basePath":776,"githubOwner":777,"githubRepo":778,"locale":18,"slug":779,"type":265},"skills/project-session-manager","Yeachan-Heo","oh-my-claudecode","project-session-manager",{"evaluate":781,"extract":789},{"promptVersionExtension":212,"promptVersionScoring":213,"score":752,"tags":782,"targetMarket":225,"tier":226},[783,784,785,786,220,787,788],"git","development-environment","workflow","tmux","cli","developer-tool",{"commitSha":301,"license":321},{"parentExtensionId":791,"repoId":792},"k17brg5egdw1jbncj1j4wfv3fh86n639","kd74zv63fryf9prygtq7gf4es986n22y",[220,787,788,784,783,786,785],{"evaluatedAt":795,"extractAt":796,"updatedAt":795},1778699613343,1778699234184,{"_creationTime":798,"_id":799,"community":800,"display":801,"identity":807,"providers":810,"relations":817,"tags":820,"workflow":821},1778699505679.3464,"k1751nm85mw95gw3rsqgrdqspx86ncq2",{"reviewCount":8},{"description":802,"installMethods":803,"name":805,"sourceUrl":806},"无需 OAuth 即可创建公开的 Google Docs 或 Google Sheet 文件。使用此技能创建和编辑 Google Docs 和 Sheets，无需登录 Google。文档可通过共享链接查看。首次使用时自动注册。",{"claudeCode":804},"zagmoai/public-google-drive","public-google-drive","https://github.com/zagmoai/public-google-drive",{"basePath":287,"githubOwner":808,"githubRepo":805,"locale":809,"slug":805,"type":265},"zagmoai","zh-CN",{"evaluate":811,"extract":816},{"promptVersionExtension":212,"promptVersionScoring":213,"score":752,"tags":812,"targetMarket":225,"tier":226},[813,814,296,220,815],"google-docs","google-sheets","api-client",{"commitSha":301},{"repoId":818,"translatedFrom":819},"kd776ynh73t0d6samn4bnxdf3x86n8mj","k1707pszx7h026a651dp5tvaxd86m3ag",[815,220,813,814,296],{"evaluatedAt":822,"extractAt":823,"updatedAt":824},1778699485884,1778699468747,1778699505679,{"_creationTime":826,"_id":827,"community":828,"display":829,"identity":832,"providers":835,"relations":842,"tags":843,"workflow":844},1778699234184.611,"k179b6dkc777g1rgyecze04wqn86m6y4",{"reviewCount":8},{"description":830,"installMethods":831,"name":778,"sourceUrl":774},"Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly",{"claudeCode":772},{"basePath":833,"githubOwner":777,"githubRepo":778,"locale":18,"slug":834,"type":265},"skills/ask","ask",{"evaluate":836,"extract":841},{"promptVersionExtension":212,"promptVersionScoring":213,"score":752,"tags":837,"targetMarket":225,"tier":226},[787,220,838,839,297,840],"llm","prompting","artifact-generation",{"commitSha":301,"license":321},{"parentExtensionId":791,"repoId":792},[840,220,787,297,838,839],{"evaluatedAt":845,"extractAt":796,"updatedAt":845},1778699303045,{"_creationTime":847,"_id":848,"community":849,"display":850,"identity":856,"providers":860,"relations":867,"tags":870,"workflow":871},1778699366078.7817,"k173mj3k9wcdq512bp1532xkwx86nrh4",{"reviewCount":8},{"description":851,"installMethods":852,"name":854,"sourceUrl":855},"当工作依赖于用户实时浏览器会话或可见的渲染状态，而不是静态抓取时使用，尤其是在浏览器调试上下文或 DevTools 选择的元素或请求、登录仪表板或 CMS 流程、localhost 应用、上传、下载、媒体检查、DOM 或 iframe 检查、Shadow DOM，或看起来像软 404、身份验证墙、反机器人检查或速率限制的浏览器故障时。",{"claudeCode":853},"xixu-me/skills","使用我的浏览器","https://github.com/xixu-me/skills",{"basePath":857,"githubOwner":858,"githubRepo":316,"locale":809,"slug":859,"type":265},"skills/use-my-browser","xixu-me","use-my-browser",{"evaluate":861,"extract":866},{"promptVersionExtension":212,"promptVersionScoring":213,"score":752,"tags":862,"targetMarket":225,"tier":226},[863,864,220,865,319],"browser","debugging","ux",{"commitSha":301,"license":321},{"repoId":868,"translatedFrom":869},"kd77r2vb42jmgam0qbr9f2c6kn86mebv","k179cgk616p3xva37r5jqsfwvh86mcp2",[220,863,864,319,865],{"evaluatedAt":872,"extractAt":873,"updatedAt":874},1778699261239,1778699106670,1778699366078,{"_creationTime":876,"_id":877,"community":878,"display":879,"identity":885,"providers":888,"relations":897,"tags":901,"workflow":902},1778699289329.1182,"k172jykxz0jywjekjxjt5thj5x86nm3n",{"reviewCount":8},{"description":880,"installMethods":881,"name":883,"sourceUrl":884},"当用户需要通过 Xquik 获取 X (Twitter) 数据或执行需要确认的 X 操作时使用：推文搜索、用户查找、关注者提取、媒体下载、监控、Webhook、MCP、SDK、发布、点赞、私信和个人资料更新。需要 Xquik API 密钥。切勿索要 X 登录凭据。",{"claudeCode":882},"Xquik-dev/x-twitter-scraper","x-twitter-scraper","https://github.com/Xquik-dev/x-twitter-scraper",{"basePath":886,"githubOwner":887,"githubRepo":883,"locale":809,"slug":883,"type":265},"skills/x-twitter-scraper","Xquik-dev",{"evaluate":889,"extract":896},{"promptVersionExtension":212,"promptVersionScoring":213,"score":752,"tags":890,"targetMarket":225,"tier":226},[891,892,893,894,220,318,895],"twitter","x","api","data-retrieval","sdk",{"commitSha":301},{"parentExtensionId":898,"repoId":899,"translatedFrom":900},"k17axvhmvwp90strpqcd5b0h7986m80d","kd783enpnwhry153ka0z65ear186mjbh","k172e8vt4zcz50bb0vfp6ptb1n86mf90",[893,220,894,318,895,891,892],{"evaluatedAt":903,"extractAt":904,"updatedAt":905},1778699230863,1778699170774,1778699289329]