[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-EveryInc-ce-agent-native-architecture-de":3,"guides-for-EveryInc-ce-agent-native-architecture":1157,"similar-k1707vz5f4n2fekq7yaeze1kmh86ngya-de":1158},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":253,"isFallback":234,"parentExtension":258,"providers":317,"relations":321,"repo":322,"tags":1155,"workflow":1156},1778686640222.7913,"k1707vz5f4n2fekq7yaeze1kmh86ngya",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.",{"claudeCode":12},"EveryInc/compound-engineering-plugin","ce-agent-native-architecture","https://github.com/EveryInc/compound-engineering-plugin",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":232,"workflow":251},1778686750170.3557,"kn7dvwvz356xvwag9n4j0wx3fs86ngj7","en",{"checks":20,"evaluatedAt":191,"extensionSummary":192,"features":193,"nonGoals":201,"practices":205,"prerequisites":211,"promptVersionExtension":212,"promptVersionScoring":213,"purpose":214,"rationale":215,"score":216,"summary":217,"tags":218,"targetMarket":225,"tier":226,"useCases":227},[21,26,29,32,36,39,44,48,51,54,58,62,65,69,72,75,78,81,84,87,90,94,98,102,106,109,112,115,119,122,125,128,131,134,137,141,145,149,152,156,159,162,165,168,172,175,178,181,184,188],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly outlines the problem of building agent-native applications where agents are first-class citizens and features are outcomes, targeting users designing autonomous agents or self-modifying systems.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill focuses on agent-native architecture principles like parity, granularity, and composability, which go beyond basic agent functionality and offer a distinct architectural approach.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill provides a comprehensive set of patterns, references, and principles for designing and building agent-native applications, covering the full lifecycle from design to testing and deployment.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses exclusively on agent-native architecture principles and patterns, without venturing into unrelated domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the skill's purpose of guiding users in building agent-native applications and lists relevant use cases.",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","This is a skill, not a tool-based extension; the check for scoped tools is not applicable.",{"category":45,"check":46,"severity":42,"summary":47},"Documentation","Configuration & parameter reference","As a skill, it does not expose parameters or configuration options directly to the end-user.",{"category":33,"check":49,"severity":42,"summary":50},"Tool naming","This is a skill, not a tool-based extension; the check for tool naming is not applicable.",{"category":33,"check":52,"severity":42,"summary":53},"Minimal I/O surface","This is a skill, not a tool-based extension; the check for minimal I/O surface is not applicable.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The extension is licensed under MIT, a permissive open-source license.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The repository shows recent commits within the last 3 months.",{"category":59,"check":63,"severity":24,"summary":64},"Dependency Management","The project has a lockfile and CI, suggesting good dependency management practices.",{"category":66,"check":67,"severity":42,"summary":68},"Security","Secret Management","The skill itself does not appear to handle secrets directly; it's an architectural guide.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill provides guidance on secure practices, including file scoping and handling untrusted data, which implies awareness of injection risks.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill focuses on architecture and principles; it does not fetch remote code or markdown to execute, and its references are internal.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill is a guide and does not include executable code that would interact with the file system or system outside its own bundle's references.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","The skill provides architectural guidance and does not contain scripts with sandbox escape primitives.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill itself does not perform outbound calls or handle confidential data; it's a guide.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled markdown files appear to be free of hidden steering tricks or obfuscation.",{"category":66,"check":88,"severity":24,"summary":89},"Opaque code execution","The skill provides markdown references and architectural guidance, with no opaque code execution.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The skill discusses file organization and patterns but does not make rigid assumptions about user-specific project structures, offering guidance instead.",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","With 25 open and 115 closed issues in the last 90 days, the closure rate is well above 50%, indicating active maintenance.",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","The project has a CHANGELOG and npm versioning, indicating clear release management.",{"category":103,"check":104,"severity":42,"summary":105},"Code Execution","Validation","This skill is purely documentation and guidance, with no executable code that requires input validation.",{"category":66,"check":107,"severity":42,"summary":108},"Unguarded Destructive Operations","The skill provides guidance and does not perform any destructive operations.",{"category":103,"check":110,"severity":42,"summary":111},"Error Handling","This skill is documentation and does not have executable code paths that can produce errors.",{"category":103,"check":113,"severity":42,"summary":114},"Logging","This skill is documentation and does not perform actions that require logging.",{"category":116,"check":117,"severity":42,"summary":118},"Compliance","GDPR","The skill is a guide and does not operate on personal data.",{"category":116,"check":120,"severity":24,"summary":121},"Target market","The skill provides general architectural guidance applicable globally, with no specific regional limitations detected.",{"category":91,"check":123,"severity":24,"summary":124},"Runtime stability","The skill is documentation and does not rely on specific runtimes or OS features.",{"category":45,"check":126,"severity":24,"summary":127},"README","The README file is comprehensive, detailing the philosophy, workflow, examples, and installation for multiple platforms.",{"category":33,"check":129,"severity":42,"summary":130},"Tool surface size","This is a skill, not a tool-based extension; the check for tool surface size is not applicable.",{"category":40,"check":132,"severity":42,"summary":133},"Overlapping near-synonym tools","This is a skill, not a tool-based extension; the check for overlapping tools is not applicable.",{"category":45,"check":135,"severity":24,"summary":136},"Phantom features","All features discussed in the documentation, such as specific patterns and principles, are elaborated upon in the reference files.",{"category":138,"check":139,"severity":24,"summary":140},"Install","Installation instruction","Comprehensive installation instructions are provided for multiple platforms, including Claude Code, Cursor, Copilot, and others, with clear copy-paste examples.",{"category":142,"check":143,"severity":42,"summary":144},"Errors","Actionable error messages","This skill is documentation and does not have user-facing error paths.",{"category":146,"check":147,"severity":42,"summary":148},"Execution","Pinned dependencies","The skill itself does not contain bundled scripts with dependencies.",{"category":33,"check":150,"severity":42,"summary":151},"Dry-run preview","This skill is documentation and does not perform state-changing operations.",{"category":153,"check":154,"severity":42,"summary":155},"Protocol","Idempotent retry & timeouts","This skill is documentation and does not involve remote calls or state-changing operations.",{"category":116,"check":157,"severity":42,"summary":158},"Telemetry opt-in","The skill is a guide and does not emit telemetry.",{"category":40,"check":160,"severity":24,"summary":161},"Precise Purpose","The description clearly states the purpose of building agent-native applications and provides specific use cases like designing autonomous agents and creating MCP tools.",{"category":40,"check":163,"severity":24,"summary":164},"Concise Frontmatter","The frontmatter is concise and self-contained, effectively summarizing the core capability of building agent-native applications.",{"category":45,"check":166,"severity":24,"summary":167},"Concise Body","The SKILL.md body is well-structured with references, keeping the main content concise and leveraging progressive disclosure.",{"category":169,"check":170,"severity":24,"summary":171},"Context","Progressive Disclosure","The skill extensively uses reference files for deep coverage of patterns, principles, and specific disciplines, adhering to progressive disclosure.",{"category":169,"check":173,"severity":42,"summary":174},"Forked exploration","The skill is a guide and does not involve deep exploration that would benefit from forking.",{"category":22,"check":176,"severity":24,"summary":177},"Usage examples","The documentation includes numerous examples across various reference files demonstrating how to apply the principles and patterns described.",{"category":22,"check":179,"severity":24,"summary":180},"Edge cases","The referenced files discuss potential limitations and considerations like context limits, conflict models, and mobile-specific challenges, offering recovery paths.",{"category":103,"check":182,"severity":42,"summary":183},"Tool Fallback","This skill is documentation and does not reference external tools that would require fallbacks.",{"category":185,"check":186,"severity":24,"summary":187},"Safety","Halt on unexpected state","The architectural guidance emphasizes clear decision-making, approval gates, and understanding context, implicitly guiding towards halting on unexpected states.",{"category":91,"check":189,"severity":24,"summary":190},"Cross-skill coupling","The skill is self-contained and provides guidance on integrating with other agent types and tools, rather than relying on implicit coupling.",1778686749952,"This skill provides a deep dive into agent-native architecture, explaining how to design applications where agents are first-class citizens. It covers core principles like parity, granularity, and composability, along with practical patterns for tool design, file organization, context injection, and execution strategies.",[194,195,196,197,198,199,200],"Agent-native architecture principles","Tool design primitives","File organization and context.md","Dynamic context injection","Execution patterns and model tier selection","Self-modification capabilities","Testing and product design implications",[202,203,204],"Providing specific code implementations for every pattern","Replacing detailed API documentation","Dictating a single rigid architectural choice",[206,207,208,209,210],"Agent-native design","Tool design","System prompt engineering","Testing","Self-modification",[],"3.0.0","4.4.0","To guide developers in building sophisticated agent-native applications by establishing core architectural principles and practical patterns.","The skill is exceptionally well-documented and comprehensive, covering all aspects of agent-native architecture with clear principles, patterns, and practical examples. Installation and development guidance are thorough, and maintenance signals are strong.",99,"An expert guide to building agent-native applications, covering core principles, tools, execution, and product design.",[219,220,221,222,223,224],"agent-native","architecture","llm","prompt-engineering","development","mobile","global","verified",[228,229,230,231],"Designing new autonomous agent systems","Implementing self-modifying agent applications","Building applications where features are agent outcomes","Creating MCP tools with atomic primitives",{"codeQuality":233,"collectedAt":235,"documentation":236,"maintenance":239,"popularity":245,"security":247,"testCoverage":250},{"hasLockfile":234},true,1778686742334,{"descriptionLength":237,"readmeSize":238},248,17582,{"closedIssues90d":240,"forks":241,"hasChangelog":234,"openIssues90d":242,"pushedAt":243,"stars":244},115,1300,25,1778686215000,16666,{"npmDownloads":246},12828,{"hasNpmPackage":234,"license":248,"smitheryVerified":249},"MIT",false,{"hasCi":234,"hasTests":234},{"updatedAt":252},1778686750170,{"basePath":254,"githubOwner":255,"githubRepo":256,"locale":18,"slug":13,"type":257},"plugins/compound-engineering/skills/ce-agent-native-architecture","EveryInc","compound-engineering-plugin","skill",{"_creationTime":259,"_id":260,"community":261,"display":262,"identity":266,"parentExtension":269,"providers":301,"relations":313,"tags":314,"workflow":315},1778686640222.7903,"k17d893df4em0e3pn8f55h1dxn86n09e",{"reviewCount":8},{"description":263,"installMethods":264,"name":265,"sourceUrl":14},"AI-powered development tools for code review, research, design, and workflow automation.",{"claudeCode":265},"compound-engineering",{"basePath":267,"githubOwner":255,"githubRepo":256,"locale":18,"slug":265,"type":268},"plugins/compound-engineering","plugin",{"_creationTime":270,"_id":271,"community":272,"display":273,"identity":277,"providers":280,"relations":295,"tags":297,"workflow":298},1778686640222.7908,"k17ef8php9wk308mkg59kdp6b186nzhx",{"reviewCount":8},{"description":274,"installMethods":275,"name":276,"sourceUrl":14},"Cursor plugin marketplace for Every Inc plugins",{"claudeCode":12},"Compound Engineering",{"basePath":278,"githubOwner":255,"githubRepo":256,"locale":18,"slug":256,"type":279},"","marketplace",{"evaluate":281,"extract":289},{"promptVersionExtension":282,"promptVersionScoring":213,"score":216,"tags":283,"targetMarket":225,"tier":226},"3.1.0",[284,285,286,287,288],"development-workflow","code-review","planning","documentation","ai-agents",{"commitSha":290,"license":248,"marketplace":291,"plugin":293},"HEAD",{"name":256,"pluginCount":292},2,{"mcpCount":8,"provider":294,"skillCount":8},"classify",{"repoId":296},"kd7e40my1b5g70tg0f60qg85ch86nn08",[288,285,284,287,286],{"evaluatedAt":299,"extractAt":300,"updatedAt":299},1778686722515,1778686640222,{"evaluate":302,"extract":310},{"promptVersionExtension":212,"promptVersionScoring":213,"score":303,"tags":304,"targetMarket":225,"tier":226},98,[305,306,285,307,287,308,286,309],"ai","developer-tools","research","workflow-automation","ideation",{"commitSha":290,"license":248,"plugin":311},{"mcpCount":8,"provider":294,"skillCount":312},37,{"parentExtensionId":271,"repoId":296},[305,285,306,287,309,286,307,308],{"evaluatedAt":316,"extractAt":300,"updatedAt":316},1778686677611,{"evaluate":318,"extract":320},{"promptVersionExtension":212,"promptVersionScoring":213,"score":216,"tags":319,"targetMarket":225,"tier":226},[219,220,221,222,223,224],{"commitSha":290,"license":248},{"parentExtensionId":260,"repoId":296},{"_creationTime":323,"_id":296,"identity":324,"providers":325,"workflow":1150},1778686632796.9226,{"githubOwner":255,"githubRepo":256,"sourceUrl":14},{"classify":326,"discover":1139,"extract":1142,"github":1143,"npm":1149},{"commitSha":290,"extensions":327},[328,337,525,544,552,569,604,612,630,640,666,674,686,702,716,730,750,770,787,795,813,827,855,873,911,923,933,943,951,971,989,1005,1017,1025,1033,1044,1052,1060,1074,1085,1097,1107,1116],{"basePath":329,"displayName":256,"installMethods":330,"rationale":331,"selectedPaths":332,"source":336,"sourceLanguage":18,"type":279},".agents/plugins",{"claudeCode":12},"marketplace.json at .agents/plugins/marketplace.json (coalesced with duplicate marketplace at /)",[333],{"path":334,"priority":335},"marketplace.json","mandatory","rule",{"basePath":267,"description":263,"displayName":265,"installMethods":338,"license":248,"rationale":339,"selectedPaths":340,"source":336,"sourceLanguage":18,"type":268},{"claudeCode":265},"plugin manifest at plugins/compound-engineering/.claude-plugin/plugin.json",[341,343,345,348,351,353,355,357,359,361,363,365,367,369,371,373,375,377,379,381,383,385,387,389,391,393,395,397,399,401,403,405,407,409,411,413,415,417,419,421,423,425,427,429,431,433,435,437,439,441,443,445,447,449,451,453,455,457,459,461,463,465,467,469,471,473,475,477,479,481,483,485,487,489,491,493,495,497,499,501,503,505,507,509,511,513,515,517,519,521,523],{"path":342,"priority":335},".claude-plugin/plugin.json",{"path":344,"priority":335},"README.md",{"path":346,"priority":347},"LICENSE","high",{"path":349,"priority":350},"skills/ce-agent-native-architecture/SKILL.md","medium",{"path":352,"priority":350},"skills/ce-agent-native-audit/SKILL.md",{"path":354,"priority":350},"skills/ce-brainstorm/SKILL.md",{"path":356,"priority":350},"skills/ce-clean-gone-branches/SKILL.md",{"path":358,"priority":350},"skills/ce-code-review/SKILL.md",{"path":360,"priority":350},"skills/ce-commit/SKILL.md",{"path":362,"priority":350},"skills/ce-commit-push-pr/SKILL.md",{"path":364,"priority":350},"skills/ce-compound/SKILL.md",{"path":366,"priority":350},"skills/ce-compound-refresh/SKILL.md",{"path":368,"priority":350},"skills/ce-debug/SKILL.md",{"path":370,"priority":350},"skills/ce-demo-reel/SKILL.md",{"path":372,"priority":350},"skills/ce-dhh-rails-style/SKILL.md",{"path":374,"priority":350},"skills/ce-doc-review/SKILL.md",{"path":376,"priority":350},"skills/ce-frontend-design/SKILL.md",{"path":378,"priority":350},"skills/ce-gemini-imagegen/SKILL.md",{"path":380,"priority":350},"skills/ce-ideate/SKILL.md",{"path":382,"priority":350},"skills/ce-optimize/SKILL.md",{"path":384,"priority":350},"skills/ce-plan/SKILL.md",{"path":386,"priority":350},"skills/ce-polish-beta/SKILL.md",{"path":388,"priority":350},"skills/ce-product-pulse/SKILL.md",{"path":390,"priority":350},"skills/ce-proof/SKILL.md",{"path":392,"priority":350},"skills/ce-release-notes/SKILL.md",{"path":394,"priority":350},"skills/ce-report-bug/SKILL.md",{"path":396,"priority":350},"skills/ce-resolve-pr-feedback/SKILL.md",{"path":398,"priority":350},"skills/ce-riffrec-feedback-analysis/SKILL.md",{"path":400,"priority":350},"skills/ce-sessions/SKILL.md",{"path":402,"priority":350},"skills/ce-setup/SKILL.md",{"path":404,"priority":350},"skills/ce-simplify-code/SKILL.md",{"path":406,"priority":350},"skills/ce-slack-research/SKILL.md",{"path":408,"priority":350},"skills/ce-strategy/SKILL.md",{"path":410,"priority":350},"skills/ce-test-browser/SKILL.md",{"path":412,"priority":350},"skills/ce-test-xcode/SKILL.md",{"path":414,"priority":350},"skills/ce-update/SKILL.md",{"path":416,"priority":350},"skills/ce-work/SKILL.md",{"path":418,"priority":350},"skills/ce-work-beta/SKILL.md",{"path":420,"priority":350},"skills/ce-worktree/SKILL.md",{"path":422,"priority":350},"skills/lfg/SKILL.md",{"path":424,"priority":347},"agents/ce-adversarial-document-reviewer.agent.md",{"path":426,"priority":347},"agents/ce-adversarial-reviewer.agent.md",{"path":428,"priority":347},"agents/ce-agent-native-reviewer.agent.md",{"path":430,"priority":347},"agents/ce-ankane-readme-writer.agent.md",{"path":432,"priority":347},"agents/ce-api-contract-reviewer.agent.md",{"path":434,"priority":347},"agents/ce-architecture-strategist.agent.md",{"path":436,"priority":347},"agents/ce-best-practices-researcher.agent.md",{"path":438,"priority":347},"agents/ce-code-simplicity-reviewer.agent.md",{"path":440,"priority":347},"agents/ce-coherence-reviewer.agent.md",{"path":442,"priority":347},"agents/ce-correctness-reviewer.agent.md",{"path":444,"priority":347},"agents/ce-data-integrity-guardian.agent.md",{"path":446,"priority":347},"agents/ce-data-migration-expert.agent.md",{"path":448,"priority":347},"agents/ce-data-migrations-reviewer.agent.md",{"path":450,"priority":347},"agents/ce-deployment-verification-agent.agent.md",{"path":452,"priority":347},"agents/ce-design-implementation-reviewer.agent.md",{"path":454,"priority":347},"agents/ce-design-iterator.agent.md",{"path":456,"priority":347},"agents/ce-design-lens-reviewer.agent.md",{"path":458,"priority":347},"agents/ce-dhh-rails-reviewer.agent.md",{"path":460,"priority":347},"agents/ce-feasibility-reviewer.agent.md",{"path":462,"priority":347},"agents/ce-figma-design-sync.agent.md",{"path":464,"priority":347},"agents/ce-framework-docs-researcher.agent.md",{"path":466,"priority":347},"agents/ce-git-history-analyzer.agent.md",{"path":468,"priority":347},"agents/ce-issue-intelligence-analyst.agent.md",{"path":470,"priority":347},"agents/ce-julik-frontend-races-reviewer.agent.md",{"path":472,"priority":347},"agents/ce-kieran-python-reviewer.agent.md",{"path":474,"priority":347},"agents/ce-kieran-rails-reviewer.agent.md",{"path":476,"priority":347},"agents/ce-kieran-typescript-reviewer.agent.md",{"path":478,"priority":347},"agents/ce-learnings-researcher.agent.md",{"path":480,"priority":347},"agents/ce-maintainability-reviewer.agent.md",{"path":482,"priority":347},"agents/ce-pattern-recognition-specialist.agent.md",{"path":484,"priority":347},"agents/ce-performance-oracle.agent.md",{"path":486,"priority":347},"agents/ce-performance-reviewer.agent.md",{"path":488,"priority":347},"agents/ce-pr-comment-resolver.agent.md",{"path":490,"priority":347},"agents/ce-previous-comments-reviewer.agent.md",{"path":492,"priority":347},"agents/ce-product-lens-reviewer.agent.md",{"path":494,"priority":347},"agents/ce-project-standards-reviewer.agent.md",{"path":496,"priority":347},"agents/ce-reliability-reviewer.agent.md",{"path":498,"priority":347},"agents/ce-repo-research-analyst.agent.md",{"path":500,"priority":347},"agents/ce-schema-drift-detector.agent.md",{"path":502,"priority":347},"agents/ce-scope-guardian-reviewer.agent.md",{"path":504,"priority":347},"agents/ce-security-lens-reviewer.agent.md",{"path":506,"priority":347},"agents/ce-security-reviewer.agent.md",{"path":508,"priority":347},"agents/ce-security-sentinel.agent.md",{"path":510,"priority":347},"agents/ce-session-historian.agent.md",{"path":512,"priority":347},"agents/ce-slack-researcher.agent.md",{"path":514,"priority":347},"agents/ce-spec-flow-analyzer.agent.md",{"path":516,"priority":347},"agents/ce-swift-ios-reviewer.agent.md",{"path":518,"priority":347},"agents/ce-testing-reviewer.agent.md",{"path":520,"priority":347},"agents/ce-web-researcher.agent.md",{"path":522,"priority":347},".codex-plugin/plugin.json",{"path":524,"priority":347},".cursor-plugin/plugin.json",{"basePath":526,"description":527,"displayName":528,"installMethods":529,"rationale":530,"selectedPaths":531,"source":336,"sourceLanguage":18,"type":268},"plugins/coding-tutor","Personalized coding tutorials that use your actual codebase for examples with spaced repetition quizzes","coding-tutor",{"claudeCode":528},"plugin manifest at plugins/coding-tutor/.claude-plugin/plugin.json",[532,533,534,536,538,540,542,543],{"path":342,"priority":335},{"path":344,"priority":335},{"path":535,"priority":350},"skills/coding-tutor/SKILL.md",{"path":537,"priority":347},"commands/quiz-me.md",{"path":539,"priority":347},"commands/sync-tutorials.md",{"path":541,"priority":347},"commands/teach-me.md",{"path":522,"priority":347},{"path":524,"priority":347},{"basePath":278,"description":274,"displayName":265,"installMethods":545,"rationale":546,"selectedPaths":547,"source":336,"sourceLanguage":18,"type":279},{"claudeCode":12},"marketplace.json at .cursor-plugin/marketplace.json",[548,550,551],{"path":549,"priority":335},".cursor-plugin/marketplace.json",{"path":344,"priority":335},{"path":346,"priority":347},{"basePath":553,"description":554,"displayName":528,"installMethods":555,"rationale":556,"selectedPaths":557,"source":336,"sourceLanguage":18,"type":257},"plugins/coding-tutor/skills/coding-tutor","Personalized coding tutorials that build on your existing knowledge and use your actual codebase for examples. Creates a persistent learning trail that compounds over time using the power of AI, spaced repetition and quizes.",{"claudeCode":12},"SKILL.md frontmatter at plugins/coding-tutor/skills/coding-tutor/SKILL.md",[558,560,563,565,567],{"path":559,"priority":335},"SKILL.md",{"path":561,"priority":562},"scripts/create_tutorial.py","low",{"path":564,"priority":562},"scripts/index_tutorials.py",{"path":566,"priority":562},"scripts/quiz_priority.py",{"path":568,"priority":562},"scripts/setup_tutorials.py",{"basePath":254,"description":10,"displayName":13,"installMethods":570,"rationale":571,"selectedPaths":572,"source":336,"sourceLanguage":18,"type":257},{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-agent-native-architecture/SKILL.md",[573,574,576,578,580,582,584,586,588,590,592,594,596,598,600,602],{"path":559,"priority":335},{"path":575,"priority":350},"references/action-parity-discipline.md",{"path":577,"priority":350},"references/agent-execution-patterns.md",{"path":579,"priority":350},"references/agent-native-testing.md",{"path":581,"priority":350},"references/architecture-patterns.md",{"path":583,"priority":350},"references/checklists.md",{"path":585,"priority":350},"references/dynamic-context-injection.md",{"path":587,"priority":350},"references/files-universal-interface.md",{"path":589,"priority":350},"references/from-primitives-to-domain-tools.md",{"path":591,"priority":350},"references/mcp-tool-design.md",{"path":593,"priority":350},"references/mobile-patterns.md",{"path":595,"priority":350},"references/product-implications.md",{"path":597,"priority":350},"references/refactoring-to-prompt-native.md",{"path":599,"priority":350},"references/self-modification.md",{"path":601,"priority":350},"references/shared-workspace-architecture.md",{"path":603,"priority":350},"references/system-prompt-design.md",{"basePath":605,"description":606,"displayName":607,"installMethods":608,"rationale":609,"selectedPaths":610,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-agent-native-audit","Run comprehensive agent-native architecture review with scored principles","ce-agent-native-audit",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-agent-native-audit/SKILL.md",[611],{"path":559,"priority":335},{"basePath":613,"description":614,"displayName":615,"installMethods":616,"rationale":617,"selectedPaths":618,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-brainstorm","Explore requirements and approaches through collaborative dialogue, then write a right-sized requirements document. Use when the user says \"let's brainstorm\", \"what should we build\", or \"help me think through X\", presents a vague or ambitious feature request, or seems unsure about scope or direction -- even without explicitly asking to brainstorm.","ce-brainstorm",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-brainstorm/SKILL.md",[619,620,622,624,626,628],{"path":559,"priority":335},{"path":621,"priority":350},"references/handoff.md",{"path":623,"priority":350},"references/requirements-capture.md",{"path":625,"priority":350},"references/synthesis-summary.md",{"path":627,"priority":350},"references/universal-brainstorming.md",{"path":629,"priority":350},"references/visual-communication.md",{"basePath":631,"description":632,"displayName":633,"installMethods":634,"rationale":635,"selectedPaths":636,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-clean-gone-branches","Clean up local branches whose remote tracking branch is gone. Use when the user says \"clean up branches\", \"delete gone branches\", \"prune local branches\", \"clean gone\", or wants to remove stale local branches that no longer exist on the remote. Also handles removing associated worktrees for branches that have them.","ce-clean-gone-branches",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-clean-gone-branches/SKILL.md",[637,638],{"path":559,"priority":335},{"path":639,"priority":562},"scripts/clean-gone",{"basePath":641,"description":642,"displayName":643,"installMethods":644,"rationale":645,"selectedPaths":646,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-code-review","Structured code review using tiered persona agents, confidence-gated findings, and a merge/dedup pipeline. Use when reviewing code changes before creating a PR.","ce-code-review",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-code-review/SKILL.md",[647,648,650,652,654,656,658,660,662,664],{"path":559,"priority":335},{"path":649,"priority":350},"references/bulk-preview.md",{"path":651,"priority":350},"references/diff-scope.md",{"path":653,"priority":350},"references/findings-schema.json",{"path":655,"priority":350},"references/persona-catalog.md",{"path":657,"priority":350},"references/review-output-template.md",{"path":659,"priority":350},"references/subagent-template.md",{"path":661,"priority":350},"references/tracker-defer.md",{"path":663,"priority":350},"references/validator-template.md",{"path":665,"priority":350},"references/walkthrough.md",{"basePath":667,"description":668,"displayName":669,"installMethods":670,"rationale":671,"selectedPaths":672,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-commit","Create a git commit with a clear, value-communicating message. Use when the user says \"commit\", \"commit this\", \"save my changes\", \"create a commit\", or wants to commit staged or unstaged work. Produces well-structured commit messages that follow repo conventions when they exist, and defaults to conventional commit format otherwise.","ce-commit",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-commit/SKILL.md",[673],{"path":559,"priority":335},{"basePath":675,"description":676,"displayName":677,"installMethods":678,"rationale":679,"selectedPaths":680,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-commit-push-pr","Commit, push, and open a PR with an adaptive, value-first description that scales in depth with the change. Use when the user says \"commit and PR\", \"ship this\", \"create a PR\", or \"open a pull request\". Also handles description-only flows (\"write a PR description\", \"rewrite the PR body\", \"describe this PR\") without committing or pushing.","ce-commit-push-pr",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-commit-push-pr/SKILL.md",[681,682,684],{"path":559,"priority":335},{"path":683,"priority":350},"references/branch-creation.md",{"path":685,"priority":350},"references/pr-description-writing.md",{"basePath":687,"description":688,"displayName":689,"installMethods":690,"rationale":691,"selectedPaths":692,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-compound","Document a recently solved problem to compound your team's knowledge","ce-compound",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-compound/SKILL.md",[693,694,696,698,700],{"path":559,"priority":335},{"path":695,"priority":562},"assets/resolution-template.md",{"path":697,"priority":350},"references/schema.yaml",{"path":699,"priority":350},"references/yaml-schema.md",{"path":701,"priority":562},"scripts/validate-frontmatter.py",{"basePath":703,"description":704,"displayName":705,"installMethods":706,"rationale":707,"selectedPaths":708,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-compound-refresh","Refresh stale learning and pattern docs under docs/solutions/ by reviewing them against the current codebase, then updating, consolidating, or deleting drifted ones. Use when the user asks to \"refresh my learnings\", \"audit docs/solutions/\", \"clean up stale learnings\", or \"consolidate overlapping docs\", or when ce-compound flags an older doc as superseded. Do not trigger for general refactor, debugging, or code-review work unless the user has explicitly pointed at docs/solutions/.","ce-compound-refresh",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-compound-refresh/SKILL.md",[709,710,711,713,714,715],{"path":559,"priority":335},{"path":695,"priority":562},{"path":712,"priority":350},"references/per-action-flows.md",{"path":697,"priority":350},{"path":699,"priority":350},{"path":701,"priority":562},{"basePath":717,"description":718,"displayName":719,"installMethods":720,"rationale":721,"selectedPaths":722,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-debug","Systematically find root causes and fix bugs. Use when debugging errors, investigating test failures, reproducing bugs from issue trackers (GitHub, Linear, Jira), or when stuck on a problem after failed fix attempts. Also use when the user says 'debug this', 'why is this failing', 'fix this bug', 'trace this error', or pastes stack traces, error messages, or issue references.","ce-debug",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-debug/SKILL.md",[723,724,726,728],{"path":559,"priority":335},{"path":725,"priority":350},"references/anti-patterns.md",{"path":727,"priority":350},"references/defense-in-depth.md",{"path":729,"priority":350},"references/investigation-techniques.md",{"basePath":731,"description":732,"displayName":733,"installMethods":734,"rationale":735,"selectedPaths":736,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-demo-reel","Capture a visual demo reel (GIF, terminal recording, screenshots) for PR descriptions. Use when shipping UI changes, CLI features, or any work with observable behavior that benefits from visual proof. Also use when asked to add a demo, record a GIF, screenshot a feature, show what changed visually, create a demo reel, capture evidence, add proof to a PR, or create a before/after comparison.","ce-demo-reel",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-demo-reel/SKILL.md",[737,738,740,742,744,746,748],{"path":559,"priority":335},{"path":739,"priority":350},"references/tier-browser-reel.md",{"path":741,"priority":350},"references/tier-screenshot-reel.md",{"path":743,"priority":350},"references/tier-static-screenshots.md",{"path":745,"priority":350},"references/tier-terminal-recording.md",{"path":747,"priority":350},"references/upload-and-approval.md",{"path":749,"priority":562},"scripts/capture-demo.py",{"basePath":751,"description":752,"displayName":753,"installMethods":754,"rationale":755,"selectedPaths":756,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-dhh-rails-style","This skill should be used when writing Ruby and Rails code in DHH's distinctive 37signals style. It applies when writing Ruby code, Rails applications, creating models, controllers, or any Ruby file. Triggers on Ruby/Rails code generation, refactoring requests, code review, or when the user mentions DHH, 37signals, Basecamp, HEY, or Campfire style. Embodies REST purity, fat models, thin controllers, Current attributes, Hotwire patterns, and the \"clarity over cleverness\" philosophy.","ce-dhh-rails-style",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-dhh-rails-style/SKILL.md",[757,758,760,762,764,766,768],{"path":559,"priority":335},{"path":759,"priority":350},"references/architecture.md",{"path":761,"priority":350},"references/controllers.md",{"path":763,"priority":350},"references/frontend.md",{"path":765,"priority":350},"references/gems.md",{"path":767,"priority":350},"references/models.md",{"path":769,"priority":350},"references/testing.md",{"basePath":771,"description":772,"displayName":773,"installMethods":774,"rationale":775,"selectedPaths":776,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-doc-review","Review requirements or plan documents using parallel persona agents that surface role-specific issues. Use when a requirements document or plan document exists and the user wants to improve it.","ce-doc-review",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-doc-review/SKILL.md",[777,778,779,780,782,783,784,786],{"path":559,"priority":335},{"path":649,"priority":350},{"path":653,"priority":350},{"path":781,"priority":350},"references/open-questions-defer.md",{"path":657,"priority":350},{"path":659,"priority":350},{"path":785,"priority":350},"references/synthesis-and-presentation.md",{"path":665,"priority":350},{"basePath":788,"description":789,"displayName":790,"installMethods":791,"rationale":792,"selectedPaths":793,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-frontend-design","Build web interfaces with genuine design quality, not AI slop. Use for any frontend work - landing pages, web apps, dashboards, admin panels, components, interactive experiences. Activates for both greenfield builds and modifications to existing applications. Detects existing design systems and respects them. Covers composition, typography, color, motion, and copy. Verifies results via screenshots before declaring done.","ce-frontend-design",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-frontend-design/SKILL.md",[794],{"path":559,"priority":335},{"basePath":796,"description":797,"displayName":798,"installMethods":799,"rationale":800,"selectedPaths":801,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-gemini-imagegen","This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.","ce-gemini-imagegen",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-gemini-imagegen/SKILL.md",[802,803,805,807,809,811],{"path":559,"priority":335},{"path":804,"priority":562},"scripts/compose_images.py",{"path":806,"priority":562},"scripts/edit_image.py",{"path":808,"priority":562},"scripts/gemini_images.py",{"path":810,"priority":562},"scripts/generate_image.py",{"path":812,"priority":562},"scripts/multi_turn_chat.py",{"basePath":814,"description":815,"displayName":816,"installMethods":817,"rationale":818,"selectedPaths":819,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-ideate","Generate and critically evaluate grounded ideas about a topic. Use when asking what to improve, requesting idea generation, exploring surprising directions, or wanting the AI to proactively suggest strong options before brainstorming one in depth. Triggers on phrases like 'what should I improve', 'give me ideas', 'ideate on X', 'surprise me', 'what would you change', or any request for AI-generated suggestions rather than refining the user's own idea.","ce-ideate",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-ideate/SKILL.md",[820,821,823,825],{"path":559,"priority":335},{"path":822,"priority":350},"references/post-ideation-workflow.md",{"path":824,"priority":350},"references/universal-ideation.md",{"path":826,"priority":350},"references/web-research-cache.md",{"basePath":828,"description":829,"displayName":830,"installMethods":831,"rationale":832,"selectedPaths":833,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-optimize","Run metric-driven iterative optimization loops -- define a measurable goal, run parallel experiments, measure each against hard gates or LLM-as-judge scores, keep improvements, and converge on the best solution. Use when optimizing clustering quality, search relevance, build performance, prompt quality, or any measurable outcome that benefits from systematic experimentation.","ce-optimize",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-optimize/SKILL.md",[834,835,837,839,841,843,845,847,849,851,853],{"path":559,"priority":335},{"path":836,"priority":350},"references/example-hard-spec.yaml",{"path":838,"priority":350},"references/example-judge-spec.yaml",{"path":840,"priority":350},"references/experiment-log-schema.yaml",{"path":842,"priority":350},"references/experiment-prompt-template.md",{"path":844,"priority":350},"references/judge-prompt-template.md",{"path":846,"priority":350},"references/optimize-spec-schema.yaml",{"path":848,"priority":350},"references/usage-guide.md",{"path":850,"priority":562},"scripts/experiment-worktree.sh",{"path":852,"priority":562},"scripts/measure.sh",{"path":854,"priority":562},"scripts/parallel-probe.sh",{"basePath":856,"description":857,"displayName":858,"installMethods":859,"rationale":860,"selectedPaths":861,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-plan","Create structured plans for multi-step tasks -- software features, research workflows, events, study plans, or any goal that benefits from breakdown. Also deepens existing plans with interactive sub-agent review. Use when the user says 'plan this', 'create a plan', 'how should we build', 'break this down', or when a brainstorm doc is ready for planning. Use 'deepen the plan' or 'deepening pass' for the deepening flow. For exploratory requests, prefer ce-brainstorm first.","ce-plan",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-plan/SKILL.md",[862,863,865,867,869,870,872],{"path":559,"priority":335},{"path":864,"priority":350},"references/deepening-workflow.md",{"path":866,"priority":350},"references/plan-handoff.md",{"path":868,"priority":350},"references/plan-template.md",{"path":625,"priority":350},{"path":871,"priority":350},"references/universal-planning.md",{"path":629,"priority":350},{"basePath":874,"description":875,"displayName":876,"installMethods":877,"rationale":878,"selectedPaths":879,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-polish-beta","[BETA] Start the dev server, open the feature in a browser, and iterate on improvements together.","ce-polish-beta",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-polish-beta/SKILL.md",[880,881,883,885,887,889,891,893,895,897,899,901,903,905,907,909],{"path":559,"priority":335},{"path":882,"priority":350},"references/dev-server-astro.md",{"path":884,"priority":350},"references/dev-server-detection.md",{"path":886,"priority":350},"references/dev-server-next.md",{"path":888,"priority":350},"references/dev-server-nuxt.md",{"path":890,"priority":350},"references/dev-server-procfile.md",{"path":892,"priority":350},"references/dev-server-rails.md",{"path":894,"priority":350},"references/dev-server-remix.md",{"path":896,"priority":350},"references/dev-server-sveltekit.md",{"path":898,"priority":350},"references/dev-server-vite.md",{"path":900,"priority":350},"references/ide-detection.md",{"path":902,"priority":350},"references/launch-json-schema.md",{"path":904,"priority":562},"scripts/detect-project-type.sh",{"path":906,"priority":562},"scripts/read-launch-json.sh",{"path":908,"priority":562},"scripts/resolve-package-manager.sh",{"path":910,"priority":562},"scripts/resolve-port.sh",{"basePath":912,"description":913,"displayName":914,"installMethods":915,"rationale":916,"selectedPaths":917,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-product-pulse","Generate a time-windowed pulse report on what users experienced and how the product performed - usage, quality, errors, signals worth investigating. Use when the user says 'run a pulse', 'show me the pulse', 'how are we doing', 'weekly recap', 'launch-day check', or passes a time window like '24h' or '7d'. Configures via .compound-engineering/config.local.yaml and saves reports to docs/pulse-reports/.","ce-product-pulse",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-product-pulse/SKILL.md",[918,919,921],{"path":559,"priority":335},{"path":920,"priority":350},"references/interview.md",{"path":922,"priority":350},"references/report-template.md",{"basePath":924,"description":925,"displayName":926,"installMethods":927,"rationale":928,"selectedPaths":929,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-proof","Run human-in-the-loop review loops over markdown via Proof (proofeditor.ai) — share, view, comment on, edit, and sync collaborative docs. Use when the user says \"view this in proof\", \"share to proof\", \"HITL this doc\", or wants a shared markdown review surface for a spec, plan, or draft, including handoffs from ce-brainstorm, ce-ideate, or ce-plan. Do not trigger on \"proof\" meaning evidence, math proofs, proof-of-concept, or \"proofread this\".","ce-proof",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-proof/SKILL.md",[930,931],{"path":559,"priority":335},{"path":932,"priority":350},"references/hitl-review.md",{"basePath":934,"description":935,"displayName":936,"installMethods":937,"rationale":938,"selectedPaths":939,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-release-notes","Summarize recent compound-engineering plugin releases, or answer a specific question about a past release with a version citation. Use when the user types `/ce-release-notes` or asks \"what changed in compound-engineering recently?\" or \"what happened to `\u003Cskill-name>`?\".","ce-release-notes",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-release-notes/SKILL.md",[940,941],{"path":559,"priority":335},{"path":942,"priority":562},"scripts/list-plugin-releases.py",{"basePath":944,"description":945,"displayName":946,"installMethods":947,"rationale":948,"selectedPaths":949,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-report-bug","Report a bug in the compound-engineering plugin","ce-report-bug",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-report-bug/SKILL.md",[950],{"path":559,"priority":335},{"basePath":952,"description":953,"displayName":954,"installMethods":955,"rationale":956,"selectedPaths":957,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-resolve-pr-feedback","Resolve PR review feedback by evaluating validity and fixing issues in parallel. Use when addressing PR review comments, resolving review threads, or fixing code review feedback.","ce-resolve-pr-feedback",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-resolve-pr-feedback/SKILL.md",[958,959,961,963,965,967,969],{"path":559,"priority":335},{"path":960,"priority":350},"references/full-mode.md",{"path":962,"priority":350},"references/targeted-mode.md",{"path":964,"priority":562},"scripts/get-pr-comments",{"path":966,"priority":562},"scripts/get-thread-for-comment",{"path":968,"priority":562},"scripts/reply-to-pr-thread",{"path":970,"priority":562},"scripts/resolve-pr-thread",{"basePath":972,"description":973,"displayName":974,"installMethods":975,"rationale":976,"selectedPaths":977,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-riffrec-feedback-analysis","Riffrec product-feedback workflow. ALWAYS load when the user posts a `riffrec-*.zip`, a bundle with `session.json` + `events.json` + `recording.webm` + `voice.webm`, a video/audio recording for product feedback, or asks how to capture and share Riffrec sessions. Routes between setup, quick bug report, and extensive analysis.","ce-riffrec-feedback-analysis",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-riffrec-feedback-analysis/SKILL.md",[978,979,981,983,985,987],{"path":559,"priority":335},{"path":980,"priority":350},"references/compound-engineering-feedback-format.md",{"path":982,"priority":350},"references/extensive-analysis.md",{"path":984,"priority":350},"references/install-riffrec.md",{"path":986,"priority":350},"references/quick-bug-report.md",{"path":988,"priority":562},"scripts/analyze_riffrec_zip.py",{"basePath":990,"description":991,"displayName":992,"installMethods":993,"rationale":994,"selectedPaths":995,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-sessions","Search and ask questions about coding agent session history across Claude Code, Codex, and Cursor. Use when asking what was worked on, what was tried before, how a problem was investigated across sessions, what happened recently, or any question about past agent sessions. Also use when the user references prior sessions, previous attempts, or past investigations — even without saying 'sessions' explicitly.","ce-sessions",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-sessions/SKILL.md",[996,997,999,1001,1003],{"path":559,"priority":335},{"path":998,"priority":562},"scripts/discover-sessions.sh",{"path":1000,"priority":562},"scripts/extract-errors.py",{"path":1002,"priority":562},"scripts/extract-metadata.py",{"path":1004,"priority":562},"scripts/extract-skeleton.py",{"basePath":1006,"description":1007,"displayName":1008,"installMethods":1009,"rationale":1010,"selectedPaths":1011,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-setup","Diagnose and configure compound-engineering environment. Checks CLI dependencies, plugin version, and repo-local config. Offers guided installation for missing tools. Use when troubleshooting missing tools, verifying setup, or before onboarding.","ce-setup",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-setup/SKILL.md",[1012,1013,1015],{"path":559,"priority":335},{"path":1014,"priority":350},"references/config-template.yaml",{"path":1016,"priority":562},"scripts/check-health",{"basePath":1018,"description":1019,"displayName":1020,"installMethods":1021,"rationale":1022,"selectedPaths":1023,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-simplify-code","Simplify and refine recently changed code for clarity, reuse, quality, and efficiency while preserving behavior.","ce-simplify-code",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-simplify-code/SKILL.md",[1024],{"path":559,"priority":335},{"basePath":1026,"description":1027,"displayName":1028,"installMethods":1029,"rationale":1030,"selectedPaths":1031,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-slack-research","Search Slack for interpreted organizational context -- decisions, constraints, and discussion arcs -- and produce a synthesized research digest with cross-cutting analysis. Use when the user says 'search slack for', 'what did we discuss about', 'slack context for', or 'what does the team think about'. Differs from slack:find-discussions, which returns raw message results without synthesis.","ce-slack-research",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-slack-research/SKILL.md",[1032],{"path":559,"priority":335},{"basePath":1034,"description":1035,"displayName":1036,"installMethods":1037,"rationale":1038,"selectedPaths":1039,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-strategy","Create or maintain STRATEGY.md - the product's target problem, approach, users, key metrics, and tracks of work. Use when starting a new product, updating direction, or when prompts like 'write our strategy', 'update the roadmap', 'what are we working on', or 'set up the strategy doc' come up. Also triggers when ce-ideate, ce-brainstorm, or ce-plan need upstream grounding and no strategy doc exists yet.","ce-strategy",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-strategy/SKILL.md",[1040,1041,1042],{"path":559,"priority":335},{"path":920,"priority":350},{"path":1043,"priority":350},"references/strategy-template.md",{"basePath":1045,"description":1046,"displayName":1047,"installMethods":1048,"rationale":1049,"selectedPaths":1050,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-test-browser","Run browser tests on pages affected by current PR or branch","ce-test-browser",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-test-browser/SKILL.md",[1051],{"path":559,"priority":335},{"basePath":1053,"description":1054,"displayName":1055,"installMethods":1056,"rationale":1057,"selectedPaths":1058,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-test-xcode","Build and test iOS apps on simulator using XcodeBuildMCP. Use after making iOS code changes, before creating a PR, or when verifying app behavior and checking for crashes on simulator.","ce-test-xcode",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-test-xcode/SKILL.md",[1059],{"path":559,"priority":335},{"basePath":1061,"description":1062,"displayName":1063,"installMethods":1064,"rationale":1065,"selectedPaths":1066,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-update","Check if the compound-engineering plugin is up to date and recommend the\nupdate command if not. Use when the user says \"update compound engineering\",\n\"check compound engineering version\", \"ce update\", \"is compound engineering\nup to date\", \"update ce plugin\", or reports issues that might stem from a\nstale compound-engineering plugin version. This skill only works in Claude\nCode — it relies on the plugin harness cache layout.\n","ce-update",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-update/SKILL.md",[1067,1068,1070,1072],{"path":559,"priority":335},{"path":1069,"priority":562},"scripts/currently-loaded-version.sh",{"path":1071,"priority":562},"scripts/marketplace-name.sh",{"path":1073,"priority":562},"scripts/upstream-version.sh",{"basePath":1075,"description":1076,"displayName":1077,"installMethods":1078,"rationale":1079,"selectedPaths":1080,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-work","Execute work efficiently while maintaining quality and finishing features","ce-work",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-work/SKILL.md",[1081,1082,1084],{"path":559,"priority":335},{"path":1083,"priority":350},"references/shipping-workflow.md",{"path":661,"priority":350},{"basePath":1086,"description":1087,"displayName":1088,"installMethods":1089,"rationale":1090,"selectedPaths":1091,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-work-beta","[BETA] Execute work with external delegate support. Same as ce-work but includes experimental Codex delegation mode for token-conserving code implementation.","ce-work-beta",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-work-beta/SKILL.md",[1092,1093,1095,1096],{"path":559,"priority":335},{"path":1094,"priority":350},"references/codex-delegation-workflow.md",{"path":1083,"priority":350},{"path":661,"priority":350},{"basePath":1098,"description":1099,"displayName":1100,"installMethods":1101,"rationale":1102,"selectedPaths":1103,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/ce-worktree","Create an isolated git worktree for parallel feature work or PR review. Use when starting work that should not disturb the current checkout, or when `ce-work` or `ce-code-review` offers a worktree option.","ce-worktree",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-worktree/SKILL.md",[1104,1105],{"path":559,"priority":335},{"path":1106,"priority":562},"scripts/worktree-manager.sh",{"basePath":1108,"description":1109,"displayName":1110,"installMethods":1111,"rationale":1112,"selectedPaths":1113,"source":336,"sourceLanguage":18,"type":257},"plugins/compound-engineering/skills/lfg","Run the full autonomous engineering pipeline end-to-end (plan, work, code review, test, commit, push, open PR, watch CI, fix CI failures until green). Use only when the user explicitly requests hands-off execution of a software task and provides a feature description; do not auto-route casual conversation here.","lfg",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/lfg/SKILL.md",[1114,1115],{"path":559,"priority":335},{"path":661,"priority":350},{"basePath":278,"description":1117,"displayName":1118,"installMethods":1119,"rationale":1120,"selectedPaths":1121,"source":336,"sourceLanguage":18,"type":1138},"Official Compound Engineering plugin for Claude Code, Codex, and more","@every-env/compound-plugin",{"npm":1118},"cli ecosystem detected at /",[1122,1124,1125,1126,1128,1130,1132,1134,1136],{"path":1123,"priority":335},"package.json",{"path":344,"priority":335},{"path":346,"priority":347},{"path":1127,"priority":350},"src/index.ts",{"path":1129,"priority":562},"src/commands/cleanup.ts",{"path":1131,"priority":562},"src/commands/convert.ts",{"path":1133,"priority":562},"src/commands/install.ts",{"path":1135,"priority":562},"src/commands/list.ts",{"path":1137,"priority":562},"src/commands/plugin-path.ts","cli",{"sources":1140},[1141],"manual",{"npmPackage":1118},{"closedIssues90d":240,"description":1144,"forks":241,"homepage":1145,"license":248,"openIssues90d":242,"pushedAt":243,"readmeSize":238,"stars":244,"topics":1146},"Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more","https://every.to/guides/compound-engineering",[1147,1148],"compound","engineering",{"downloads":246},{"classifiedAt":1151,"discoverAt":1152,"extractAt":1153,"githubAt":1153,"npmAt":1154,"updatedAt":1151},1778686639998,1778686632796,1778686635929,1778686638203,[219,220,223,221,224,222],{"evaluatedAt":252,"extractAt":300,"updatedAt":252},[],[1159,1188,1216,1244,1272,1302],{"_creationTime":1160,"_id":1161,"community":1162,"display":1163,"identity":1169,"providers":1174,"relations":1182,"tags":1184,"workflow":1185},1778687399826.0247,"k173skx1fvkafn38prsv2d0qbh86nn4h",{"reviewCount":8},{"description":1164,"installMethods":1165,"name":1167,"sourceUrl":1168},"Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output quality, prompt engineering, prompt tuning, or system prompt improvement.",{"claudeCode":1166},"github/awesome-copilot","Arize Prompt Optimization","https://github.com/github/awesome-copilot",{"basePath":1170,"githubOwner":1171,"githubRepo":1172,"locale":18,"slug":1173,"type":257},"skills/arize-prompt-optimization","github","awesome-copilot","arize-prompt-optimization",{"evaluate":1175,"extract":1181},{"promptVersionExtension":212,"promptVersionScoring":213,"score":1176,"tags":1177,"targetMarket":225,"tier":226},100,[221,222,1178,1179,1138,1180],"optimization","arize","data-analysis",{"commitSha":290,"license":248},{"repoId":1183},"kd7dsmv976w8rtkqnjjfdtfgks86nnmw",[1179,1138,1180,221,1178,222],{"evaluatedAt":1186,"extractAt":1187,"updatedAt":1186},1778689257343,1778687399826,{"_creationTime":1189,"_id":1190,"community":1191,"display":1192,"identity":1198,"providers":1203,"relations":1208,"tags":1211,"workflow":1212},1778675763394.726,"k17da8jzz57jd92ph2ny16chhs86maf9",{"reviewCount":8},{"description":1193,"installMethods":1194,"name":1196,"sourceUrl":1197},"Wendet Prompt-Wiederholung an, um die Genauigkeit für LLMs ohne Schlussfolgerungsfähigkeit zu verbessern",{"claudeCode":1195},"asklokesh/loki-mode","prompt-optimization","https://github.com/asklokesh/loki-mode",{"basePath":1199,"githubOwner":1200,"githubRepo":1201,"locale":1202,"slug":1196,"type":257},"agent-skills/prompt-optimization","asklokesh","loki-mode","de",{"evaluate":1204,"extract":1207},{"promptVersionExtension":212,"promptVersionScoring":213,"score":1176,"tags":1205,"targetMarket":225,"tier":226},[221,222,1206,1178],"accuracy",{"commitSha":290},{"repoId":1209,"translatedFrom":1210},"kd7dy44r49793jt8bt02wdezk586nxsn","k17bjgfyvbnt05kpma9n0gn4j186n152",[1206,221,1178,222],{"evaluatedAt":1213,"extractAt":1214,"updatedAt":1215},1778675713014,1778675659559,1778675763394,{"_creationTime":1217,"_id":1218,"community":1219,"display":1220,"identity":1226,"providers":1230,"relations":1238,"tags":1240,"workflow":1241},1778688417731.9468,"k171m9pw7az13daagx489nghw986nr3b",{"reviewCount":8},{"description":1221,"installMethods":1222,"name":1224,"sourceUrl":1225},"Command-line interface for Blender - A stateful command-line interface for 3D scene editing, following the same patterns as the GIMP CLI ...",{"claudeCode":1223},"hkuds/cli-anything","cli-anything-blender","https://github.com/hkuds/cli-anything",{"basePath":1227,"githubOwner":1228,"githubRepo":1229,"locale":18,"slug":1224,"type":257},"skills/cli-anything-blender","hkuds","cli-anything",{"evaluate":1231,"extract":1237},{"promptVersionExtension":212,"promptVersionScoring":213,"score":1176,"tags":1232,"targetMarket":225,"tier":226},[1233,1234,1235,1138,1236,219],"blender","3d-modeling","rendering","automation",{"commitSha":290},{"repoId":1239},"kd7e2bra4ymb6r521a25r6yges86n35p",[1234,219,1236,1233,1138,1235],{"evaluatedAt":1242,"extractAt":1243,"updatedAt":1242},1778688604253,1778688417732,{"_creationTime":1245,"_id":1246,"community":1247,"display":1248,"identity":1254,"providers":1258,"relations":1266,"tags":1268,"workflow":1269},1778696691708.3062,"k178rt0mhkwtjj1axhgtt0tfth86mt09",{"reviewCount":8},{"description":1249,"installMethods":1250,"name":1252,"sourceUrl":1253},"Domain-Driven Design architecture for claude-flow v3. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern.",{"claudeCode":1251},"ruvnet/ruflo","v3-ddd-architecture","https://github.com/ruvnet/ruflo",{"basePath":1255,"githubOwner":1256,"githubRepo":1257,"locale":18,"slug":1252,"type":257},".claude/skills/v3-ddd-architecture","ruvnet","ruflo",{"evaluate":1259,"extract":1265},{"promptVersionExtension":212,"promptVersionScoring":213,"score":1176,"tags":1260,"targetMarket":225,"tier":226},[1261,220,1262,1263,1264],"ddd","refactoring","clean-architecture","typescript",{"commitSha":290},{"repoId":1267},"kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[220,1263,1261,1262,1264],{"evaluatedAt":1270,"extractAt":1271,"updatedAt":1270},1778699412094,1778696691708,{"_creationTime":1273,"_id":1274,"community":1275,"display":1276,"identity":1282,"providers":1287,"relations":1294,"tags":1297,"workflow":1298},1778698405469.0413,"k17e4wbf2c3x45d7e730x7eje986mc5g",{"reviewCount":8},{"description":1277,"installMethods":1278,"name":1280,"sourceUrl":1281},"Ordnet eine Codebasis in Feature-gruppierte Flussdiagramme ein, identifiziert doppelte Belange über Features hinweg und schlägt eine einheitliche Architektur vor. Wird verwendet, wenn nach \"dem idealen Pfad\" gefragt wird, duplizierte Systeme vereinheitlicht oder die Architektur vor einem Refactoring auditiert werden soll. Gibt ein vorgeschlagenes einheitliches Flussdiagramm sowie Prompts zum Erstellen eines Plans pro System aus.",{"claudeCode":1279},"thedotmack/claude-mem","Pathfinder","https://github.com/thedotmack/claude-mem",{"basePath":1283,"githubOwner":1284,"githubRepo":1285,"locale":1202,"slug":1286,"type":257},"plugin/skills/pathfinder","thedotmack","claude-mem","pathfinder",{"evaluate":1288,"extract":1292},{"promptVersionExtension":212,"promptVersionScoring":213,"score":1176,"tags":1289,"targetMarket":225,"tier":226},[1290,220,287,1262,1291],"code-analysis","flowchart",{"commitSha":290,"license":1293},"Apache-2.0",{"repoId":1295,"translatedFrom":1296},"kd70jnxgm695az2wtf37zbqdj986mp7k","k176pxdjxvnyex7jv6abt3myd586n5vv",[220,1290,287,1291,1262],{"evaluatedAt":1299,"extractAt":1300,"updatedAt":1301},1778698228002,1778698056313,1778698405469,{"_creationTime":1303,"_id":1304,"community":1305,"display":1306,"identity":1312,"providers":1316,"relations":1322,"tags":1325,"workflow":1326},1778692764716.7837,"k17ex2pfs1bykksynnhwdp5ywd86mjtd",{"reviewCount":8},{"description":1307,"installMethods":1308,"name":1310,"sourceUrl":1311},"Analysieren Sie eine Codebasis, um einen interaktiven Wissensgraphen zur Verständnis von Architektur, Komponenten und Beziehungen zu erstellen",{"claudeCode":1309},"Lum1104/Understand-Anything","understand","https://github.com/Lum1104/Understand-Anything",{"basePath":1313,"githubOwner":1314,"githubRepo":1315,"locale":1202,"slug":1310,"type":257},"understand-anything-plugin/skills/understand","Lum1104","Understand-Anything",{"evaluate":1317,"extract":1321},{"promptVersionExtension":212,"promptVersionScoring":213,"score":1176,"tags":1318,"targetMarket":225,"tier":226},[1290,1319,306,220,1320],"knowledge-graph","code-exploration",{"commitSha":290},{"repoId":1323,"translatedFrom":1324},"kd78egfytykkxxbpr6k3t7wsph86n83x","k17cmt6ekj6t5bf5dbscrqa3an86m6p3",[220,1290,1320,306,1319],{"evaluatedAt":1327,"extractAt":1328,"updatedAt":1329},1778692606129,1778692549705,1778692764716]