[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-EveryInc-ce-optimize-en":3,"guides-for-EveryInc-ce-optimize":1156,"similar-k178bs4zybvyebq2gnym4jazch86np03-en":1157},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":250,"isFallback":246,"parentExtension":256,"providers":316,"relations":320,"repo":321,"tags":1154,"workflow":1155},1778686640222.7952,"k178bs4zybvyebq2gnym4jazch86np03",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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.",{"claudeCode":12},"EveryInc/compound-engineering-plugin","CE Optimize","https://github.com/EveryInc/compound-engineering-plugin",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":229,"workflow":248},1778687141592.4922,"kn7cbgkyr165q4gn7dmvkc3txd86man4","en",{"checks":20,"evaluatedAt":186,"extensionSummary":187,"features":188,"nonGoals":194,"practices":199,"prerequisites":205,"promptVersionExtension":210,"promptVersionScoring":211,"purpose":212,"rationale":213,"score":214,"summary":215,"tags":216,"targetMarket":222,"tier":223,"useCases":224},[21,26,29,32,36,39,43,46,50,54,58,61,64,68,72,76,80,83,86,89,92,95,98,102,105,109,113,117,120,123,126,130,133,136,139,142,145,148,152,156,159,162,166,169,173,177,180,183],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly names the problem of iterative optimization for measurable goals and provides specific use cases like clustering, search relevance, and prompt quality.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers a structured, metric-driven approach to optimization that goes beyond simple prompt engineering, including features like automated experimentation, gated evaluation, and convergence on best solutions.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill provides a comprehensive lifecycle for optimization, including setup, measurement scaffolding, iterative loops, persistence, and wrap-up, with clear instructions for user interaction and state management.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses specifically on iterative optimization loops, defining goals, running experiments, and converging on solutions, without extending into unrelated domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the skill's core functionality of running metric-driven iterative optimization loops and provides relevant use cases.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Precise Purpose","The SKILL.md frontmatter concisely defines the skill's purpose (iterative optimization) and provides clear triggers for its use, such as optimizing measurable outcomes with systematic experimentation.",{"category":40,"check":44,"severity":24,"summary":45},"Concise Frontmatter","The SKILL.md frontmatter is dense and self-contained, clearly summarizing the core capability and providing relevant trigger phrases.",{"category":47,"check":48,"severity":24,"summary":49},"Documentation","Concise Body","The SKILL.md body is well-structured with progressive disclosure, delegating detailed procedures and schemas to separate reference files.",{"category":51,"check":52,"severity":24,"summary":53},"Context","Progressive Disclosure","The SKILL.md effectively uses relative paths to link into `references/` files for schemas, guides, and examples, enabling progressive disclosure.",{"category":51,"check":55,"severity":56,"summary":57},"Forked exploration","not_applicable","The skill does not appear to involve extensive, long-form exploration that would necessitate `context: fork`; it focuses on structured iteration and measurement.",{"category":22,"check":59,"severity":24,"summary":60},"Usage examples","The SKILL.md provides clear quick start guidance and references to usage examples for different scenarios (hard metrics vs. judge mode), which are likely ready-to-use.",{"category":22,"check":62,"severity":24,"summary":63},"Edge cases","The SKILL.md extensively details edge cases, failure modes, and recovery steps, particularly concerning persistence discipline and handling of judge/measurement outcomes.",{"category":65,"check":66,"severity":56,"summary":67},"Code Execution","Tool Fallback","The skill relies on Claude Code internal tools and does not explicitly reference external MCP servers or tools requiring fallback mechanisms.",{"category":69,"check":70,"severity":24,"summary":71},"Safety","Halt on unexpected state","The skill's persistence discipline mandates halting and reporting on unexpected pre-state, ensuring operations do not proceed on corrupted data.",{"category":73,"check":74,"severity":24,"summary":75},"Portability","Cross-skill coupling","The skill is self-contained and does not appear to implicitly rely on other skills; cross-references are to documentation or related skills, not functional dependencies.",{"category":77,"check":78,"severity":24,"summary":79},"Security","Secret Management","The skill focuses on measurement and experimentation within a defined scope and does not appear to handle or expose secrets.",{"category":77,"check":81,"severity":24,"summary":82},"Injection","The skill defines clear input and output contracts, and its focus on structured spec files and isolated worktrees mitigates injection risks.",{"category":77,"check":84,"severity":24,"summary":85},"Transitive Supply-Chain Grenades","The skill operates within a controlled environment, using bundled scripts and defined commands, and does not fetch remote code or data at runtime.",{"category":77,"check":87,"severity":24,"summary":88},"Sandbox Isolation","The skill utilizes git worktrees and defined scopes (`mutable`, `immutable`) to maintain sandbox isolation, preventing unintended modifications outside the project.",{"category":77,"check":90,"severity":24,"summary":91},"Sandbox escape primitives","The scripts and workflow described do not appear to contain primitives for escaping the sandbox, such as detached processes or deny-retry loops.",{"category":77,"check":93,"severity":24,"summary":94},"Data Exfiltration","The skill's purpose is focused on local optimization and measurement; there are no apparent mechanisms for exfiltrating user data.",{"category":77,"check":96,"severity":24,"summary":97},"Hidden Text Tricks","The bundled markdown and scripts appear to be free of hidden text tricks or obfuscation designed to steer the model.",{"category":99,"check":100,"severity":24,"summary":101},"Hooks","Opaque code execution","The provided scripts and instructions are plain readable code, with no evidence of obfuscation, base64 payloads, or runtime code fetching.",{"category":73,"check":103,"severity":24,"summary":104},"Structural Assumption","The skill defines explicit scopes for mutable and immutable files, and uses relative paths, avoiding assumptions about user-specific project structures.",{"category":106,"check":107,"severity":24,"summary":108},"Trust","Issues Attention","With 25 open issues and 115 closed in 90 days, the closure rate is well above 50%, indicating active maintenance.",{"category":110,"check":111,"severity":24,"summary":112},"Versioning","Release Management","The presence of GitHub release tags and a CHANGELOG.md indicate a clear versioning and release management process.",{"category":114,"check":115,"severity":24,"summary":116},"Execution","Validation","The SKILL.md and schemas clearly define input validation for the optimization spec, and the measurement command output is expected to be JSON, implying structured validation.",{"category":77,"check":118,"severity":24,"summary":119},"Unguarded Destructive Operations","The skill operates on experiment worktrees and does not perform destructive operations on the main project without clear isolation and management procedures.",{"category":65,"check":121,"severity":24,"summary":122},"Error Handling","The persistence discipline section mandates robust error handling, including immediate writing of results and verification, ensuring fail-closed behavior.",{"category":65,"check":124,"severity":24,"summary":125},"Logging","The persistence discipline ensures that all critical operations, including experiment results and state changes, are logged to disk for auditability.",{"category":127,"check":128,"severity":56,"summary":129},"Compliance","GDPR","The skill operates on code and configuration, not personal data, so GDPR compliance is not applicable.",{"category":127,"check":131,"severity":24,"summary":132},"Target market","The skill is a generic engineering tool with no regional or jurisdictional logic; targetMarket is global.",{"category":73,"check":134,"severity":24,"summary":135},"Runtime stability","The skill uses standard shell scripts and git commands, and its worktree isolation ensures platform portability.",{"category":47,"check":137,"severity":24,"summary":138},"README","The README provides a good overview of the Compound Engineering philosophy, workflow, and includes installation instructions.",{"category":33,"check":140,"severity":56,"summary":141},"Tool surface size","This is a single-purpose skill (`ce-optimize`) and does not expose a large number of distinct tools.",{"category":40,"check":143,"severity":56,"summary":144},"Overlapping near-synonym tools","This is a single-purpose skill and does not have overlapping tools.",{"category":47,"check":146,"severity":24,"summary":147},"Phantom features","All features described in the README and SKILL.md appear to be implemented or directly referenced by the provided schemas and scripts.",{"category":149,"check":150,"severity":24,"summary":151},"Install","Installation instruction","The README provides detailed installation instructions for various platforms (Claude Code, Cursor, Codex, Copilot, etc.) with copy-pasteable examples.",{"category":153,"check":154,"severity":24,"summary":155},"Errors","Actionable error messages","The SKILL.md outlines specific error handling procedures, including reporting unexpected states and persisting results, which implies actionable error messages.",{"category":114,"check":157,"severity":24,"summary":158},"Pinned dependencies","The `package.json` and lockfiles, combined with the schema and script declarations, suggest dependencies are pinned and managed.",{"category":33,"check":160,"severity":56,"summary":161},"Dry-run preview","The skill's operations are primarily focused on managing isolated worktrees and executing measurement commands; a dry-run preview of these actions is not applicable.",{"category":163,"check":164,"severity":24,"summary":165},"Protocol","Idempotent retry & timeouts","The `measure.sh` script implements timeouts, and the skill's design emphasizes state persistence to handle retries and failures gracefully.",{"category":127,"check":167,"severity":24,"summary":168},"Telemetry opt-in","The skill does not appear to emit telemetry; its focus is on local optimization and measurement within user-controlled environments.",{"category":170,"check":171,"severity":24,"summary":172},"License","License usability","The extension is licensed under the MIT license, as indicated by the LICENSE file and the SPDX identifier.",{"category":174,"check":175,"severity":24,"summary":176},"Maintenance","Commit recency","The last commit was on 2026-05-13, indicating recent activity within the last 90 days.",{"category":174,"check":178,"severity":24,"summary":179},"Dependency Management","The project uses npm with lockfiles and `bun install`, indicating good dependency management practices.",{"category":40,"check":181,"severity":24,"summary":182},"Minimal I/O surface","The skill takes a spec file or description as input and produces JSON output for measurement, with clear boundaries defined by scopes.",{"category":33,"check":184,"severity":56,"summary":185},"Tool naming","This is a skill, not a toolset with multiple user-facing commands, so tool naming conventions are not directly applicable.",1778687141478,"This skill enables metric-driven iterative optimization by defining goals, running parallel experiments, measuring outcomes against hard gates or LLM-as-judge scores, and converging on the best solution. It includes detailed persistence discipline, worktree management, and spec validation.",[189,190,191,192,193],"Metric-driven iterative optimization loops","Support for hard metrics and LLM-as-judge","Automated experiment execution and measurement","Robust persistence and crash recovery","Scoped modification of code and configuration",[195,196,197,198],"Implementing the core logic being optimized","Replacing manual code development entirely","Running experiments without a defined measurement harness","Performing optimizations that cannot be measured or evaluated systematically",[200,201,202,203,204],"Experiment design","Iterative development","Metric definition","Code quality","MLOps",[206,207,208,209],"Git repository","Bash shell","Python 3","The `ce-optimize` skill installed","3.0.0","4.4.0","To systematically improve measurable outcomes through automated, iterative experimentation and convergence.","All checks passed. The skill is robust, well-documented, and adheres to best practices for safety, maintainability, and utility.",100,"A robust skill for metric-driven iterative optimization with strong persistence and safety guarantees.",[217,218,219,220,221],"optimization","experimentation","mlops","code-quality","prompt-engineering","global","verified",[225,226,227,228],"Optimizing build performance or test coverage","Tuning LLM prompts for quality and cost","Improving search relevance or clustering quality","Systematically experimenting with code or configuration variants",{"codeQuality":230,"collectedAt":232,"documentation":233,"maintenance":236,"popularity":242,"security":244,"testCoverage":247},{"hasLockfile":231},true,1778687119424,{"descriptionLength":234,"readmeSize":235},377,17582,{"closedIssues90d":237,"forks":238,"hasChangelog":231,"openIssues90d":239,"pushedAt":240,"stars":241},115,1300,25,1778686215000,16666,{"npmDownloads":243},12828,{"hasNpmPackage":231,"license":245,"smitheryVerified":246},"MIT",false,{"hasCi":231,"hasTests":231},{"updatedAt":249},1778687141592,{"basePath":251,"githubOwner":252,"githubRepo":253,"locale":18,"slug":254,"type":255},"plugins/compound-engineering/skills/ce-optimize","EveryInc","compound-engineering-plugin","ce-optimize","skill",{"_creationTime":257,"_id":258,"community":259,"display":260,"identity":264,"parentExtension":267,"providers":300,"relations":312,"tags":313,"workflow":314},1778686640222.7903,"k17d893df4em0e3pn8f55h1dxn86n09e",{"reviewCount":8},{"description":261,"installMethods":262,"name":263,"sourceUrl":14},"AI-powered development tools for code review, research, design, and workflow automation.",{"claudeCode":263},"compound-engineering",{"basePath":265,"githubOwner":252,"githubRepo":253,"locale":18,"slug":263,"type":266},"plugins/compound-engineering","plugin",{"_creationTime":268,"_id":269,"community":270,"display":271,"identity":275,"providers":278,"relations":294,"tags":296,"workflow":297},1778686640222.7908,"k17ef8php9wk308mkg59kdp6b186nzhx",{"reviewCount":8},{"description":272,"installMethods":273,"name":274,"sourceUrl":14},"Cursor plugin marketplace for Every Inc plugins",{"claudeCode":12},"Compound Engineering",{"basePath":276,"githubOwner":252,"githubRepo":253,"locale":18,"slug":253,"type":277},"","marketplace",{"evaluate":279,"extract":288},{"promptVersionExtension":280,"promptVersionScoring":211,"score":281,"tags":282,"targetMarket":222,"tier":223},"3.1.0",99,[283,284,285,286,287],"development-workflow","code-review","planning","documentation","ai-agents",{"commitSha":289,"license":245,"marketplace":290,"plugin":292},"HEAD",{"name":253,"pluginCount":291},2,{"mcpCount":8,"provider":293,"skillCount":8},"classify",{"repoId":295},"kd7e40my1b5g70tg0f60qg85ch86nn08",[287,284,283,286,285],{"evaluatedAt":298,"extractAt":299,"updatedAt":298},1778686722515,1778686640222,{"evaluate":301,"extract":309},{"promptVersionExtension":210,"promptVersionScoring":211,"score":302,"tags":303,"targetMarket":222,"tier":223},98,[304,305,284,306,286,307,285,308],"ai","developer-tools","research","workflow-automation","ideation",{"commitSha":289,"license":245,"plugin":310},{"mcpCount":8,"provider":293,"skillCount":311},37,{"parentExtensionId":269,"repoId":295},[304,284,305,286,308,285,306,307],{"evaluatedAt":315,"extractAt":299,"updatedAt":315},1778686677611,{"evaluate":317,"extract":319},{"promptVersionExtension":210,"promptVersionScoring":211,"score":214,"tags":318,"targetMarket":222,"tier":223},[217,218,219,220,221],{"commitSha":289,"license":245},{"parentExtensionId":258,"repoId":295},{"_creationTime":322,"_id":295,"identity":323,"providers":324,"workflow":1149},1778686632796.9226,{"githubOwner":252,"githubRepo":253,"sourceUrl":14},{"classify":325,"discover":1138,"extract":1141,"github":1142,"npm":1148},{"commitSha":289,"extensions":326},[327,336,524,543,551,568,606,614,632,642,668,676,688,704,718,732,752,772,789,797,815,829,854,872,910,922,932,942,950,970,988,1004,1016,1024,1032,1043,1051,1059,1073,1084,1096,1106,1115],{"basePath":328,"displayName":253,"installMethods":329,"rationale":330,"selectedPaths":331,"source":335,"sourceLanguage":18,"type":277},".agents/plugins",{"claudeCode":12},"marketplace.json at .agents/plugins/marketplace.json (coalesced with duplicate marketplace at /)",[332],{"path":333,"priority":334},"marketplace.json","mandatory","rule",{"basePath":265,"description":261,"displayName":263,"installMethods":337,"license":245,"rationale":338,"selectedPaths":339,"source":335,"sourceLanguage":18,"type":266},{"claudeCode":263},"plugin manifest at plugins/compound-engineering/.claude-plugin/plugin.json",[340,342,344,347,350,352,354,356,358,360,362,364,366,368,370,372,374,376,378,380,382,384,386,388,390,392,394,396,398,400,402,404,406,408,410,412,414,416,418,420,422,424,426,428,430,432,434,436,438,440,442,444,446,448,450,452,454,456,458,460,462,464,466,468,470,472,474,476,478,480,482,484,486,488,490,492,494,496,498,500,502,504,506,508,510,512,514,516,518,520,522],{"path":341,"priority":334},".claude-plugin/plugin.json",{"path":343,"priority":334},"README.md",{"path":345,"priority":346},"LICENSE","high",{"path":348,"priority":349},"skills/ce-agent-native-architecture/SKILL.md","medium",{"path":351,"priority":349},"skills/ce-agent-native-audit/SKILL.md",{"path":353,"priority":349},"skills/ce-brainstorm/SKILL.md",{"path":355,"priority":349},"skills/ce-clean-gone-branches/SKILL.md",{"path":357,"priority":349},"skills/ce-code-review/SKILL.md",{"path":359,"priority":349},"skills/ce-commit/SKILL.md",{"path":361,"priority":349},"skills/ce-commit-push-pr/SKILL.md",{"path":363,"priority":349},"skills/ce-compound/SKILL.md",{"path":365,"priority":349},"skills/ce-compound-refresh/SKILL.md",{"path":367,"priority":349},"skills/ce-debug/SKILL.md",{"path":369,"priority":349},"skills/ce-demo-reel/SKILL.md",{"path":371,"priority":349},"skills/ce-dhh-rails-style/SKILL.md",{"path":373,"priority":349},"skills/ce-doc-review/SKILL.md",{"path":375,"priority":349},"skills/ce-frontend-design/SKILL.md",{"path":377,"priority":349},"skills/ce-gemini-imagegen/SKILL.md",{"path":379,"priority":349},"skills/ce-ideate/SKILL.md",{"path":381,"priority":349},"skills/ce-optimize/SKILL.md",{"path":383,"priority":349},"skills/ce-plan/SKILL.md",{"path":385,"priority":349},"skills/ce-polish-beta/SKILL.md",{"path":387,"priority":349},"skills/ce-product-pulse/SKILL.md",{"path":389,"priority":349},"skills/ce-proof/SKILL.md",{"path":391,"priority":349},"skills/ce-release-notes/SKILL.md",{"path":393,"priority":349},"skills/ce-report-bug/SKILL.md",{"path":395,"priority":349},"skills/ce-resolve-pr-feedback/SKILL.md",{"path":397,"priority":349},"skills/ce-riffrec-feedback-analysis/SKILL.md",{"path":399,"priority":349},"skills/ce-sessions/SKILL.md",{"path":401,"priority":349},"skills/ce-setup/SKILL.md",{"path":403,"priority":349},"skills/ce-simplify-code/SKILL.md",{"path":405,"priority":349},"skills/ce-slack-research/SKILL.md",{"path":407,"priority":349},"skills/ce-strategy/SKILL.md",{"path":409,"priority":349},"skills/ce-test-browser/SKILL.md",{"path":411,"priority":349},"skills/ce-test-xcode/SKILL.md",{"path":413,"priority":349},"skills/ce-update/SKILL.md",{"path":415,"priority":349},"skills/ce-work/SKILL.md",{"path":417,"priority":349},"skills/ce-work-beta/SKILL.md",{"path":419,"priority":349},"skills/ce-worktree/SKILL.md",{"path":421,"priority":349},"skills/lfg/SKILL.md",{"path":423,"priority":346},"agents/ce-adversarial-document-reviewer.agent.md",{"path":425,"priority":346},"agents/ce-adversarial-reviewer.agent.md",{"path":427,"priority":346},"agents/ce-agent-native-reviewer.agent.md",{"path":429,"priority":346},"agents/ce-ankane-readme-writer.agent.md",{"path":431,"priority":346},"agents/ce-api-contract-reviewer.agent.md",{"path":433,"priority":346},"agents/ce-architecture-strategist.agent.md",{"path":435,"priority":346},"agents/ce-best-practices-researcher.agent.md",{"path":437,"priority":346},"agents/ce-code-simplicity-reviewer.agent.md",{"path":439,"priority":346},"agents/ce-coherence-reviewer.agent.md",{"path":441,"priority":346},"agents/ce-correctness-reviewer.agent.md",{"path":443,"priority":346},"agents/ce-data-integrity-guardian.agent.md",{"path":445,"priority":346},"agents/ce-data-migration-expert.agent.md",{"path":447,"priority":346},"agents/ce-data-migrations-reviewer.agent.md",{"path":449,"priority":346},"agents/ce-deployment-verification-agent.agent.md",{"path":451,"priority":346},"agents/ce-design-implementation-reviewer.agent.md",{"path":453,"priority":346},"agents/ce-design-iterator.agent.md",{"path":455,"priority":346},"agents/ce-design-lens-reviewer.agent.md",{"path":457,"priority":346},"agents/ce-dhh-rails-reviewer.agent.md",{"path":459,"priority":346},"agents/ce-feasibility-reviewer.agent.md",{"path":461,"priority":346},"agents/ce-figma-design-sync.agent.md",{"path":463,"priority":346},"agents/ce-framework-docs-researcher.agent.md",{"path":465,"priority":346},"agents/ce-git-history-analyzer.agent.md",{"path":467,"priority":346},"agents/ce-issue-intelligence-analyst.agent.md",{"path":469,"priority":346},"agents/ce-julik-frontend-races-reviewer.agent.md",{"path":471,"priority":346},"agents/ce-kieran-python-reviewer.agent.md",{"path":473,"priority":346},"agents/ce-kieran-rails-reviewer.agent.md",{"path":475,"priority":346},"agents/ce-kieran-typescript-reviewer.agent.md",{"path":477,"priority":346},"agents/ce-learnings-researcher.agent.md",{"path":479,"priority":346},"agents/ce-maintainability-reviewer.agent.md",{"path":481,"priority":346},"agents/ce-pattern-recognition-specialist.agent.md",{"path":483,"priority":346},"agents/ce-performance-oracle.agent.md",{"path":485,"priority":346},"agents/ce-performance-reviewer.agent.md",{"path":487,"priority":346},"agents/ce-pr-comment-resolver.agent.md",{"path":489,"priority":346},"agents/ce-previous-comments-reviewer.agent.md",{"path":491,"priority":346},"agents/ce-product-lens-reviewer.agent.md",{"path":493,"priority":346},"agents/ce-project-standards-reviewer.agent.md",{"path":495,"priority":346},"agents/ce-reliability-reviewer.agent.md",{"path":497,"priority":346},"agents/ce-repo-research-analyst.agent.md",{"path":499,"priority":346},"agents/ce-schema-drift-detector.agent.md",{"path":501,"priority":346},"agents/ce-scope-guardian-reviewer.agent.md",{"path":503,"priority":346},"agents/ce-security-lens-reviewer.agent.md",{"path":505,"priority":346},"agents/ce-security-reviewer.agent.md",{"path":507,"priority":346},"agents/ce-security-sentinel.agent.md",{"path":509,"priority":346},"agents/ce-session-historian.agent.md",{"path":511,"priority":346},"agents/ce-slack-researcher.agent.md",{"path":513,"priority":346},"agents/ce-spec-flow-analyzer.agent.md",{"path":515,"priority":346},"agents/ce-swift-ios-reviewer.agent.md",{"path":517,"priority":346},"agents/ce-testing-reviewer.agent.md",{"path":519,"priority":346},"agents/ce-web-researcher.agent.md",{"path":521,"priority":346},".codex-plugin/plugin.json",{"path":523,"priority":346},".cursor-plugin/plugin.json",{"basePath":525,"description":526,"displayName":527,"installMethods":528,"rationale":529,"selectedPaths":530,"source":335,"sourceLanguage":18,"type":266},"plugins/coding-tutor","Personalized coding tutorials that use your actual codebase for examples with spaced repetition quizzes","coding-tutor",{"claudeCode":527},"plugin manifest at plugins/coding-tutor/.claude-plugin/plugin.json",[531,532,533,535,537,539,541,542],{"path":341,"priority":334},{"path":343,"priority":334},{"path":534,"priority":349},"skills/coding-tutor/SKILL.md",{"path":536,"priority":346},"commands/quiz-me.md",{"path":538,"priority":346},"commands/sync-tutorials.md",{"path":540,"priority":346},"commands/teach-me.md",{"path":521,"priority":346},{"path":523,"priority":346},{"basePath":276,"description":272,"displayName":263,"installMethods":544,"rationale":545,"selectedPaths":546,"source":335,"sourceLanguage":18,"type":277},{"claudeCode":12},"marketplace.json at .cursor-plugin/marketplace.json",[547,549,550],{"path":548,"priority":334},".cursor-plugin/marketplace.json",{"path":343,"priority":334},{"path":345,"priority":346},{"basePath":552,"description":553,"displayName":527,"installMethods":554,"rationale":555,"selectedPaths":556,"source":335,"sourceLanguage":18,"type":255},"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",[557,559,562,564,566],{"path":558,"priority":334},"SKILL.md",{"path":560,"priority":561},"scripts/create_tutorial.py","low",{"path":563,"priority":561},"scripts/index_tutorials.py",{"path":565,"priority":561},"scripts/quiz_priority.py",{"path":567,"priority":561},"scripts/setup_tutorials.py",{"basePath":569,"description":570,"displayName":571,"installMethods":572,"rationale":573,"selectedPaths":574,"source":335,"sourceLanguage":18,"type":255},"plugins/compound-engineering/skills/ce-agent-native-architecture","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.","ce-agent-native-architecture",{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-agent-native-architecture/SKILL.md",[575,576,578,580,582,584,586,588,590,592,594,596,598,600,602,604],{"path":558,"priority":334},{"path":577,"priority":349},"references/action-parity-discipline.md",{"path":579,"priority":349},"references/agent-execution-patterns.md",{"path":581,"priority":349},"references/agent-native-testing.md",{"path":583,"priority":349},"references/architecture-patterns.md",{"path":585,"priority":349},"references/checklists.md",{"path":587,"priority":349},"references/dynamic-context-injection.md",{"path":589,"priority":349},"references/files-universal-interface.md",{"path":591,"priority":349},"references/from-primitives-to-domain-tools.md",{"path":593,"priority":349},"references/mcp-tool-design.md",{"path":595,"priority":349},"references/mobile-patterns.md",{"path":597,"priority":349},"references/product-implications.md",{"path":599,"priority":349},"references/refactoring-to-prompt-native.md",{"path":601,"priority":349},"references/self-modification.md",{"path":603,"priority":349},"references/shared-workspace-architecture.md",{"path":605,"priority":349},"references/system-prompt-design.md",{"basePath":607,"description":608,"displayName":609,"installMethods":610,"rationale":611,"selectedPaths":612,"source":335,"sourceLanguage":18,"type":255},"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",[613],{"path":558,"priority":334},{"basePath":615,"description":616,"displayName":617,"installMethods":618,"rationale":619,"selectedPaths":620,"source":335,"sourceLanguage":18,"type":255},"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",[621,622,624,626,628,630],{"path":558,"priority":334},{"path":623,"priority":349},"references/handoff.md",{"path":625,"priority":349},"references/requirements-capture.md",{"path":627,"priority":349},"references/synthesis-summary.md",{"path":629,"priority":349},"references/universal-brainstorming.md",{"path":631,"priority":349},"references/visual-communication.md",{"basePath":633,"description":634,"displayName":635,"installMethods":636,"rationale":637,"selectedPaths":638,"source":335,"sourceLanguage":18,"type":255},"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",[639,640],{"path":558,"priority":334},{"path":641,"priority":561},"scripts/clean-gone",{"basePath":643,"description":644,"displayName":645,"installMethods":646,"rationale":647,"selectedPaths":648,"source":335,"sourceLanguage":18,"type":255},"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",[649,650,652,654,656,658,660,662,664,666],{"path":558,"priority":334},{"path":651,"priority":349},"references/bulk-preview.md",{"path":653,"priority":349},"references/diff-scope.md",{"path":655,"priority":349},"references/findings-schema.json",{"path":657,"priority":349},"references/persona-catalog.md",{"path":659,"priority":349},"references/review-output-template.md",{"path":661,"priority":349},"references/subagent-template.md",{"path":663,"priority":349},"references/tracker-defer.md",{"path":665,"priority":349},"references/validator-template.md",{"path":667,"priority":349},"references/walkthrough.md",{"basePath":669,"description":670,"displayName":671,"installMethods":672,"rationale":673,"selectedPaths":674,"source":335,"sourceLanguage":18,"type":255},"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",[675],{"path":558,"priority":334},{"basePath":677,"description":678,"displayName":679,"installMethods":680,"rationale":681,"selectedPaths":682,"source":335,"sourceLanguage":18,"type":255},"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",[683,684,686],{"path":558,"priority":334},{"path":685,"priority":349},"references/branch-creation.md",{"path":687,"priority":349},"references/pr-description-writing.md",{"basePath":689,"description":690,"displayName":691,"installMethods":692,"rationale":693,"selectedPaths":694,"source":335,"sourceLanguage":18,"type":255},"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",[695,696,698,700,702],{"path":558,"priority":334},{"path":697,"priority":561},"assets/resolution-template.md",{"path":699,"priority":349},"references/schema.yaml",{"path":701,"priority":349},"references/yaml-schema.md",{"path":703,"priority":561},"scripts/validate-frontmatter.py",{"basePath":705,"description":706,"displayName":707,"installMethods":708,"rationale":709,"selectedPaths":710,"source":335,"sourceLanguage":18,"type":255},"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",[711,712,713,715,716,717],{"path":558,"priority":334},{"path":697,"priority":561},{"path":714,"priority":349},"references/per-action-flows.md",{"path":699,"priority":349},{"path":701,"priority":349},{"path":703,"priority":561},{"basePath":719,"description":720,"displayName":721,"installMethods":722,"rationale":723,"selectedPaths":724,"source":335,"sourceLanguage":18,"type":255},"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",[725,726,728,730],{"path":558,"priority":334},{"path":727,"priority":349},"references/anti-patterns.md",{"path":729,"priority":349},"references/defense-in-depth.md",{"path":731,"priority":349},"references/investigation-techniques.md",{"basePath":733,"description":734,"displayName":735,"installMethods":736,"rationale":737,"selectedPaths":738,"source":335,"sourceLanguage":18,"type":255},"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",[739,740,742,744,746,748,750],{"path":558,"priority":334},{"path":741,"priority":349},"references/tier-browser-reel.md",{"path":743,"priority":349},"references/tier-screenshot-reel.md",{"path":745,"priority":349},"references/tier-static-screenshots.md",{"path":747,"priority":349},"references/tier-terminal-recording.md",{"path":749,"priority":349},"references/upload-and-approval.md",{"path":751,"priority":561},"scripts/capture-demo.py",{"basePath":753,"description":754,"displayName":755,"installMethods":756,"rationale":757,"selectedPaths":758,"source":335,"sourceLanguage":18,"type":255},"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",[759,760,762,764,766,768,770],{"path":558,"priority":334},{"path":761,"priority":349},"references/architecture.md",{"path":763,"priority":349},"references/controllers.md",{"path":765,"priority":349},"references/frontend.md",{"path":767,"priority":349},"references/gems.md",{"path":769,"priority":349},"references/models.md",{"path":771,"priority":349},"references/testing.md",{"basePath":773,"description":774,"displayName":775,"installMethods":776,"rationale":777,"selectedPaths":778,"source":335,"sourceLanguage":18,"type":255},"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",[779,780,781,782,784,785,786,788],{"path":558,"priority":334},{"path":651,"priority":349},{"path":655,"priority":349},{"path":783,"priority":349},"references/open-questions-defer.md",{"path":659,"priority":349},{"path":661,"priority":349},{"path":787,"priority":349},"references/synthesis-and-presentation.md",{"path":667,"priority":349},{"basePath":790,"description":791,"displayName":792,"installMethods":793,"rationale":794,"selectedPaths":795,"source":335,"sourceLanguage":18,"type":255},"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",[796],{"path":558,"priority":334},{"basePath":798,"description":799,"displayName":800,"installMethods":801,"rationale":802,"selectedPaths":803,"source":335,"sourceLanguage":18,"type":255},"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",[804,805,807,809,811,813],{"path":558,"priority":334},{"path":806,"priority":561},"scripts/compose_images.py",{"path":808,"priority":561},"scripts/edit_image.py",{"path":810,"priority":561},"scripts/gemini_images.py",{"path":812,"priority":561},"scripts/generate_image.py",{"path":814,"priority":561},"scripts/multi_turn_chat.py",{"basePath":816,"description":817,"displayName":818,"installMethods":819,"rationale":820,"selectedPaths":821,"source":335,"sourceLanguage":18,"type":255},"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",[822,823,825,827],{"path":558,"priority":334},{"path":824,"priority":349},"references/post-ideation-workflow.md",{"path":826,"priority":349},"references/universal-ideation.md",{"path":828,"priority":349},"references/web-research-cache.md",{"basePath":251,"description":10,"displayName":254,"installMethods":830,"rationale":831,"selectedPaths":832,"source":335,"sourceLanguage":18,"type":255},{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-optimize/SKILL.md",[833,834,836,838,840,842,844,846,848,850,852],{"path":558,"priority":334},{"path":835,"priority":349},"references/example-hard-spec.yaml",{"path":837,"priority":349},"references/example-judge-spec.yaml",{"path":839,"priority":349},"references/experiment-log-schema.yaml",{"path":841,"priority":349},"references/experiment-prompt-template.md",{"path":843,"priority":349},"references/judge-prompt-template.md",{"path":845,"priority":349},"references/optimize-spec-schema.yaml",{"path":847,"priority":349},"references/usage-guide.md",{"path":849,"priority":561},"scripts/experiment-worktree.sh",{"path":851,"priority":561},"scripts/measure.sh",{"path":853,"priority":561},"scripts/parallel-probe.sh",{"basePath":855,"description":856,"displayName":857,"installMethods":858,"rationale":859,"selectedPaths":860,"source":335,"sourceLanguage":18,"type":255},"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",[861,862,864,866,868,869,871],{"path":558,"priority":334},{"path":863,"priority":349},"references/deepening-workflow.md",{"path":865,"priority":349},"references/plan-handoff.md",{"path":867,"priority":349},"references/plan-template.md",{"path":627,"priority":349},{"path":870,"priority":349},"references/universal-planning.md",{"path":631,"priority":349},{"basePath":873,"description":874,"displayName":875,"installMethods":876,"rationale":877,"selectedPaths":878,"source":335,"sourceLanguage":18,"type":255},"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",[879,880,882,884,886,888,890,892,894,896,898,900,902,904,906,908],{"path":558,"priority":334},{"path":881,"priority":349},"references/dev-server-astro.md",{"path":883,"priority":349},"references/dev-server-detection.md",{"path":885,"priority":349},"references/dev-server-next.md",{"path":887,"priority":349},"references/dev-server-nuxt.md",{"path":889,"priority":349},"references/dev-server-procfile.md",{"path":891,"priority":349},"references/dev-server-rails.md",{"path":893,"priority":349},"references/dev-server-remix.md",{"path":895,"priority":349},"references/dev-server-sveltekit.md",{"path":897,"priority":349},"references/dev-server-vite.md",{"path":899,"priority":349},"references/ide-detection.md",{"path":901,"priority":349},"references/launch-json-schema.md",{"path":903,"priority":561},"scripts/detect-project-type.sh",{"path":905,"priority":561},"scripts/read-launch-json.sh",{"path":907,"priority":561},"scripts/resolve-package-manager.sh",{"path":909,"priority":561},"scripts/resolve-port.sh",{"basePath":911,"description":912,"displayName":913,"installMethods":914,"rationale":915,"selectedPaths":916,"source":335,"sourceLanguage":18,"type":255},"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",[917,918,920],{"path":558,"priority":334},{"path":919,"priority":349},"references/interview.md",{"path":921,"priority":349},"references/report-template.md",{"basePath":923,"description":924,"displayName":925,"installMethods":926,"rationale":927,"selectedPaths":928,"source":335,"sourceLanguage":18,"type":255},"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",[929,930],{"path":558,"priority":334},{"path":931,"priority":349},"references/hitl-review.md",{"basePath":933,"description":934,"displayName":935,"installMethods":936,"rationale":937,"selectedPaths":938,"source":335,"sourceLanguage":18,"type":255},"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",[939,940],{"path":558,"priority":334},{"path":941,"priority":561},"scripts/list-plugin-releases.py",{"basePath":943,"description":944,"displayName":945,"installMethods":946,"rationale":947,"selectedPaths":948,"source":335,"sourceLanguage":18,"type":255},"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",[949],{"path":558,"priority":334},{"basePath":951,"description":952,"displayName":953,"installMethods":954,"rationale":955,"selectedPaths":956,"source":335,"sourceLanguage":18,"type":255},"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",[957,958,960,962,964,966,968],{"path":558,"priority":334},{"path":959,"priority":349},"references/full-mode.md",{"path":961,"priority":349},"references/targeted-mode.md",{"path":963,"priority":561},"scripts/get-pr-comments",{"path":965,"priority":561},"scripts/get-thread-for-comment",{"path":967,"priority":561},"scripts/reply-to-pr-thread",{"path":969,"priority":561},"scripts/resolve-pr-thread",{"basePath":971,"description":972,"displayName":973,"installMethods":974,"rationale":975,"selectedPaths":976,"source":335,"sourceLanguage":18,"type":255},"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",[977,978,980,982,984,986],{"path":558,"priority":334},{"path":979,"priority":349},"references/compound-engineering-feedback-format.md",{"path":981,"priority":349},"references/extensive-analysis.md",{"path":983,"priority":349},"references/install-riffrec.md",{"path":985,"priority":349},"references/quick-bug-report.md",{"path":987,"priority":561},"scripts/analyze_riffrec_zip.py",{"basePath":989,"description":990,"displayName":991,"installMethods":992,"rationale":993,"selectedPaths":994,"source":335,"sourceLanguage":18,"type":255},"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",[995,996,998,1000,1002],{"path":558,"priority":334},{"path":997,"priority":561},"scripts/discover-sessions.sh",{"path":999,"priority":561},"scripts/extract-errors.py",{"path":1001,"priority":561},"scripts/extract-metadata.py",{"path":1003,"priority":561},"scripts/extract-skeleton.py",{"basePath":1005,"description":1006,"displayName":1007,"installMethods":1008,"rationale":1009,"selectedPaths":1010,"source":335,"sourceLanguage":18,"type":255},"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",[1011,1012,1014],{"path":558,"priority":334},{"path":1013,"priority":349},"references/config-template.yaml",{"path":1015,"priority":561},"scripts/check-health",{"basePath":1017,"description":1018,"displayName":1019,"installMethods":1020,"rationale":1021,"selectedPaths":1022,"source":335,"sourceLanguage":18,"type":255},"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",[1023],{"path":558,"priority":334},{"basePath":1025,"description":1026,"displayName":1027,"installMethods":1028,"rationale":1029,"selectedPaths":1030,"source":335,"sourceLanguage":18,"type":255},"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",[1031],{"path":558,"priority":334},{"basePath":1033,"description":1034,"displayName":1035,"installMethods":1036,"rationale":1037,"selectedPaths":1038,"source":335,"sourceLanguage":18,"type":255},"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",[1039,1040,1041],{"path":558,"priority":334},{"path":919,"priority":349},{"path":1042,"priority":349},"references/strategy-template.md",{"basePath":1044,"description":1045,"displayName":1046,"installMethods":1047,"rationale":1048,"selectedPaths":1049,"source":335,"sourceLanguage":18,"type":255},"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",[1050],{"path":558,"priority":334},{"basePath":1052,"description":1053,"displayName":1054,"installMethods":1055,"rationale":1056,"selectedPaths":1057,"source":335,"sourceLanguage":18,"type":255},"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",[1058],{"path":558,"priority":334},{"basePath":1060,"description":1061,"displayName":1062,"installMethods":1063,"rationale":1064,"selectedPaths":1065,"source":335,"sourceLanguage":18,"type":255},"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",[1066,1067,1069,1071],{"path":558,"priority":334},{"path":1068,"priority":561},"scripts/currently-loaded-version.sh",{"path":1070,"priority":561},"scripts/marketplace-name.sh",{"path":1072,"priority":561},"scripts/upstream-version.sh",{"basePath":1074,"description":1075,"displayName":1076,"installMethods":1077,"rationale":1078,"selectedPaths":1079,"source":335,"sourceLanguage":18,"type":255},"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",[1080,1081,1083],{"path":558,"priority":334},{"path":1082,"priority":349},"references/shipping-workflow.md",{"path":663,"priority":349},{"basePath":1085,"description":1086,"displayName":1087,"installMethods":1088,"rationale":1089,"selectedPaths":1090,"source":335,"sourceLanguage":18,"type":255},"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",[1091,1092,1094,1095],{"path":558,"priority":334},{"path":1093,"priority":349},"references/codex-delegation-workflow.md",{"path":1082,"priority":349},{"path":663,"priority":349},{"basePath":1097,"description":1098,"displayName":1099,"installMethods":1100,"rationale":1101,"selectedPaths":1102,"source":335,"sourceLanguage":18,"type":255},"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",[1103,1104],{"path":558,"priority":334},{"path":1105,"priority":561},"scripts/worktree-manager.sh",{"basePath":1107,"description":1108,"displayName":1109,"installMethods":1110,"rationale":1111,"selectedPaths":1112,"source":335,"sourceLanguage":18,"type":255},"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",[1113,1114],{"path":558,"priority":334},{"path":663,"priority":349},{"basePath":276,"description":1116,"displayName":1117,"installMethods":1118,"rationale":1119,"selectedPaths":1120,"source":335,"sourceLanguage":18,"type":1137},"Official Compound Engineering plugin for Claude Code, Codex, and more","@every-env/compound-plugin",{"npm":1117},"cli ecosystem detected at /",[1121,1123,1124,1125,1127,1129,1131,1133,1135],{"path":1122,"priority":334},"package.json",{"path":343,"priority":334},{"path":345,"priority":346},{"path":1126,"priority":349},"src/index.ts",{"path":1128,"priority":561},"src/commands/cleanup.ts",{"path":1130,"priority":561},"src/commands/convert.ts",{"path":1132,"priority":561},"src/commands/install.ts",{"path":1134,"priority":561},"src/commands/list.ts",{"path":1136,"priority":561},"src/commands/plugin-path.ts","cli",{"sources":1139},[1140],"manual",{"npmPackage":1117},{"closedIssues90d":237,"description":1143,"forks":238,"homepage":1144,"license":245,"openIssues90d":239,"pushedAt":240,"readmeSize":235,"stars":241,"topics":1145},"Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more","https://every.to/guides/compound-engineering",[1146,1147],"compound","engineering",{"downloads":243},{"classifiedAt":1150,"discoverAt":1151,"extractAt":1152,"githubAt":1152,"npmAt":1153,"updatedAt":1150},1778686639998,1778686632796,1778686635929,1778686638203,[220,218,219,217,221],{"evaluatedAt":249,"extractAt":299,"updatedAt":249},[],[1158,1188,1214,1235,1261,1291],{"_creationTime":1159,"_id":1160,"community":1161,"display":1162,"identity":1168,"providers":1174,"relations":1180,"tags":1183,"workflow":1184},1778698296017.8315,"k17dzgrxxkxpeqmtcn5v3tjmad86n5tm",{"reviewCount":8},{"description":1163,"installMethods":1164,"name":1166,"sourceUrl":1167},"과잉 엔지니어링 패턴이 감지되면 자동으로 활성화됩니다: (1) 사용자가 명시적으로 변경을 요청하지 않은 코드나 파일을 수정하는 경우 (2) 요청되지 않은 새로운 추상화 레이어(class, interface, factory, wrapper)를 생성하는 경우 (3) 요청되지 않은 주석, 문서, JSDoc, 타입 어노테이션을 추가하는 경우 (4) 요청되지 않은 새로운 의존성을 도입하는 경우 (5) 최소한의 편집 대신 파일 전체를 다시 작성하는 경우 (6) diff 범위가 사용자의 요청을 명백히 초과하는 경우 (7) 사용자가 \"너무 많아\", \"거기는 건드리지 마\", \"X만 변경해\", \"간단하게\", \"그만\" 등의 신호를 보내는 경우 (8) 발생할 수 없는 시나리오에 대한 에러 처리, 유효성 검사, 방어적 코드를 추가하는 경우 (9) 요청되지 않은 테스트, 설정 스캐폴딩, 문서를 생성하는 경우\n",{"claudeCode":1165},"uucz/moyu","Moyu (摸鱼)","https://github.com/uucz/moyu",{"basePath":1169,"githubOwner":1170,"githubRepo":1171,"locale":1172,"slug":1173,"type":255},"skills/moyu-ko","uucz","moyu","ko","moyu-ko",{"evaluate":1175,"extract":1179},{"promptVersionExtension":210,"promptVersionScoring":211,"score":214,"tags":1176,"targetMarket":222,"tier":223},[1177,220,221,305,1178],"ai-assist","refactoring",{"commitSha":289,"license":245},{"parentExtensionId":1181,"repoId":1182},"k17a8j7hxkm1n8dabrtcwp2z2d86nr39","kd7ccbpk8y3xm113xt8wy1c5jd86n94h",[1177,220,305,221,1178],{"evaluatedAt":1185,"extractAt":1186,"updatedAt":1187},1778698415064,1778698296017,1778698589704,{"_creationTime":1189,"_id":1190,"community":1191,"display":1192,"identity":1198,"providers":1202,"relations":1208,"tags":1210,"workflow":1211},1778687399826.024,"k17atkje2ddcydy18p1qa43ks186n9c0",{"reviewCount":8},{"description":1193,"installMethods":1194,"name":1196,"sourceUrl":1197},"Creates, runs, and analyzes Arize experiments for evaluating and comparing model performance. Covers experiment CRUD, exporting runs, comparing results, and evaluation workflows using the ax CLI. Use when the user mentions create experiment, run experiment, compare models, model performance, evaluate AI, experiment results, benchmark, A/B test models, or measure accuracy.",{"claudeCode":1195},"github/awesome-copilot","arize-experiment","https://github.com/github/awesome-copilot",{"basePath":1199,"githubOwner":1200,"githubRepo":1201,"locale":18,"slug":1196,"type":255},"skills/arize-experiment","github","awesome-copilot",{"evaluate":1203,"extract":1207},{"promptVersionExtension":210,"promptVersionScoring":211,"score":214,"tags":1204,"targetMarket":222,"tier":223},[1205,219,218,1206,1137],"arize","model-evaluation",{"commitSha":289},{"repoId":1209},"kd7dsmv976w8rtkqnjjfdtfgks86nnmw",[1205,1137,218,219,1206],{"evaluatedAt":1212,"extractAt":1213,"updatedAt":1212},1778689184664,1778687399826,{"_creationTime":1215,"_id":1216,"community":1217,"display":1218,"identity":1222,"providers":1225,"relations":1231,"tags":1232,"workflow":1233},1778687399826.0247,"k173skx1fvkafn38prsv2d0qbh86nn4h",{"reviewCount":8},{"description":1219,"installMethods":1220,"name":1221,"sourceUrl":1197},"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":1195},"Arize Prompt Optimization",{"basePath":1223,"githubOwner":1200,"githubRepo":1201,"locale":18,"slug":1224,"type":255},"skills/arize-prompt-optimization","arize-prompt-optimization",{"evaluate":1226,"extract":1230},{"promptVersionExtension":210,"promptVersionScoring":211,"score":214,"tags":1227,"targetMarket":222,"tier":223},[1228,221,217,1205,1137,1229],"llm","data-analysis",{"commitSha":289,"license":245},{"repoId":1209},[1205,1137,1229,1228,217,221],{"evaluatedAt":1234,"extractAt":1213,"updatedAt":1234},1778689257343,{"_creationTime":1236,"_id":1237,"community":1238,"display":1239,"identity":1245,"providers":1249,"relations":1254,"tags":1256,"workflow":1257},1778675659559.518,"k17bjgfyvbnt05kpma9n0gn4j186n152",{"reviewCount":8},{"description":1240,"installMethods":1241,"name":1243,"sourceUrl":1244},"Applies prompt repetition to improve accuracy for non-reasoning LLMs",{"claudeCode":1242},"asklokesh/loki-mode","prompt-optimization","https://github.com/asklokesh/loki-mode",{"basePath":1246,"githubOwner":1247,"githubRepo":1248,"locale":18,"slug":1243,"type":255},"agent-skills/prompt-optimization","asklokesh","loki-mode",{"evaluate":1250,"extract":1253},{"promptVersionExtension":210,"promptVersionScoring":211,"score":214,"tags":1251,"targetMarket":222,"tier":223},[1228,221,1252,217],"accuracy",{"commitSha":289},{"repoId":1255},"kd7dy44r49793jt8bt02wdezk586nxsn",[1252,1228,217,221],{"evaluatedAt":1258,"extractAt":1259,"updatedAt":1260},1778675713014,1778675659559,1778675796091,{"_creationTime":1262,"_id":1263,"community":1264,"display":1265,"identity":1271,"providers":1276,"relations":1284,"tags":1287,"workflow":1288},1778699018122.808,"k179cp8dcc6tj4x327s72vgkp186m472",{"reviewCount":8},{"description":1266,"installMethods":1267,"name":1269,"sourceUrl":1270},"Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.",{"claudeCode":1268},"wshobson/agents","Vector Index Tuning","https://github.com/wshobson/agents",{"basePath":1272,"githubOwner":1273,"githubRepo":1274,"locale":18,"slug":1275,"type":255},"plugins/llm-application-dev/skills/vector-index-tuning","wshobson","agents","vector-index-tuning",{"evaluate":1277,"extract":1283},{"promptVersionExtension":210,"promptVersionScoring":211,"score":281,"tags":1278,"targetMarket":222,"tier":223},[1279,1280,1281,1282,217,219],"vector-database","hns","quantization","performance",{"commitSha":289,"license":245},{"parentExtensionId":1285,"repoId":1286},"k1719fyk9jrke6aq23wbyf8ej586n3af","kd74de64zj0axtg5b8t7eqqe2x86nske",[1280,219,217,1282,1281,1279],{"evaluatedAt":1289,"extractAt":1290,"updatedAt":1289},1778701887084,1778699018122,{"_creationTime":1292,"_id":1293,"community":1294,"display":1295,"identity":1301,"providers":1305,"relations":1313,"tags":1316,"workflow":1317},1778696691708.3264,"k179thjzaw5kepc7zhdj9sat3n86mcqp",{"reviewCount":8},{"description":1296,"installMethods":1297,"name":1299,"sourceUrl":1300},"Validate pending migrations for foreign key consistency, rollback safety, and best practices",{"claudeCode":1298},"ruvnet/ruflo","migrate-validate","https://github.com/ruvnet/ruflo",{"basePath":1302,"githubOwner":1303,"githubRepo":1304,"locale":18,"slug":1299,"type":255},"plugins/ruflo-migrations/skills/migrate-validate","ruvnet","ruflo",{"evaluate":1306,"extract":1312},{"promptVersionExtension":210,"promptVersionScoring":211,"score":214,"tags":1307,"targetMarket":222,"tier":223},[1308,1309,1310,1311,220,305],"database","migrations","sql","validation",{"commitSha":289},{"parentExtensionId":1314,"repoId":1315},"k176me0sh9b6bc3gzttnywx4w986njzh","kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[220,1308,305,1309,1310,1311],{"evaluatedAt":1318,"extractAt":1319,"updatedAt":1318},1778701008912,1778696691708]