[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-EveryInc-ce-riffrec-feedback-analysis-zh-CN":3,"guides-for-EveryInc-ce-riffrec-feedback-analysis":1158,"similar-k17akpsk99wfpp6s3xwjf64h7h86mtbm-zh-CN":1159},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":253,"isFallback":234,"parentExtension":259,"providers":318,"relations":322,"repo":323,"tags":1156,"workflow":1157},1778686640222.797,"k17akpsk99wfpp6s3xwjf64h7h86mtbm",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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.",{"claudeCode":12},"EveryInc/compound-engineering-plugin","Riffrec Feedback Analysis","https://github.com/EveryInc/compound-engineering-plugin",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":232,"workflow":251},1778687353683.7856,"kn7bxrqydgen02bgz11qh28ka586md97","en",{"checks":20,"evaluatedAt":191,"extensionSummary":192,"features":193,"nonGoals":199,"practices":204,"prerequisites":208,"promptVersionExtension":213,"promptVersionScoring":214,"purpose":215,"rationale":216,"score":217,"summary":218,"tags":219,"targetMarket":225,"tier":226,"useCases":227},[21,26,29,32,36,39,43,46,50,54,58,61,64,66,70,74,77,80,83,86,90,94,97,101,104,107,110,113,116,119,123,126,130,134,138,141,145,148,152,155,158,161,164,167,170,174,178,181,184,188],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly names the problem of processing Riffrec product feedback and specifies when it should be used by mentioning the input types and intended routing.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers a structured workflow for processing Riffrec feedback, routing it to specific analysis paths (setup, quick bug report, extensive analysis), which goes beyond basic transcription or analysis.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill and its associated script appear to cover the complete lifecycle of processing Riffrec feedback, from initial analysis to generating structured artifacts for downstream agents.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill is focused on analyzing Riffrec feedback, including setup, quick reports, and extensive analysis, which represents a coherent workflow.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the skill's purpose and capabilities as detailed in the SKILL.md file.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Precise Purpose","The description clearly states the skill's purpose (Riffrec product-feedback workflow) and its triggers (riffrec-*.zip, video/audio recording, how-to questions) and routes.",{"category":40,"check":44,"severity":24,"summary":45},"Concise Frontmatter","The frontmatter is concise, self-contained, and effectively summarizes the core capability and routing logic.",{"category":47,"check":48,"severity":24,"summary":49},"Documentation","Concise Body","The SKILL.md body is concise and delegates deeper material to referenced markdown files, adhering to progressive disclosure.",{"category":51,"check":52,"severity":24,"summary":53},"Context","Progressive Disclosure","The SKILL.md outlines the workflow and links to specific reference files for setup, quick bug reports, and extensive analysis, demonstrating progressive disclosure.",{"category":51,"check":55,"severity":56,"summary":57},"Forked exploration","not_applicable","This skill is primarily analytical and does not involve deep exploration or code review that would necessitate `context: fork`.",{"category":22,"check":59,"severity":24,"summary":60},"Usage examples","The SKILL.md and its references provide clear instructions on how to use the skill for different feedback scenarios, including setup and analysis paths.",{"category":22,"check":62,"severity":24,"summary":63},"Edge cases","The skill and its scripts handle edge cases such as ambiguous input, missing transcription models, and different media types, providing recovery paths or clear messages.",{"category":40,"check":48,"severity":24,"summary":65},"The SKILL.md body is concise and delegates detailed procedures to reference files.",{"category":67,"check":68,"severity":24,"summary":69},"Safety","Halt on unexpected state","The script includes checks for file existence and handles potential errors gracefully, halting if necessary with informative messages.",{"category":71,"check":72,"severity":24,"summary":73},"Portability","Cross-skill coupling","The skill is self-contained and does not implicitly rely on other skills, although it explicitly mentions handoff to `ce-brainstorm`.",{"category":33,"check":75,"severity":56,"summary":76},"Scoped tools","This is a skill, not an extension that exposes tools directly, therefore this check is not applicable.",{"category":47,"check":78,"severity":24,"summary":79},"Configuration & parameter reference","The script's arguments and environment variables (like OPENAI_API_KEY) are documented or clear from context. Configuration options for output directory are also explicit.",{"category":33,"check":81,"severity":56,"summary":82},"Tool naming","As this is a skill and not an extension exposing tools directly, this check is not applicable.",{"category":33,"check":84,"severity":24,"summary":85},"Minimal I/O surface","The script's input (source path) and output (generated markdown files and directories) are well-defined and focused on the task of analysis and artifact generation.",{"category":87,"check":88,"severity":24,"summary":89},"License","License usability","The project is licensed under the MIT license, which is permissive and readily usable.",{"category":91,"check":92,"severity":24,"summary":93},"Maintenance","Commit recency","The repository shows recent commits, indicating active maintenance.",{"category":91,"check":95,"severity":24,"summary":96},"Dependency Management","The project uses `bun install` and includes `package.json`, indicating standard dependency management practices. The `LICENSE` file is present, and `CHANGELOG.md` is mentioned.",{"category":98,"check":99,"severity":24,"summary":100},"Security","Secret Management","The script relies on an external environment variable (OPENAI_API_KEY) for sensitive operations, which is a standard and appropriate way to handle secrets.",{"category":98,"check":102,"severity":24,"summary":103},"Injection","The script handles file paths and external data carefully, using `shutil.copy2` and `safe_extract` to prevent path traversal or arbitrary code execution from input files.",{"category":98,"check":105,"severity":24,"summary":106},"Transitive Supply-Chain Grenades","The script relies on local executables (python, ffmpeg, curl) and does not fetch or execute arbitrary remote code. Media processing is done via locally installed tools.",{"category":98,"check":108,"severity":24,"summary":109},"Sandbox Isolation","The script operates on provided input paths and writes artifacts to specified output directories, respecting typical sandbox boundaries. It does not appear to modify files outside its designated scope.",{"category":98,"check":111,"severity":24,"summary":112},"Sandbox escape primitives","No evidence of detached process spawns or deny-retry loops was found in the provided script.",{"category":98,"check":114,"severity":24,"summary":115},"Data Exfiltration","The script's primary interaction with external services is transcription via OpenAI API, which requires an API key passed via environment variable. No other undocumented outbound calls or exfiltration mechanisms were observed.",{"category":98,"check":117,"severity":24,"summary":118},"Hidden Text Tricks","The provided source code and markdown files do not contain any hidden text, control characters, or Unicode tricks designed to manipulate the model.",{"category":120,"check":121,"severity":24,"summary":122},"Hooks","Opaque code execution","The Python script is written in clear, readable Python and does not use obfuscation techniques like base64 encoding or runtime code fetching.",{"category":71,"check":124,"severity":24,"summary":125},"Structural Assumption","The script handles file paths robustly and allows the output directory to be specified, avoiding assumptions about rigid project structures.",{"category":127,"check":128,"severity":24,"summary":129},"Trust","Issues Attention","The repository has a healthy ratio of closed to open issues over the last 90 days, and the number of open issues is not excessive, indicating active maintainer engagement.",{"category":131,"check":132,"severity":24,"summary":133},"Versioning","Release Management","The project has a `package.json` with a version field and GitHub releases, clearly indicating version management.",{"category":135,"check":136,"severity":24,"summary":137},"Execution","Validation","The script performs input validation for file paths and handles potential errors from subprocess calls and JSON parsing, though it doesn't explicitly use a schema library for all inputs.",{"category":98,"check":139,"severity":24,"summary":140},"Unguarded Destructive Operations","The script primarily performs file reads and writes to specified output directories. It does not contain operations like `rm -rf` or direct file modifications outside of its artifact generation.",{"category":142,"check":143,"severity":24,"summary":144},"Code Execution","Error Handling","The script includes error handling for file operations, subprocess calls, and external API interactions, providing informative messages and exiting non-zero on failure.",{"category":142,"check":146,"severity":56,"summary":147},"Logging","The script logs output to stdout and stderr, but does not implement a specific local audit log file. Given the nature of the script, this is not a critical omission.",{"category":149,"check":150,"severity":24,"summary":151},"Compliance","GDPR","The script processes user-provided feedback data and potentially sends it for transcription via OpenAI. However, it does not explicitly handle personal data beyond what's in the feedback itself and relies on OpenAI's policies for transcription data handling.",{"category":149,"check":153,"severity":24,"summary":154},"Target market","The skill processes general product feedback and uses a global transcription service. There are no specific regional or jurisdictional limitations detected.",{"category":71,"check":156,"severity":24,"summary":157},"Runtime stability","The script relies on common tools like Python, ffmpeg, and curl, and provides clear messages if they are missing. It should be reasonably portable across POSIX-like environments.",{"category":47,"check":159,"severity":24,"summary":160},"README","The project has a comprehensive README that explains its philosophy, workflow, installation, and contribution guidelines.",{"category":33,"check":162,"severity":56,"summary":163},"Tool surface size","This extension is a single skill with an associated Python script, not a collection of multiple tools or commands.",{"category":40,"check":165,"severity":56,"summary":166},"Overlapping near-synonym tools","As this is a single skill, there are no overlapping tools to evaluate.",{"category":47,"check":168,"severity":24,"summary":169},"Phantom features","All advertised features, such as processing different input types and generating specific markdown artifacts, are implemented in the provided script and SKILL.md.",{"category":171,"check":172,"severity":24,"summary":173},"Install","Installation instruction","The README provides detailed installation instructions for multiple platforms (Claude Code, Cursor, Codex, Copilot, etc.) and includes clear copy-paste commands and setup steps.",{"category":175,"check":176,"severity":24,"summary":177},"Errors","Actionable error messages","The script provides actionable error messages for missing dependencies, API errors, timeouts, and file processing issues, often suggesting remediation steps or reasons for failure.",{"category":135,"check":179,"severity":24,"summary":180},"Pinned dependencies","The project uses `bun install` with a `package.json`, suggesting dependency pinning. The Python script has a shebang and relies on standard libraries and `pip` for external dependencies (like OpenAI if used).",{"category":33,"check":182,"severity":56,"summary":183},"Dry-run preview","The script's primary function is analysis and artifact generation, which is inherently a read-only operation on the input and writing to output, so a dry-run mode is not applicable.",{"category":185,"check":186,"severity":24,"summary":187},"Protocol","Idempotent retry & timeouts","The script includes timeouts for subprocess calls and API requests. While not strictly focused on mutating operations, its artifact generation is idempotent based on input.",{"category":149,"check":189,"severity":24,"summary":190},"Telemetry opt-in","The script uses an API key via environment variable for transcription and does not appear to collect or transmit any telemetry by default.",1778687353570,"This skill analyzes Riffrec feedback bundles (zip files containing session data, recordings, and events) or standalone media files (video, audio, notes). It extracts transcripts, identifies key moments, and generates structured artifacts like analysis summaries, problem reports, and requirements kickoff documents, intended for use with other Compound Engineering skills.",[194,195,196,197,198],"Processes Riffrec zip bundles, video, audio, and notes files.","Transcribes audio/video and extracts key moments with screenshots.","Generates analysis, problem reports, and requirements kickoff documents.","Routes feedback to setup, quick bug report, or extensive analysis paths.","Integrates with `ce-brainstorm` for requirement refinement.",[200,201,202,203],"Implementing the Riffrec capture tool itself.","Performing code review or direct code fixes.","Acting as a user-facing bug tracker or issue creation tool.","Storing raw media files or extracted frames in version control by default.",[205,206,207],"Feedback analysis","Structured documentation","AI-assisted product development",[209,210,211,212],"Python 3.8+","ffmpeg (for media processing)","curl (for transcription)","OpenAI API key (optional, for transcription)","3.0.0","4.4.0","To convert raw product feedback recordings into structured, actionable evidence for AI-driven product development workflows, ensuring clear traceability and facilitating downstream analysis and planning.","The extension demonstrates high quality across all evaluated criteria, including clear documentation, robust error handling, and secure practices. There are no significant warnings or critical findings.",98,"A well-documented and robust skill for analyzing product feedback recordings, generating structured artifacts for downstream agents.",[220,221,222,223,224],"product-feedback","recording-analysis","transcription","reporting","workflow","global","verified",[228,229,230,231],"Analyzing recorded product feedback sessions to identify bugs and usability issues.","Extracting requirements from user recordings for feature development.","Providing structured input for AI-driven product brainstorming and planning.","Setting up a feedback capture workflow for development teams.",{"codeQuality":233,"collectedAt":235,"documentation":236,"maintenance":239,"popularity":245,"security":247,"testCoverage":250},{"hasLockfile":234},true,1778687330481,{"descriptionLength":237,"readmeSize":238},326,17582,{"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},1778687353683,{"basePath":254,"githubOwner":255,"githubRepo":256,"locale":18,"slug":257,"type":258},"plugins/compound-engineering/skills/ce-riffrec-feedback-analysis","EveryInc","compound-engineering-plugin","ce-riffrec-feedback-analysis","skill",{"_creationTime":260,"_id":261,"community":262,"display":263,"identity":267,"parentExtension":270,"providers":303,"relations":314,"tags":315,"workflow":316},1778686640222.7903,"k17d893df4em0e3pn8f55h1dxn86n09e",{"reviewCount":8},{"description":264,"installMethods":265,"name":266,"sourceUrl":14},"AI-powered development tools for code review, research, design, and workflow automation.",{"claudeCode":266},"compound-engineering",{"basePath":268,"githubOwner":255,"githubRepo":256,"locale":18,"slug":266,"type":269},"plugins/compound-engineering","plugin",{"_creationTime":271,"_id":272,"community":273,"display":274,"identity":278,"providers":281,"relations":297,"tags":299,"workflow":300},1778686640222.7908,"k17ef8php9wk308mkg59kdp6b186nzhx",{"reviewCount":8},{"description":275,"installMethods":276,"name":277,"sourceUrl":14},"Cursor plugin marketplace for Every Inc plugins",{"claudeCode":12},"Compound Engineering",{"basePath":279,"githubOwner":255,"githubRepo":256,"locale":18,"slug":256,"type":280},"","marketplace",{"evaluate":282,"extract":291},{"promptVersionExtension":283,"promptVersionScoring":214,"score":284,"tags":285,"targetMarket":225,"tier":226},"3.1.0",99,[286,287,288,289,290],"development-workflow","code-review","planning","documentation","ai-agents",{"commitSha":292,"license":248,"marketplace":293,"plugin":295},"HEAD",{"name":256,"pluginCount":294},2,{"mcpCount":8,"provider":296,"skillCount":8},"classify",{"repoId":298},"kd7e40my1b5g70tg0f60qg85ch86nn08",[290,287,286,289,288],{"evaluatedAt":301,"extractAt":302,"updatedAt":301},1778686722515,1778686640222,{"evaluate":304,"extract":311},{"promptVersionExtension":213,"promptVersionScoring":214,"score":217,"tags":305,"targetMarket":225,"tier":226},[306,307,287,308,289,309,288,310],"ai","developer-tools","research","workflow-automation","ideation",{"commitSha":292,"license":248,"plugin":312},{"mcpCount":8,"provider":296,"skillCount":313},37,{"parentExtensionId":272,"repoId":298},[306,287,307,289,310,288,308,309],{"evaluatedAt":317,"extractAt":302,"updatedAt":317},1778686677611,{"evaluate":319,"extract":321},{"promptVersionExtension":213,"promptVersionScoring":214,"score":217,"tags":320,"targetMarket":225,"tier":226},[220,221,222,223,224],{"commitSha":292,"license":248},{"parentExtensionId":261,"repoId":298},{"_creationTime":324,"_id":298,"identity":325,"providers":326,"workflow":1151},1778686632796.9226,{"githubOwner":255,"githubRepo":256,"sourceUrl":14},{"classify":327,"discover":1140,"extract":1143,"github":1144,"npm":1150},{"commitSha":292,"extensions":328},[329,338,526,545,553,570,608,616,634,644,670,678,690,706,720,734,754,774,791,799,817,831,859,877,915,927,937,947,955,975,990,1006,1018,1026,1034,1045,1053,1061,1075,1086,1098,1108,1117],{"basePath":330,"displayName":256,"installMethods":331,"rationale":332,"selectedPaths":333,"source":337,"sourceLanguage":18,"type":280},".agents/plugins",{"claudeCode":12},"marketplace.json at .agents/plugins/marketplace.json (coalesced with duplicate marketplace at /)",[334],{"path":335,"priority":336},"marketplace.json","mandatory","rule",{"basePath":268,"description":264,"displayName":266,"installMethods":339,"license":248,"rationale":340,"selectedPaths":341,"source":337,"sourceLanguage":18,"type":269},{"claudeCode":266},"plugin manifest at plugins/compound-engineering/.claude-plugin/plugin.json",[342,344,346,349,352,354,356,358,360,362,364,366,368,370,372,374,376,378,380,382,384,386,388,390,392,394,396,398,400,402,404,406,408,410,412,414,416,418,420,422,424,426,428,430,432,434,436,438,440,442,444,446,448,450,452,454,456,458,460,462,464,466,468,470,472,474,476,478,480,482,484,486,488,490,492,494,496,498,500,502,504,506,508,510,512,514,516,518,520,522,524],{"path":343,"priority":336},".claude-plugin/plugin.json",{"path":345,"priority":336},"README.md",{"path":347,"priority":348},"LICENSE","high",{"path":350,"priority":351},"skills/ce-agent-native-architecture/SKILL.md","medium",{"path":353,"priority":351},"skills/ce-agent-native-audit/SKILL.md",{"path":355,"priority":351},"skills/ce-brainstorm/SKILL.md",{"path":357,"priority":351},"skills/ce-clean-gone-branches/SKILL.md",{"path":359,"priority":351},"skills/ce-code-review/SKILL.md",{"path":361,"priority":351},"skills/ce-commit/SKILL.md",{"path":363,"priority":351},"skills/ce-commit-push-pr/SKILL.md",{"path":365,"priority":351},"skills/ce-compound/SKILL.md",{"path":367,"priority":351},"skills/ce-compound-refresh/SKILL.md",{"path":369,"priority":351},"skills/ce-debug/SKILL.md",{"path":371,"priority":351},"skills/ce-demo-reel/SKILL.md",{"path":373,"priority":351},"skills/ce-dhh-rails-style/SKILL.md",{"path":375,"priority":351},"skills/ce-doc-review/SKILL.md",{"path":377,"priority":351},"skills/ce-frontend-design/SKILL.md",{"path":379,"priority":351},"skills/ce-gemini-imagegen/SKILL.md",{"path":381,"priority":351},"skills/ce-ideate/SKILL.md",{"path":383,"priority":351},"skills/ce-optimize/SKILL.md",{"path":385,"priority":351},"skills/ce-plan/SKILL.md",{"path":387,"priority":351},"skills/ce-polish-beta/SKILL.md",{"path":389,"priority":351},"skills/ce-product-pulse/SKILL.md",{"path":391,"priority":351},"skills/ce-proof/SKILL.md",{"path":393,"priority":351},"skills/ce-release-notes/SKILL.md",{"path":395,"priority":351},"skills/ce-report-bug/SKILL.md",{"path":397,"priority":351},"skills/ce-resolve-pr-feedback/SKILL.md",{"path":399,"priority":351},"skills/ce-riffrec-feedback-analysis/SKILL.md",{"path":401,"priority":351},"skills/ce-sessions/SKILL.md",{"path":403,"priority":351},"skills/ce-setup/SKILL.md",{"path":405,"priority":351},"skills/ce-simplify-code/SKILL.md",{"path":407,"priority":351},"skills/ce-slack-research/SKILL.md",{"path":409,"priority":351},"skills/ce-strategy/SKILL.md",{"path":411,"priority":351},"skills/ce-test-browser/SKILL.md",{"path":413,"priority":351},"skills/ce-test-xcode/SKILL.md",{"path":415,"priority":351},"skills/ce-update/SKILL.md",{"path":417,"priority":351},"skills/ce-work/SKILL.md",{"path":419,"priority":351},"skills/ce-work-beta/SKILL.md",{"path":421,"priority":351},"skills/ce-worktree/SKILL.md",{"path":423,"priority":351},"skills/lfg/SKILL.md",{"path":425,"priority":348},"agents/ce-adversarial-document-reviewer.agent.md",{"path":427,"priority":348},"agents/ce-adversarial-reviewer.agent.md",{"path":429,"priority":348},"agents/ce-agent-native-reviewer.agent.md",{"path":431,"priority":348},"agents/ce-ankane-readme-writer.agent.md",{"path":433,"priority":348},"agents/ce-api-contract-reviewer.agent.md",{"path":435,"priority":348},"agents/ce-architecture-strategist.agent.md",{"path":437,"priority":348},"agents/ce-best-practices-researcher.agent.md",{"path":439,"priority":348},"agents/ce-code-simplicity-reviewer.agent.md",{"path":441,"priority":348},"agents/ce-coherence-reviewer.agent.md",{"path":443,"priority":348},"agents/ce-correctness-reviewer.agent.md",{"path":445,"priority":348},"agents/ce-data-integrity-guardian.agent.md",{"path":447,"priority":348},"agents/ce-data-migration-expert.agent.md",{"path":449,"priority":348},"agents/ce-data-migrations-reviewer.agent.md",{"path":451,"priority":348},"agents/ce-deployment-verification-agent.agent.md",{"path":453,"priority":348},"agents/ce-design-implementation-reviewer.agent.md",{"path":455,"priority":348},"agents/ce-design-iterator.agent.md",{"path":457,"priority":348},"agents/ce-design-lens-reviewer.agent.md",{"path":459,"priority":348},"agents/ce-dhh-rails-reviewer.agent.md",{"path":461,"priority":348},"agents/ce-feasibility-reviewer.agent.md",{"path":463,"priority":348},"agents/ce-figma-design-sync.agent.md",{"path":465,"priority":348},"agents/ce-framework-docs-researcher.agent.md",{"path":467,"priority":348},"agents/ce-git-history-analyzer.agent.md",{"path":469,"priority":348},"agents/ce-issue-intelligence-analyst.agent.md",{"path":471,"priority":348},"agents/ce-julik-frontend-races-reviewer.agent.md",{"path":473,"priority":348},"agents/ce-kieran-python-reviewer.agent.md",{"path":475,"priority":348},"agents/ce-kieran-rails-reviewer.agent.md",{"path":477,"priority":348},"agents/ce-kieran-typescript-reviewer.agent.md",{"path":479,"priority":348},"agents/ce-learnings-researcher.agent.md",{"path":481,"priority":348},"agents/ce-maintainability-reviewer.agent.md",{"path":483,"priority":348},"agents/ce-pattern-recognition-specialist.agent.md",{"path":485,"priority":348},"agents/ce-performance-oracle.agent.md",{"path":487,"priority":348},"agents/ce-performance-reviewer.agent.md",{"path":489,"priority":348},"agents/ce-pr-comment-resolver.agent.md",{"path":491,"priority":348},"agents/ce-previous-comments-reviewer.agent.md",{"path":493,"priority":348},"agents/ce-product-lens-reviewer.agent.md",{"path":495,"priority":348},"agents/ce-project-standards-reviewer.agent.md",{"path":497,"priority":348},"agents/ce-reliability-reviewer.agent.md",{"path":499,"priority":348},"agents/ce-repo-research-analyst.agent.md",{"path":501,"priority":348},"agents/ce-schema-drift-detector.agent.md",{"path":503,"priority":348},"agents/ce-scope-guardian-reviewer.agent.md",{"path":505,"priority":348},"agents/ce-security-lens-reviewer.agent.md",{"path":507,"priority":348},"agents/ce-security-reviewer.agent.md",{"path":509,"priority":348},"agents/ce-security-sentinel.agent.md",{"path":511,"priority":348},"agents/ce-session-historian.agent.md",{"path":513,"priority":348},"agents/ce-slack-researcher.agent.md",{"path":515,"priority":348},"agents/ce-spec-flow-analyzer.agent.md",{"path":517,"priority":348},"agents/ce-swift-ios-reviewer.agent.md",{"path":519,"priority":348},"agents/ce-testing-reviewer.agent.md",{"path":521,"priority":348},"agents/ce-web-researcher.agent.md",{"path":523,"priority":348},".codex-plugin/plugin.json",{"path":525,"priority":348},".cursor-plugin/plugin.json",{"basePath":527,"description":528,"displayName":529,"installMethods":530,"rationale":531,"selectedPaths":532,"source":337,"sourceLanguage":18,"type":269},"plugins/coding-tutor","Personalized coding tutorials that use your actual codebase for examples with spaced repetition quizzes","coding-tutor",{"claudeCode":529},"plugin manifest at plugins/coding-tutor/.claude-plugin/plugin.json",[533,534,535,537,539,541,543,544],{"path":343,"priority":336},{"path":345,"priority":336},{"path":536,"priority":351},"skills/coding-tutor/SKILL.md",{"path":538,"priority":348},"commands/quiz-me.md",{"path":540,"priority":348},"commands/sync-tutorials.md",{"path":542,"priority":348},"commands/teach-me.md",{"path":523,"priority":348},{"path":525,"priority":348},{"basePath":279,"description":275,"displayName":266,"installMethods":546,"rationale":547,"selectedPaths":548,"source":337,"sourceLanguage":18,"type":280},{"claudeCode":12},"marketplace.json at .cursor-plugin/marketplace.json",[549,551,552],{"path":550,"priority":336},".cursor-plugin/marketplace.json",{"path":345,"priority":336},{"path":347,"priority":348},{"basePath":554,"description":555,"displayName":529,"installMethods":556,"rationale":557,"selectedPaths":558,"source":337,"sourceLanguage":18,"type":258},"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",[559,561,564,566,568],{"path":560,"priority":336},"SKILL.md",{"path":562,"priority":563},"scripts/create_tutorial.py","low",{"path":565,"priority":563},"scripts/index_tutorials.py",{"path":567,"priority":563},"scripts/quiz_priority.py",{"path":569,"priority":563},"scripts/setup_tutorials.py",{"basePath":571,"description":572,"displayName":573,"installMethods":574,"rationale":575,"selectedPaths":576,"source":337,"sourceLanguage":18,"type":258},"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",[577,578,580,582,584,586,588,590,592,594,596,598,600,602,604,606],{"path":560,"priority":336},{"path":579,"priority":351},"references/action-parity-discipline.md",{"path":581,"priority":351},"references/agent-execution-patterns.md",{"path":583,"priority":351},"references/agent-native-testing.md",{"path":585,"priority":351},"references/architecture-patterns.md",{"path":587,"priority":351},"references/checklists.md",{"path":589,"priority":351},"references/dynamic-context-injection.md",{"path":591,"priority":351},"references/files-universal-interface.md",{"path":593,"priority":351},"references/from-primitives-to-domain-tools.md",{"path":595,"priority":351},"references/mcp-tool-design.md",{"path":597,"priority":351},"references/mobile-patterns.md",{"path":599,"priority":351},"references/product-implications.md",{"path":601,"priority":351},"references/refactoring-to-prompt-native.md",{"path":603,"priority":351},"references/self-modification.md",{"path":605,"priority":351},"references/shared-workspace-architecture.md",{"path":607,"priority":351},"references/system-prompt-design.md",{"basePath":609,"description":610,"displayName":611,"installMethods":612,"rationale":613,"selectedPaths":614,"source":337,"sourceLanguage":18,"type":258},"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",[615],{"path":560,"priority":336},{"basePath":617,"description":618,"displayName":619,"installMethods":620,"rationale":621,"selectedPaths":622,"source":337,"sourceLanguage":18,"type":258},"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",[623,624,626,628,630,632],{"path":560,"priority":336},{"path":625,"priority":351},"references/handoff.md",{"path":627,"priority":351},"references/requirements-capture.md",{"path":629,"priority":351},"references/synthesis-summary.md",{"path":631,"priority":351},"references/universal-brainstorming.md",{"path":633,"priority":351},"references/visual-communication.md",{"basePath":635,"description":636,"displayName":637,"installMethods":638,"rationale":639,"selectedPaths":640,"source":337,"sourceLanguage":18,"type":258},"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",[641,642],{"path":560,"priority":336},{"path":643,"priority":563},"scripts/clean-gone",{"basePath":645,"description":646,"displayName":647,"installMethods":648,"rationale":649,"selectedPaths":650,"source":337,"sourceLanguage":18,"type":258},"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",[651,652,654,656,658,660,662,664,666,668],{"path":560,"priority":336},{"path":653,"priority":351},"references/bulk-preview.md",{"path":655,"priority":351},"references/diff-scope.md",{"path":657,"priority":351},"references/findings-schema.json",{"path":659,"priority":351},"references/persona-catalog.md",{"path":661,"priority":351},"references/review-output-template.md",{"path":663,"priority":351},"references/subagent-template.md",{"path":665,"priority":351},"references/tracker-defer.md",{"path":667,"priority":351},"references/validator-template.md",{"path":669,"priority":351},"references/walkthrough.md",{"basePath":671,"description":672,"displayName":673,"installMethods":674,"rationale":675,"selectedPaths":676,"source":337,"sourceLanguage":18,"type":258},"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",[677],{"path":560,"priority":336},{"basePath":679,"description":680,"displayName":681,"installMethods":682,"rationale":683,"selectedPaths":684,"source":337,"sourceLanguage":18,"type":258},"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",[685,686,688],{"path":560,"priority":336},{"path":687,"priority":351},"references/branch-creation.md",{"path":689,"priority":351},"references/pr-description-writing.md",{"basePath":691,"description":692,"displayName":693,"installMethods":694,"rationale":695,"selectedPaths":696,"source":337,"sourceLanguage":18,"type":258},"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",[697,698,700,702,704],{"path":560,"priority":336},{"path":699,"priority":563},"assets/resolution-template.md",{"path":701,"priority":351},"references/schema.yaml",{"path":703,"priority":351},"references/yaml-schema.md",{"path":705,"priority":563},"scripts/validate-frontmatter.py",{"basePath":707,"description":708,"displayName":709,"installMethods":710,"rationale":711,"selectedPaths":712,"source":337,"sourceLanguage":18,"type":258},"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",[713,714,715,717,718,719],{"path":560,"priority":336},{"path":699,"priority":563},{"path":716,"priority":351},"references/per-action-flows.md",{"path":701,"priority":351},{"path":703,"priority":351},{"path":705,"priority":563},{"basePath":721,"description":722,"displayName":723,"installMethods":724,"rationale":725,"selectedPaths":726,"source":337,"sourceLanguage":18,"type":258},"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",[727,728,730,732],{"path":560,"priority":336},{"path":729,"priority":351},"references/anti-patterns.md",{"path":731,"priority":351},"references/defense-in-depth.md",{"path":733,"priority":351},"references/investigation-techniques.md",{"basePath":735,"description":736,"displayName":737,"installMethods":738,"rationale":739,"selectedPaths":740,"source":337,"sourceLanguage":18,"type":258},"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",[741,742,744,746,748,750,752],{"path":560,"priority":336},{"path":743,"priority":351},"references/tier-browser-reel.md",{"path":745,"priority":351},"references/tier-screenshot-reel.md",{"path":747,"priority":351},"references/tier-static-screenshots.md",{"path":749,"priority":351},"references/tier-terminal-recording.md",{"path":751,"priority":351},"references/upload-and-approval.md",{"path":753,"priority":563},"scripts/capture-demo.py",{"basePath":755,"description":756,"displayName":757,"installMethods":758,"rationale":759,"selectedPaths":760,"source":337,"sourceLanguage":18,"type":258},"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",[761,762,764,766,768,770,772],{"path":560,"priority":336},{"path":763,"priority":351},"references/architecture.md",{"path":765,"priority":351},"references/controllers.md",{"path":767,"priority":351},"references/frontend.md",{"path":769,"priority":351},"references/gems.md",{"path":771,"priority":351},"references/models.md",{"path":773,"priority":351},"references/testing.md",{"basePath":775,"description":776,"displayName":777,"installMethods":778,"rationale":779,"selectedPaths":780,"source":337,"sourceLanguage":18,"type":258},"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",[781,782,783,784,786,787,788,790],{"path":560,"priority":336},{"path":653,"priority":351},{"path":657,"priority":351},{"path":785,"priority":351},"references/open-questions-defer.md",{"path":661,"priority":351},{"path":663,"priority":351},{"path":789,"priority":351},"references/synthesis-and-presentation.md",{"path":669,"priority":351},{"basePath":792,"description":793,"displayName":794,"installMethods":795,"rationale":796,"selectedPaths":797,"source":337,"sourceLanguage":18,"type":258},"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",[798],{"path":560,"priority":336},{"basePath":800,"description":801,"displayName":802,"installMethods":803,"rationale":804,"selectedPaths":805,"source":337,"sourceLanguage":18,"type":258},"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",[806,807,809,811,813,815],{"path":560,"priority":336},{"path":808,"priority":563},"scripts/compose_images.py",{"path":810,"priority":563},"scripts/edit_image.py",{"path":812,"priority":563},"scripts/gemini_images.py",{"path":814,"priority":563},"scripts/generate_image.py",{"path":816,"priority":563},"scripts/multi_turn_chat.py",{"basePath":818,"description":819,"displayName":820,"installMethods":821,"rationale":822,"selectedPaths":823,"source":337,"sourceLanguage":18,"type":258},"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",[824,825,827,829],{"path":560,"priority":336},{"path":826,"priority":351},"references/post-ideation-workflow.md",{"path":828,"priority":351},"references/universal-ideation.md",{"path":830,"priority":351},"references/web-research-cache.md",{"basePath":832,"description":833,"displayName":834,"installMethods":835,"rationale":836,"selectedPaths":837,"source":337,"sourceLanguage":18,"type":258},"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",[838,839,841,843,845,847,849,851,853,855,857],{"path":560,"priority":336},{"path":840,"priority":351},"references/example-hard-spec.yaml",{"path":842,"priority":351},"references/example-judge-spec.yaml",{"path":844,"priority":351},"references/experiment-log-schema.yaml",{"path":846,"priority":351},"references/experiment-prompt-template.md",{"path":848,"priority":351},"references/judge-prompt-template.md",{"path":850,"priority":351},"references/optimize-spec-schema.yaml",{"path":852,"priority":351},"references/usage-guide.md",{"path":854,"priority":563},"scripts/experiment-worktree.sh",{"path":856,"priority":563},"scripts/measure.sh",{"path":858,"priority":563},"scripts/parallel-probe.sh",{"basePath":860,"description":861,"displayName":862,"installMethods":863,"rationale":864,"selectedPaths":865,"source":337,"sourceLanguage":18,"type":258},"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",[866,867,869,871,873,874,876],{"path":560,"priority":336},{"path":868,"priority":351},"references/deepening-workflow.md",{"path":870,"priority":351},"references/plan-handoff.md",{"path":872,"priority":351},"references/plan-template.md",{"path":629,"priority":351},{"path":875,"priority":351},"references/universal-planning.md",{"path":633,"priority":351},{"basePath":878,"description":879,"displayName":880,"installMethods":881,"rationale":882,"selectedPaths":883,"source":337,"sourceLanguage":18,"type":258},"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",[884,885,887,889,891,893,895,897,899,901,903,905,907,909,911,913],{"path":560,"priority":336},{"path":886,"priority":351},"references/dev-server-astro.md",{"path":888,"priority":351},"references/dev-server-detection.md",{"path":890,"priority":351},"references/dev-server-next.md",{"path":892,"priority":351},"references/dev-server-nuxt.md",{"path":894,"priority":351},"references/dev-server-procfile.md",{"path":896,"priority":351},"references/dev-server-rails.md",{"path":898,"priority":351},"references/dev-server-remix.md",{"path":900,"priority":351},"references/dev-server-sveltekit.md",{"path":902,"priority":351},"references/dev-server-vite.md",{"path":904,"priority":351},"references/ide-detection.md",{"path":906,"priority":351},"references/launch-json-schema.md",{"path":908,"priority":563},"scripts/detect-project-type.sh",{"path":910,"priority":563},"scripts/read-launch-json.sh",{"path":912,"priority":563},"scripts/resolve-package-manager.sh",{"path":914,"priority":563},"scripts/resolve-port.sh",{"basePath":916,"description":917,"displayName":918,"installMethods":919,"rationale":920,"selectedPaths":921,"source":337,"sourceLanguage":18,"type":258},"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",[922,923,925],{"path":560,"priority":336},{"path":924,"priority":351},"references/interview.md",{"path":926,"priority":351},"references/report-template.md",{"basePath":928,"description":929,"displayName":930,"installMethods":931,"rationale":932,"selectedPaths":933,"source":337,"sourceLanguage":18,"type":258},"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",[934,935],{"path":560,"priority":336},{"path":936,"priority":351},"references/hitl-review.md",{"basePath":938,"description":939,"displayName":940,"installMethods":941,"rationale":942,"selectedPaths":943,"source":337,"sourceLanguage":18,"type":258},"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",[944,945],{"path":560,"priority":336},{"path":946,"priority":563},"scripts/list-plugin-releases.py",{"basePath":948,"description":949,"displayName":950,"installMethods":951,"rationale":952,"selectedPaths":953,"source":337,"sourceLanguage":18,"type":258},"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",[954],{"path":560,"priority":336},{"basePath":956,"description":957,"displayName":958,"installMethods":959,"rationale":960,"selectedPaths":961,"source":337,"sourceLanguage":18,"type":258},"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",[962,963,965,967,969,971,973],{"path":560,"priority":336},{"path":964,"priority":351},"references/full-mode.md",{"path":966,"priority":351},"references/targeted-mode.md",{"path":968,"priority":563},"scripts/get-pr-comments",{"path":970,"priority":563},"scripts/get-thread-for-comment",{"path":972,"priority":563},"scripts/reply-to-pr-thread",{"path":974,"priority":563},"scripts/resolve-pr-thread",{"basePath":254,"description":10,"displayName":257,"installMethods":976,"rationale":977,"selectedPaths":978,"source":337,"sourceLanguage":18,"type":258},{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-riffrec-feedback-analysis/SKILL.md",[979,980,982,984,986,988],{"path":560,"priority":336},{"path":981,"priority":351},"references/compound-engineering-feedback-format.md",{"path":983,"priority":351},"references/extensive-analysis.md",{"path":985,"priority":351},"references/install-riffrec.md",{"path":987,"priority":351},"references/quick-bug-report.md",{"path":989,"priority":563},"scripts/analyze_riffrec_zip.py",{"basePath":991,"description":992,"displayName":993,"installMethods":994,"rationale":995,"selectedPaths":996,"source":337,"sourceLanguage":18,"type":258},"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",[997,998,1000,1002,1004],{"path":560,"priority":336},{"path":999,"priority":563},"scripts/discover-sessions.sh",{"path":1001,"priority":563},"scripts/extract-errors.py",{"path":1003,"priority":563},"scripts/extract-metadata.py",{"path":1005,"priority":563},"scripts/extract-skeleton.py",{"basePath":1007,"description":1008,"displayName":1009,"installMethods":1010,"rationale":1011,"selectedPaths":1012,"source":337,"sourceLanguage":18,"type":258},"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",[1013,1014,1016],{"path":560,"priority":336},{"path":1015,"priority":351},"references/config-template.yaml",{"path":1017,"priority":563},"scripts/check-health",{"basePath":1019,"description":1020,"displayName":1021,"installMethods":1022,"rationale":1023,"selectedPaths":1024,"source":337,"sourceLanguage":18,"type":258},"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",[1025],{"path":560,"priority":336},{"basePath":1027,"description":1028,"displayName":1029,"installMethods":1030,"rationale":1031,"selectedPaths":1032,"source":337,"sourceLanguage":18,"type":258},"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",[1033],{"path":560,"priority":336},{"basePath":1035,"description":1036,"displayName":1037,"installMethods":1038,"rationale":1039,"selectedPaths":1040,"source":337,"sourceLanguage":18,"type":258},"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",[1041,1042,1043],{"path":560,"priority":336},{"path":924,"priority":351},{"path":1044,"priority":351},"references/strategy-template.md",{"basePath":1046,"description":1047,"displayName":1048,"installMethods":1049,"rationale":1050,"selectedPaths":1051,"source":337,"sourceLanguage":18,"type":258},"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",[1052],{"path":560,"priority":336},{"basePath":1054,"description":1055,"displayName":1056,"installMethods":1057,"rationale":1058,"selectedPaths":1059,"source":337,"sourceLanguage":18,"type":258},"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",[1060],{"path":560,"priority":336},{"basePath":1062,"description":1063,"displayName":1064,"installMethods":1065,"rationale":1066,"selectedPaths":1067,"source":337,"sourceLanguage":18,"type":258},"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",[1068,1069,1071,1073],{"path":560,"priority":336},{"path":1070,"priority":563},"scripts/currently-loaded-version.sh",{"path":1072,"priority":563},"scripts/marketplace-name.sh",{"path":1074,"priority":563},"scripts/upstream-version.sh",{"basePath":1076,"description":1077,"displayName":1078,"installMethods":1079,"rationale":1080,"selectedPaths":1081,"source":337,"sourceLanguage":18,"type":258},"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",[1082,1083,1085],{"path":560,"priority":336},{"path":1084,"priority":351},"references/shipping-workflow.md",{"path":665,"priority":351},{"basePath":1087,"description":1088,"displayName":1089,"installMethods":1090,"rationale":1091,"selectedPaths":1092,"source":337,"sourceLanguage":18,"type":258},"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",[1093,1094,1096,1097],{"path":560,"priority":336},{"path":1095,"priority":351},"references/codex-delegation-workflow.md",{"path":1084,"priority":351},{"path":665,"priority":351},{"basePath":1099,"description":1100,"displayName":1101,"installMethods":1102,"rationale":1103,"selectedPaths":1104,"source":337,"sourceLanguage":18,"type":258},"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",[1105,1106],{"path":560,"priority":336},{"path":1107,"priority":563},"scripts/worktree-manager.sh",{"basePath":1109,"description":1110,"displayName":1111,"installMethods":1112,"rationale":1113,"selectedPaths":1114,"source":337,"sourceLanguage":18,"type":258},"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",[1115,1116],{"path":560,"priority":336},{"path":665,"priority":351},{"basePath":279,"description":1118,"displayName":1119,"installMethods":1120,"rationale":1121,"selectedPaths":1122,"source":337,"sourceLanguage":18,"type":1139},"Official Compound Engineering plugin for Claude Code, Codex, and more","@every-env/compound-plugin",{"npm":1119},"cli ecosystem detected at /",[1123,1125,1126,1127,1129,1131,1133,1135,1137],{"path":1124,"priority":336},"package.json",{"path":345,"priority":336},{"path":347,"priority":348},{"path":1128,"priority":351},"src/index.ts",{"path":1130,"priority":563},"src/commands/cleanup.ts",{"path":1132,"priority":563},"src/commands/convert.ts",{"path":1134,"priority":563},"src/commands/install.ts",{"path":1136,"priority":563},"src/commands/list.ts",{"path":1138,"priority":563},"src/commands/plugin-path.ts","cli",{"sources":1141},[1142],"manual",{"npmPackage":1119},{"closedIssues90d":240,"description":1145,"forks":241,"homepage":1146,"license":248,"openIssues90d":242,"pushedAt":243,"readmeSize":238,"stars":244,"topics":1147},"Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more","https://every.to/guides/compound-engineering",[1148,1149],"compound","engineering",{"downloads":246},{"classifiedAt":1152,"discoverAt":1153,"extractAt":1154,"githubAt":1154,"npmAt":1155,"updatedAt":1152},1778686639998,1778686632796,1778686635929,1778686638203,[220,221,223,222,224],{"evaluatedAt":252,"extractAt":302,"updatedAt":252},[],[1160,1191,1220,1247,1276,1306],{"_creationTime":1161,"_id":1162,"community":1163,"display":1164,"identity":1170,"providers":1175,"relations":1185,"tags":1187,"workflow":1188},1778696691708.3035,"k17br1j5s86ae90zqeyd7zcg2586mkwr",{"reviewCount":8},{"description":1165,"installMethods":1166,"name":1168,"sourceUrl":1169},"Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms\n",{"claudeCode":1167},"ruvnet/ruflo","Performance Analysis","https://github.com/ruvnet/ruflo",{"basePath":1171,"githubOwner":1172,"githubRepo":1173,"locale":18,"slug":1174,"type":258},".claude/skills/performance-analysis","ruvnet","ruflo","performance-analysis",{"evaluate":1176,"extract":1184},{"promptVersionExtension":213,"promptVersionScoring":214,"score":1177,"tags":1178,"targetMarket":225,"tier":226},100,[1179,1180,1181,1182,1183,223],"performance","analysis","optimization","claude-flow","bottleneck-detection",{"commitSha":292,"license":248},{"repoId":1186},"kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[1180,1183,1182,1181,1179,223],{"evaluatedAt":1189,"extractAt":1190,"updatedAt":1189},1778699217174,1778696691708,{"_creationTime":1192,"_id":1193,"community":1194,"display":1195,"identity":1201,"providers":1205,"relations":1213,"tags":1216,"workflow":1217},1778698144006.2202,"k172517ana4f5vj79mb22xzwsx86mksv",{"reviewCount":8},{"description":1196,"installMethods":1197,"name":1199,"sourceUrl":1200},"Audit and consolidate HubSpot reporting dashboards. Identifies unused, duplicate, or outdated dashboards. Must be performed manually — no dashboard API is available.",{"claudeCode":1198},"TomGranot/hubspot-admin-skills","cleanup-dashboards","https://github.com/TomGranot/hubspot-admin-skills",{"basePath":1202,"githubOwner":1203,"githubRepo":1204,"locale":18,"slug":1199,"type":258},"skills/cleanup-dashboards","TomGranot","hubspot-admin-skills",{"evaluate":1206,"extract":1212},{"promptVersionExtension":213,"promptVersionScoring":214,"score":1177,"tags":1207,"targetMarket":225,"tier":226},[1208,1209,1210,223,1211],"hubspot","crm","maintenance","cleanup",{"commitSha":292},{"parentExtensionId":1214,"repoId":1215},"k17c3p8t0thc73pbc8egtz31y986mwr0","kd75kpec7arn6z2wz641vfaj8n86nab6",[1211,1209,1208,1210,223],{"evaluatedAt":1218,"extractAt":1219,"updatedAt":1218},1778698268281,1778698144006,{"_creationTime":1221,"_id":1222,"community":1223,"display":1224,"identity":1230,"providers":1234,"relations":1240,"tags":1243,"workflow":1244},1778694480889.9524,"k17cem4hc58gq77dezte6rz8mx86nkpf",{"reviewCount":8},{"description":1225,"installMethods":1226,"name":1228,"sourceUrl":1229},"Display the current state of the FPF knowledge base",{"claudeCode":1227},"NeoLabHQ/context-engineering-kit","status","https://github.com/NeoLabHQ/context-engineering-kit",{"basePath":1231,"githubOwner":1232,"githubRepo":1233,"locale":18,"slug":1228,"type":258},"plugins/fpf/skills/status","NeoLabHQ","context-engineering-kit",{"evaluate":1235,"extract":1239},{"promptVersionExtension":213,"promptVersionScoring":214,"score":1177,"tags":1236,"targetMarket":225,"tier":226},[1237,1228,223,1238],"knowledge-base","fpf",{"commitSha":292},{"parentExtensionId":1241,"repoId":1242},"k170dd9j7raacsjs3ta67k8cw986m50s","kd7a3rj13ezgx1wgm0jfh08hsx86n0sz",[1238,1237,223,1228],{"evaluatedAt":1245,"extractAt":1246,"updatedAt":1245},1778695034738,1778694480890,{"_creationTime":1248,"_id":1249,"community":1250,"display":1251,"identity":1257,"providers":1261,"relations":1269,"tags":1272,"workflow":1273},1778692726926.7627,"k17dhmskz6t7wpxvd9ygy7fvsh86n695",{"reviewCount":8},{"description":1252,"installMethods":1253,"name":1255,"sourceUrl":1256},"End-of-quarter strategic review in narrative style with a bets scorecard. Use when someone says \"quarter review\", \"strategic review\", \"what happened last quarter\", \"quarterly retro\", \"bets scorecard\", \"review our bets\", \"end of quarter report\".\n",{"claudeCode":1254},"marfoerst/the-pragmatic-pm","pm-strategic-review","https://github.com/marfoerst/the-pragmatic-pm",{"basePath":1258,"githubOwner":1259,"githubRepo":1260,"locale":18,"slug":1255,"type":258},"skills/pm-strategic-review","marfoerst","the-pragmatic-pm",{"evaluate":1262,"extract":1268},{"promptVersionExtension":213,"promptVersionScoring":214,"score":1177,"tags":1263,"targetMarket":225,"tier":226},[1264,1265,223,1266,1267],"product-management","strategy","review","scorecard",{"commitSha":292},{"parentExtensionId":1270,"repoId":1271},"k17ehawghqbe3ff7rxmq9cq1xs86nm21","kd731k864fr1ezp8r85ecbhz9986mzz7",[1264,223,1266,1267,1265],{"evaluatedAt":1274,"extractAt":1275,"updatedAt":1274},1778693621016,1778692726926,{"_creationTime":1277,"_id":1278,"community":1279,"display":1280,"identity":1286,"providers":1290,"relations":1299,"tags":1302,"workflow":1303},1778692306427.1023,"k17f0vqhj9x3ee4773kq2m8fph86n5ct",{"reviewCount":8},{"description":1281,"installMethods":1282,"name":1284,"sourceUrl":1285},"Revenue and costs tracker. AWS spend via aws ce, credits tracker, project revenue stages. Shows burn rate, runway estimate, credits expiring.",{"claudeCode":1283},"Lifecycle-Innovations-Limited/claude-ops","ops-revenue","https://github.com/Lifecycle-Innovations-Limited/claude-ops",{"basePath":1287,"githubOwner":1288,"githubRepo":1289,"locale":18,"slug":1284,"type":258},"claude-ops/skills/ops-revenue","Lifecycle-Innovations-Limited","claude-ops",{"evaluate":1291,"extract":1298},{"promptVersionExtension":213,"promptVersionScoring":214,"score":1177,"tags":1292,"targetMarket":225,"tier":226},[1293,1294,1295,1296,223,1297],"finance","aws","cost-tracking","revenue","dashboard",{"commitSha":292},{"parentExtensionId":1300,"repoId":1301},"k17d0t6ns7y6t377pfprg128hd86nm89","kd7d52tcek2e34r805zs06b10d86n39v",[1294,1295,1297,1293,223,1296],{"evaluatedAt":1304,"extractAt":1305,"updatedAt":1304},1778692873720,1778692306427,{"_creationTime":1307,"_id":1308,"community":1309,"display":1310,"identity":1316,"providers":1321,"relations":1329,"tags":1332,"workflow":1333},1778692707070.0664,"k1745c75pw18shtjfgm186w7zn86mb7q",{"reviewCount":8},{"description":1311,"installMethods":1312,"name":1314,"sourceUrl":1315},"用于 README 优先的 AI 代码库进行可信执行和报告的技能。当任务是专门从选定的 smoke test 或已文档化的推理或评估命令捕获或标准化证据，并写入标准化的 `repro_outputs/` 文件（包括在存储库文件更改时生成补丁说明）时使用。请勿用于训练执行、初始代码库引入、通用环境设置、论文查找、目标选择或单独的端到端编排。",{"claudeCode":1313},"lllllllama/ai-paper-reproduction-skill","minimal-run-and-audit","https://github.com/lllllllama/ai-paper-reproduction-skill",{"basePath":1317,"githubOwner":1318,"githubRepo":1319,"locale":1320,"slug":1314,"type":258},"skills/minimal-run-and-audit","lllllllama","ai-paper-reproduction-skill","zh-CN",{"evaluate":1322,"extract":1328},{"promptVersionExtension":213,"promptVersionScoring":214,"score":1177,"tags":1323,"targetMarket":225,"tier":226},[1324,1325,223,1326,1327],"reproduction","testing","code-execution","evidence-capture",{"commitSha":292},{"repoId":1330,"translatedFrom":1331},"kd7629v5mqesxwwe9w7qtfgp7d86n6re","k1718b6r9230y7ft3t8gkmsg2986my9z",[1326,1327,223,1324,1325],{"evaluatedAt":1334,"extractAt":1335,"updatedAt":1336},1778692567369,1778692396032,1778692707070]