[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-EveryInc-ce-resolve-pr-feedback-de":3,"guides-for-EveryInc-ce-resolve-pr-feedback":1148,"similar-k1742kfbm6m0t2s5zf0c3wbpp986md7d-de":1149},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":245,"isFallback":226,"parentExtension":250,"providers":308,"relations":312,"repo":313,"tags":1146,"workflow":1147},1778686640222.7969,"k1742kfbm6m0t2s5zf0c3wbpp986md7d",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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.",{"claudeCode":12},"EveryInc/compound-engineering-plugin","ce-resolve-pr-feedback","https://github.com/EveryInc/compound-engineering-plugin",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":224,"workflow":243},1778687329770.445,"kn71m1tsmvwbx5j91yzeehnas986nj26","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"promptVersionExtension":205,"promptVersionScoring":206,"purpose":207,"rationale":208,"score":209,"summary":210,"tags":211,"targetMarket":217,"tier":218,"useCases":219},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,113,116,121,124,127,130,133,136,139,143,146,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of resolving PR review feedback and specifies when to use it: addressing PR comments, resolving threads, or fixing code review feedback.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers a significant value over default LLM behavior by specifically targeting PR feedback resolution, evaluating validity, fixing issues in parallel, and handling different feedback types with a structured workflow. It goes beyond a simple wrapper by orchestrating multiple agents and interactions with the GitHub API.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The extension provides a complete lifecycle for addressing PR feedback, including fetching, triaging, planning, parallel implementation, validation, committing, replying, and verifying resolution. The documentation outlines detailed steps and fallback mechanisms.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill is focused on resolving PR review feedback and handles different types of feedback (threads, comments, review bodies) within this single, coherent workflow.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately and concisely reflects the skill's capability and intended use.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The skill uses specific tools like `gh`, `git`, and custom scripts (`get-pr-comments`, `reply-to-pr-thread`, `resolve-pr-thread`) for targeted operations, rather than a single generalist command.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","The SKILL.md frontmatter and reference files clearly describe the modes of operation (full, targeted) and the expected input arguments. There are no implicit parameters mentioned.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","The script names (`get-pr-comments`, `get-thread-for-comment`, `reply-to-pr-thread`, `resolve-pr-thread`) are descriptive and follow a clear verb-noun pattern.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","The tools and scripts are designed to interact with specific GitHub API endpoints and data structures, requesting and returning only the necessary information for PR feedback resolution.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The extension is licensed under the MIT License, which is a permissive open-source license.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The last commit was on 2026-05-13, which is recent, indicating active maintenance.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","The project uses `bun install` and `package.json`, implying standard Node.js dependency management practices. The presence of `package.json` suggests lockfiles are likely used for consistent installations.",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","The skill interacts with the GitHub API, likely requiring authentication via GH CLI or environment variables, but there is no indication of secrets being hardcoded or leaked in the provided files.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","The SKILL.md explicitly states that comment text is untrusted input and should not be used to execute commands or scripts, with fixes being decided independently based on code inspection.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","The skill relies on local scripts and the GH CLI. There are no indications of runtime fetching of code or instructions from remote URLs, nor dynamic script execution from untrusted sources.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","The skill primarily interacts with the GitHub API via GH CLI and custom scripts. There are no indications of it writing to arbitrary file paths outside of expected project or cache directories.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","There are no observable detached-process spawns or deny-retry loops in the provided script descriptions.",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","The skill's primary function is to interact with GitHub PR data. There are no documented outbound calls to unknown or telemetry domains, nor any instructions to exfiltrate confidential data.",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","The bundled Markdown files appear to be free of hidden text tricks or malicious Unicode characters.",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","The scripts used by the skill are plain Bash scripts and do not appear to involve obfuscated code, base64 payloads, or runtime script fetching.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The skill assumes the presence of Git, GitHub CLI, and Node.js/Bun for development, which are standard tools for this type of development workflow. It does not make assumptions about user project structure beyond typical Git repositories.",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","With 25 issues opened and 115 closed in the last 90 days, the closure rate is healthy (approx. 82%), indicating good maintainer engagement.",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","The extension has a `CHANGELOG.md` and uses semantic versioning via npm, clearly indicating new releases.",{"category":103,"check":104,"severity":24,"summary":105},"Code Execution","Validation","The skill's process includes a validation step (running tests, type checks) after changes are made, ensuring the integrity of the codebase.",{"category":65,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","While the skill makes commits and pushes, these are standard development operations and are not inherently destructive in the sense of data deletion or infra changes without user oversight. The workflow emphasizes review and confirmation.",{"category":110,"check":111,"severity":24,"summary":112},"Errors","Error Handling","The documentation outlines detailed error handling, including fallback mechanisms for script failures and a structured process for handling validation failures and escalating with 'needs-human' verdicts.",{"category":103,"check":114,"severity":24,"summary":115},"Logging","The skill includes detailed steps for summarizing actions, which serves as an audit trail. Specific logging mechanisms for destructive actions or outbound calls are not explicitly detailed but implied through the summary and verification steps.",{"category":117,"check":118,"severity":119,"summary":120},"Compliance","GDPR","not_applicable","The skill operates on GitHub PR data and code, not personal data that would trigger GDPR concerns.",{"category":117,"check":122,"severity":24,"summary":123},"Target market","The skill interacts with GitHub and standard development tools, making it globally applicable. There are no regional or jurisdictional restrictions identified.",{"category":91,"check":125,"severity":24,"summary":126},"Runtime stability","The skill relies on standard tools like Git, GH CLI, and Bash/Bun, which are widely available on POSIX-like systems. No specific OS or shell assumptions are evident.",{"category":44,"check":128,"severity":24,"summary":129},"README","The README file exists, is comprehensive, and clearly states the project's philosophy, workflow, and provides installation and usage instructions.",{"category":33,"check":131,"severity":24,"summary":132},"Tool surface size","The skill primarily utilizes GH CLI and custom scripts for its core functionality, keeping the direct tool surface small and focused.",{"category":40,"check":134,"severity":24,"summary":135},"Overlapping near-synonym tools","The skill's core operations are handled by distinct scripts and GH CLI commands, avoiding redundant or overlapping functionality.",{"category":44,"check":137,"severity":24,"summary":138},"Phantom features","All advertised features, such as resolving PR feedback and handling different modes, have corresponding implementations described in the SKILL.md and reference files.",{"category":140,"check":141,"severity":24,"summary":142},"Install","Installation instruction","The README provides detailed installation instructions for multiple platforms (Claude Code, Cursor, Codex, Copilot, etc.) including copy-pasteable commands and setup steps.",{"category":110,"check":144,"severity":24,"summary":145},"Actionable error messages","The documentation details comprehensive error handling, including specific instructions for reporting failures, escalating 'needs-human' verdicts, and providing context for user decisions.",{"category":147,"check":148,"severity":24,"summary":149},"Execution","Pinned dependencies","The project uses `bun install`, which typically relies on lockfiles (`bun.lockb`) for pinned dependencies, ensuring reproducible builds.",{"category":33,"check":151,"severity":119,"summary":152},"Dry-run preview","The skill's core operations involve interacting with GitHub's API to resolve PR feedback. While commits are made, the process is review-centric, and direct destructive operations that would typically require a dry-run are not the primary focus.",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","The skill's workflow, particularly the error handling and retry logic described for validation and agent dispatches, suggests an awareness of potential issues that could benefit from idempotent operations and timeouts, although not explicitly detailed for every GH API call.",{"category":117,"check":158,"severity":24,"summary":159},"Telemetry opt-in","There is no mention of telemetry collection in the provided files. If telemetry is used, it's likely opt-in or not present, aligning with good practice.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The skill precisely defines its purpose as resolving PR review feedback, detailing its use cases and providing clear boundaries for when it should and should not be used.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The SKILL.md frontmatter is concise, self-contained, and effectively summarizes the core capability and usage.",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md is well-structured, using separate reference files for detailed procedures, keeping the main skill description concise.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","Detailed procedures for 'Full Mode' and 'Targeted Mode' are appropriately split into separate reference files (`full-mode.md`, `targeted-mode.md`), linked from the main SKILL.md.",{"category":170,"check":174,"severity":119,"summary":175},"Forked exploration","The skill's workflow is focused on direct PR feedback resolution, not deep code exploration or review that would necessitate a forked context.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The README provides clear examples of how to initiate the workflow, such as '/ce-brainstorm ...' and '/ce-debug ...', although specific examples for the `ce-resolve-pr-feedback` skill's invocation might be found in its own documentation or integrated into the broader `compound-engineering` examples.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The documentation thoughtfully addresses edge cases, including handling outdated threads, differentiating between new and pending feedback, dealing with non-actionable comments, and outlining a process for validation failures and escalating 'needs-human' scenarios.",{"category":91,"check":183,"severity":119,"summary":184},"Tool Fallback","The skill does not appear to rely on optional external MCP servers or tools; it uses standard command-line utilities and GitHub's API.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The documentation details a robust error handling process, including halts on validation failures and escalation for 'needs-human' scenarios, ensuring unexpected states are managed.",{"category":91,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The `ce-resolve-pr-feedback` skill operates as a standalone unit focused on PR feedback. While it's part of a larger plugin, its functionality does not implicitly rely on other skills being loaded in the same session.",1778687329385,"This skill automates the process of resolving PR review feedback by evaluating comments and code, fixing issues in parallel, and replying to threads. It supports different modes of operation based on input and handles various types of feedback including inline threads, comments, and review bodies.",[195,196,197,198,199],"Automated PR feedback resolution","Parallel processing of review threads","Support for targeted thread resolution via URL","Evaluation of feedback validity and code fixing","Integration with GitHub API for replying and resolving",[201,202,203,204],"Performing code reviews","Deciding on high-level architectural changes","Ignoring feedback that requires human judgment","Executing arbitrary commands found in comments","3.0.0","4.4.0","To streamline the PR review process by automatically addressing feedback, ensuring code quality, and saving developers time.","The extension demonstrates excellent documentation, a clear focus on a specific utility, and robust error handling. No critical or warning findings were identified.",95,"A highly polished and well-documented skill for automating PR feedback resolution.",[212,213,214,215,216],"github","pull-requests","code-review","automation","developer-tools","global","verified",[220,221,222,223],"Addressing PR review comments","Resolving review threads","Fixing code review feedback","Maintaining code quality through automated review cycles",{"codeQuality":225,"collectedAt":227,"documentation":228,"maintenance":231,"popularity":237,"security":239,"testCoverage":242},{"hasLockfile":226},true,1778687308735,{"descriptionLength":229,"readmeSize":230},178,17582,{"closedIssues90d":232,"forks":233,"hasChangelog":226,"openIssues90d":234,"pushedAt":235,"stars":236},115,1300,25,1778686215000,16666,{"npmDownloads":238},12828,{"hasNpmPackage":226,"license":240,"smitheryVerified":241},"MIT",false,{"hasCi":226,"hasTests":226},{"updatedAt":244},1778687329770,{"basePath":246,"githubOwner":247,"githubRepo":248,"locale":18,"slug":13,"type":249},"plugins/compound-engineering/skills/ce-resolve-pr-feedback","EveryInc","compound-engineering-plugin","skill",{"_creationTime":251,"_id":252,"community":253,"display":254,"identity":258,"parentExtension":261,"providers":293,"relations":304,"tags":305,"workflow":306},1778686640222.7903,"k17d893df4em0e3pn8f55h1dxn86n09e",{"reviewCount":8},{"description":255,"installMethods":256,"name":257,"sourceUrl":14},"AI-powered development tools for code review, research, design, and workflow automation.",{"claudeCode":257},"compound-engineering",{"basePath":259,"githubOwner":247,"githubRepo":248,"locale":18,"slug":257,"type":260},"plugins/compound-engineering","plugin",{"_creationTime":262,"_id":263,"community":264,"display":265,"identity":269,"providers":272,"relations":287,"tags":289,"workflow":290},1778686640222.7908,"k17ef8php9wk308mkg59kdp6b186nzhx",{"reviewCount":8},{"description":266,"installMethods":267,"name":268,"sourceUrl":14},"Cursor plugin marketplace for Every Inc plugins",{"claudeCode":12},"Compound Engineering",{"basePath":270,"githubOwner":247,"githubRepo":248,"locale":18,"slug":248,"type":271},"","marketplace",{"evaluate":273,"extract":281},{"promptVersionExtension":274,"promptVersionScoring":206,"score":275,"tags":276,"targetMarket":217,"tier":218},"3.1.0",99,[277,214,278,279,280],"development-workflow","planning","documentation","ai-agents",{"commitSha":282,"license":240,"marketplace":283,"plugin":285},"HEAD",{"name":248,"pluginCount":284},2,{"mcpCount":8,"provider":286,"skillCount":8},"classify",{"repoId":288},"kd7e40my1b5g70tg0f60qg85ch86nn08",[280,214,277,279,278],{"evaluatedAt":291,"extractAt":292,"updatedAt":291},1778686722515,1778686640222,{"evaluate":294,"extract":301},{"promptVersionExtension":205,"promptVersionScoring":206,"score":295,"tags":296,"targetMarket":217,"tier":218},98,[297,216,214,298,279,299,278,300],"ai","research","workflow-automation","ideation",{"commitSha":282,"license":240,"plugin":302},{"mcpCount":8,"provider":286,"skillCount":303},37,{"parentExtensionId":263,"repoId":288},[297,214,216,279,300,278,298,299],{"evaluatedAt":307,"extractAt":292,"updatedAt":307},1778686677611,{"evaluate":309,"extract":311},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":310,"targetMarket":217,"tier":218},[212,213,214,215,216],{"commitSha":282},{"parentExtensionId":252,"repoId":288},{"_creationTime":314,"_id":288,"identity":315,"providers":316,"workflow":1141},1778686632796.9226,{"githubOwner":247,"githubRepo":248,"sourceUrl":14},{"classify":317,"discover":1130,"extract":1133,"github":1134,"npm":1140},{"commitSha":282,"extensions":318},[319,328,516,535,543,560,598,606,624,634,660,668,680,696,710,724,744,764,781,789,807,821,849,867,905,917,927,937,945,962,980,996,1008,1016,1024,1035,1043,1051,1065,1076,1088,1098,1107],{"basePath":320,"displayName":248,"installMethods":321,"rationale":322,"selectedPaths":323,"source":327,"sourceLanguage":18,"type":271},".agents/plugins",{"claudeCode":12},"marketplace.json at .agents/plugins/marketplace.json (coalesced with duplicate marketplace at /)",[324],{"path":325,"priority":326},"marketplace.json","mandatory","rule",{"basePath":259,"description":255,"displayName":257,"installMethods":329,"license":240,"rationale":330,"selectedPaths":331,"source":327,"sourceLanguage":18,"type":260},{"claudeCode":257},"plugin manifest at plugins/compound-engineering/.claude-plugin/plugin.json",[332,334,336,339,342,344,346,348,350,352,354,356,358,360,362,364,366,368,370,372,374,376,378,380,382,384,386,388,390,392,394,396,398,400,402,404,406,408,410,412,414,416,418,420,422,424,426,428,430,432,434,436,438,440,442,444,446,448,450,452,454,456,458,460,462,464,466,468,470,472,474,476,478,480,482,484,486,488,490,492,494,496,498,500,502,504,506,508,510,512,514],{"path":333,"priority":326},".claude-plugin/plugin.json",{"path":335,"priority":326},"README.md",{"path":337,"priority":338},"LICENSE","high",{"path":340,"priority":341},"skills/ce-agent-native-architecture/SKILL.md","medium",{"path":343,"priority":341},"skills/ce-agent-native-audit/SKILL.md",{"path":345,"priority":341},"skills/ce-brainstorm/SKILL.md",{"path":347,"priority":341},"skills/ce-clean-gone-branches/SKILL.md",{"path":349,"priority":341},"skills/ce-code-review/SKILL.md",{"path":351,"priority":341},"skills/ce-commit/SKILL.md",{"path":353,"priority":341},"skills/ce-commit-push-pr/SKILL.md",{"path":355,"priority":341},"skills/ce-compound/SKILL.md",{"path":357,"priority":341},"skills/ce-compound-refresh/SKILL.md",{"path":359,"priority":341},"skills/ce-debug/SKILL.md",{"path":361,"priority":341},"skills/ce-demo-reel/SKILL.md",{"path":363,"priority":341},"skills/ce-dhh-rails-style/SKILL.md",{"path":365,"priority":341},"skills/ce-doc-review/SKILL.md",{"path":367,"priority":341},"skills/ce-frontend-design/SKILL.md",{"path":369,"priority":341},"skills/ce-gemini-imagegen/SKILL.md",{"path":371,"priority":341},"skills/ce-ideate/SKILL.md",{"path":373,"priority":341},"skills/ce-optimize/SKILL.md",{"path":375,"priority":341},"skills/ce-plan/SKILL.md",{"path":377,"priority":341},"skills/ce-polish-beta/SKILL.md",{"path":379,"priority":341},"skills/ce-product-pulse/SKILL.md",{"path":381,"priority":341},"skills/ce-proof/SKILL.md",{"path":383,"priority":341},"skills/ce-release-notes/SKILL.md",{"path":385,"priority":341},"skills/ce-report-bug/SKILL.md",{"path":387,"priority":341},"skills/ce-resolve-pr-feedback/SKILL.md",{"path":389,"priority":341},"skills/ce-riffrec-feedback-analysis/SKILL.md",{"path":391,"priority":341},"skills/ce-sessions/SKILL.md",{"path":393,"priority":341},"skills/ce-setup/SKILL.md",{"path":395,"priority":341},"skills/ce-simplify-code/SKILL.md",{"path":397,"priority":341},"skills/ce-slack-research/SKILL.md",{"path":399,"priority":341},"skills/ce-strategy/SKILL.md",{"path":401,"priority":341},"skills/ce-test-browser/SKILL.md",{"path":403,"priority":341},"skills/ce-test-xcode/SKILL.md",{"path":405,"priority":341},"skills/ce-update/SKILL.md",{"path":407,"priority":341},"skills/ce-work/SKILL.md",{"path":409,"priority":341},"skills/ce-work-beta/SKILL.md",{"path":411,"priority":341},"skills/ce-worktree/SKILL.md",{"path":413,"priority":341},"skills/lfg/SKILL.md",{"path":415,"priority":338},"agents/ce-adversarial-document-reviewer.agent.md",{"path":417,"priority":338},"agents/ce-adversarial-reviewer.agent.md",{"path":419,"priority":338},"agents/ce-agent-native-reviewer.agent.md",{"path":421,"priority":338},"agents/ce-ankane-readme-writer.agent.md",{"path":423,"priority":338},"agents/ce-api-contract-reviewer.agent.md",{"path":425,"priority":338},"agents/ce-architecture-strategist.agent.md",{"path":427,"priority":338},"agents/ce-best-practices-researcher.agent.md",{"path":429,"priority":338},"agents/ce-code-simplicity-reviewer.agent.md",{"path":431,"priority":338},"agents/ce-coherence-reviewer.agent.md",{"path":433,"priority":338},"agents/ce-correctness-reviewer.agent.md",{"path":435,"priority":338},"agents/ce-data-integrity-guardian.agent.md",{"path":437,"priority":338},"agents/ce-data-migration-expert.agent.md",{"path":439,"priority":338},"agents/ce-data-migrations-reviewer.agent.md",{"path":441,"priority":338},"agents/ce-deployment-verification-agent.agent.md",{"path":443,"priority":338},"agents/ce-design-implementation-reviewer.agent.md",{"path":445,"priority":338},"agents/ce-design-iterator.agent.md",{"path":447,"priority":338},"agents/ce-design-lens-reviewer.agent.md",{"path":449,"priority":338},"agents/ce-dhh-rails-reviewer.agent.md",{"path":451,"priority":338},"agents/ce-feasibility-reviewer.agent.md",{"path":453,"priority":338},"agents/ce-figma-design-sync.agent.md",{"path":455,"priority":338},"agents/ce-framework-docs-researcher.agent.md",{"path":457,"priority":338},"agents/ce-git-history-analyzer.agent.md",{"path":459,"priority":338},"agents/ce-issue-intelligence-analyst.agent.md",{"path":461,"priority":338},"agents/ce-julik-frontend-races-reviewer.agent.md",{"path":463,"priority":338},"agents/ce-kieran-python-reviewer.agent.md",{"path":465,"priority":338},"agents/ce-kieran-rails-reviewer.agent.md",{"path":467,"priority":338},"agents/ce-kieran-typescript-reviewer.agent.md",{"path":469,"priority":338},"agents/ce-learnings-researcher.agent.md",{"path":471,"priority":338},"agents/ce-maintainability-reviewer.agent.md",{"path":473,"priority":338},"agents/ce-pattern-recognition-specialist.agent.md",{"path":475,"priority":338},"agents/ce-performance-oracle.agent.md",{"path":477,"priority":338},"agents/ce-performance-reviewer.agent.md",{"path":479,"priority":338},"agents/ce-pr-comment-resolver.agent.md",{"path":481,"priority":338},"agents/ce-previous-comments-reviewer.agent.md",{"path":483,"priority":338},"agents/ce-product-lens-reviewer.agent.md",{"path":485,"priority":338},"agents/ce-project-standards-reviewer.agent.md",{"path":487,"priority":338},"agents/ce-reliability-reviewer.agent.md",{"path":489,"priority":338},"agents/ce-repo-research-analyst.agent.md",{"path":491,"priority":338},"agents/ce-schema-drift-detector.agent.md",{"path":493,"priority":338},"agents/ce-scope-guardian-reviewer.agent.md",{"path":495,"priority":338},"agents/ce-security-lens-reviewer.agent.md",{"path":497,"priority":338},"agents/ce-security-reviewer.agent.md",{"path":499,"priority":338},"agents/ce-security-sentinel.agent.md",{"path":501,"priority":338},"agents/ce-session-historian.agent.md",{"path":503,"priority":338},"agents/ce-slack-researcher.agent.md",{"path":505,"priority":338},"agents/ce-spec-flow-analyzer.agent.md",{"path":507,"priority":338},"agents/ce-swift-ios-reviewer.agent.md",{"path":509,"priority":338},"agents/ce-testing-reviewer.agent.md",{"path":511,"priority":338},"agents/ce-web-researcher.agent.md",{"path":513,"priority":338},".codex-plugin/plugin.json",{"path":515,"priority":338},".cursor-plugin/plugin.json",{"basePath":517,"description":518,"displayName":519,"installMethods":520,"rationale":521,"selectedPaths":522,"source":327,"sourceLanguage":18,"type":260},"plugins/coding-tutor","Personalized coding tutorials that use your actual codebase for examples with spaced repetition quizzes","coding-tutor",{"claudeCode":519},"plugin manifest at plugins/coding-tutor/.claude-plugin/plugin.json",[523,524,525,527,529,531,533,534],{"path":333,"priority":326},{"path":335,"priority":326},{"path":526,"priority":341},"skills/coding-tutor/SKILL.md",{"path":528,"priority":338},"commands/quiz-me.md",{"path":530,"priority":338},"commands/sync-tutorials.md",{"path":532,"priority":338},"commands/teach-me.md",{"path":513,"priority":338},{"path":515,"priority":338},{"basePath":270,"description":266,"displayName":257,"installMethods":536,"rationale":537,"selectedPaths":538,"source":327,"sourceLanguage":18,"type":271},{"claudeCode":12},"marketplace.json at .cursor-plugin/marketplace.json",[539,541,542],{"path":540,"priority":326},".cursor-plugin/marketplace.json",{"path":335,"priority":326},{"path":337,"priority":338},{"basePath":544,"description":545,"displayName":519,"installMethods":546,"rationale":547,"selectedPaths":548,"source":327,"sourceLanguage":18,"type":249},"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",[549,551,554,556,558],{"path":550,"priority":326},"SKILL.md",{"path":552,"priority":553},"scripts/create_tutorial.py","low",{"path":555,"priority":553},"scripts/index_tutorials.py",{"path":557,"priority":553},"scripts/quiz_priority.py",{"path":559,"priority":553},"scripts/setup_tutorials.py",{"basePath":561,"description":562,"displayName":563,"installMethods":564,"rationale":565,"selectedPaths":566,"source":327,"sourceLanguage":18,"type":249},"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",[567,568,570,572,574,576,578,580,582,584,586,588,590,592,594,596],{"path":550,"priority":326},{"path":569,"priority":341},"references/action-parity-discipline.md",{"path":571,"priority":341},"references/agent-execution-patterns.md",{"path":573,"priority":341},"references/agent-native-testing.md",{"path":575,"priority":341},"references/architecture-patterns.md",{"path":577,"priority":341},"references/checklists.md",{"path":579,"priority":341},"references/dynamic-context-injection.md",{"path":581,"priority":341},"references/files-universal-interface.md",{"path":583,"priority":341},"references/from-primitives-to-domain-tools.md",{"path":585,"priority":341},"references/mcp-tool-design.md",{"path":587,"priority":341},"references/mobile-patterns.md",{"path":589,"priority":341},"references/product-implications.md",{"path":591,"priority":341},"references/refactoring-to-prompt-native.md",{"path":593,"priority":341},"references/self-modification.md",{"path":595,"priority":341},"references/shared-workspace-architecture.md",{"path":597,"priority":341},"references/system-prompt-design.md",{"basePath":599,"description":600,"displayName":601,"installMethods":602,"rationale":603,"selectedPaths":604,"source":327,"sourceLanguage":18,"type":249},"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",[605],{"path":550,"priority":326},{"basePath":607,"description":608,"displayName":609,"installMethods":610,"rationale":611,"selectedPaths":612,"source":327,"sourceLanguage":18,"type":249},"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",[613,614,616,618,620,622],{"path":550,"priority":326},{"path":615,"priority":341},"references/handoff.md",{"path":617,"priority":341},"references/requirements-capture.md",{"path":619,"priority":341},"references/synthesis-summary.md",{"path":621,"priority":341},"references/universal-brainstorming.md",{"path":623,"priority":341},"references/visual-communication.md",{"basePath":625,"description":626,"displayName":627,"installMethods":628,"rationale":629,"selectedPaths":630,"source":327,"sourceLanguage":18,"type":249},"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",[631,632],{"path":550,"priority":326},{"path":633,"priority":553},"scripts/clean-gone",{"basePath":635,"description":636,"displayName":637,"installMethods":638,"rationale":639,"selectedPaths":640,"source":327,"sourceLanguage":18,"type":249},"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",[641,642,644,646,648,650,652,654,656,658],{"path":550,"priority":326},{"path":643,"priority":341},"references/bulk-preview.md",{"path":645,"priority":341},"references/diff-scope.md",{"path":647,"priority":341},"references/findings-schema.json",{"path":649,"priority":341},"references/persona-catalog.md",{"path":651,"priority":341},"references/review-output-template.md",{"path":653,"priority":341},"references/subagent-template.md",{"path":655,"priority":341},"references/tracker-defer.md",{"path":657,"priority":341},"references/validator-template.md",{"path":659,"priority":341},"references/walkthrough.md",{"basePath":661,"description":662,"displayName":663,"installMethods":664,"rationale":665,"selectedPaths":666,"source":327,"sourceLanguage":18,"type":249},"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",[667],{"path":550,"priority":326},{"basePath":669,"description":670,"displayName":671,"installMethods":672,"rationale":673,"selectedPaths":674,"source":327,"sourceLanguage":18,"type":249},"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",[675,676,678],{"path":550,"priority":326},{"path":677,"priority":341},"references/branch-creation.md",{"path":679,"priority":341},"references/pr-description-writing.md",{"basePath":681,"description":682,"displayName":683,"installMethods":684,"rationale":685,"selectedPaths":686,"source":327,"sourceLanguage":18,"type":249},"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",[687,688,690,692,694],{"path":550,"priority":326},{"path":689,"priority":553},"assets/resolution-template.md",{"path":691,"priority":341},"references/schema.yaml",{"path":693,"priority":341},"references/yaml-schema.md",{"path":695,"priority":553},"scripts/validate-frontmatter.py",{"basePath":697,"description":698,"displayName":699,"installMethods":700,"rationale":701,"selectedPaths":702,"source":327,"sourceLanguage":18,"type":249},"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",[703,704,705,707,708,709],{"path":550,"priority":326},{"path":689,"priority":553},{"path":706,"priority":341},"references/per-action-flows.md",{"path":691,"priority":341},{"path":693,"priority":341},{"path":695,"priority":553},{"basePath":711,"description":712,"displayName":713,"installMethods":714,"rationale":715,"selectedPaths":716,"source":327,"sourceLanguage":18,"type":249},"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",[717,718,720,722],{"path":550,"priority":326},{"path":719,"priority":341},"references/anti-patterns.md",{"path":721,"priority":341},"references/defense-in-depth.md",{"path":723,"priority":341},"references/investigation-techniques.md",{"basePath":725,"description":726,"displayName":727,"installMethods":728,"rationale":729,"selectedPaths":730,"source":327,"sourceLanguage":18,"type":249},"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",[731,732,734,736,738,740,742],{"path":550,"priority":326},{"path":733,"priority":341},"references/tier-browser-reel.md",{"path":735,"priority":341},"references/tier-screenshot-reel.md",{"path":737,"priority":341},"references/tier-static-screenshots.md",{"path":739,"priority":341},"references/tier-terminal-recording.md",{"path":741,"priority":341},"references/upload-and-approval.md",{"path":743,"priority":553},"scripts/capture-demo.py",{"basePath":745,"description":746,"displayName":747,"installMethods":748,"rationale":749,"selectedPaths":750,"source":327,"sourceLanguage":18,"type":249},"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",[751,752,754,756,758,760,762],{"path":550,"priority":326},{"path":753,"priority":341},"references/architecture.md",{"path":755,"priority":341},"references/controllers.md",{"path":757,"priority":341},"references/frontend.md",{"path":759,"priority":341},"references/gems.md",{"path":761,"priority":341},"references/models.md",{"path":763,"priority":341},"references/testing.md",{"basePath":765,"description":766,"displayName":767,"installMethods":768,"rationale":769,"selectedPaths":770,"source":327,"sourceLanguage":18,"type":249},"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",[771,772,773,774,776,777,778,780],{"path":550,"priority":326},{"path":643,"priority":341},{"path":647,"priority":341},{"path":775,"priority":341},"references/open-questions-defer.md",{"path":651,"priority":341},{"path":653,"priority":341},{"path":779,"priority":341},"references/synthesis-and-presentation.md",{"path":659,"priority":341},{"basePath":782,"description":783,"displayName":784,"installMethods":785,"rationale":786,"selectedPaths":787,"source":327,"sourceLanguage":18,"type":249},"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",[788],{"path":550,"priority":326},{"basePath":790,"description":791,"displayName":792,"installMethods":793,"rationale":794,"selectedPaths":795,"source":327,"sourceLanguage":18,"type":249},"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",[796,797,799,801,803,805],{"path":550,"priority":326},{"path":798,"priority":553},"scripts/compose_images.py",{"path":800,"priority":553},"scripts/edit_image.py",{"path":802,"priority":553},"scripts/gemini_images.py",{"path":804,"priority":553},"scripts/generate_image.py",{"path":806,"priority":553},"scripts/multi_turn_chat.py",{"basePath":808,"description":809,"displayName":810,"installMethods":811,"rationale":812,"selectedPaths":813,"source":327,"sourceLanguage":18,"type":249},"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",[814,815,817,819],{"path":550,"priority":326},{"path":816,"priority":341},"references/post-ideation-workflow.md",{"path":818,"priority":341},"references/universal-ideation.md",{"path":820,"priority":341},"references/web-research-cache.md",{"basePath":822,"description":823,"displayName":824,"installMethods":825,"rationale":826,"selectedPaths":827,"source":327,"sourceLanguage":18,"type":249},"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",[828,829,831,833,835,837,839,841,843,845,847],{"path":550,"priority":326},{"path":830,"priority":341},"references/example-hard-spec.yaml",{"path":832,"priority":341},"references/example-judge-spec.yaml",{"path":834,"priority":341},"references/experiment-log-schema.yaml",{"path":836,"priority":341},"references/experiment-prompt-template.md",{"path":838,"priority":341},"references/judge-prompt-template.md",{"path":840,"priority":341},"references/optimize-spec-schema.yaml",{"path":842,"priority":341},"references/usage-guide.md",{"path":844,"priority":553},"scripts/experiment-worktree.sh",{"path":846,"priority":553},"scripts/measure.sh",{"path":848,"priority":553},"scripts/parallel-probe.sh",{"basePath":850,"description":851,"displayName":852,"installMethods":853,"rationale":854,"selectedPaths":855,"source":327,"sourceLanguage":18,"type":249},"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",[856,857,859,861,863,864,866],{"path":550,"priority":326},{"path":858,"priority":341},"references/deepening-workflow.md",{"path":860,"priority":341},"references/plan-handoff.md",{"path":862,"priority":341},"references/plan-template.md",{"path":619,"priority":341},{"path":865,"priority":341},"references/universal-planning.md",{"path":623,"priority":341},{"basePath":868,"description":869,"displayName":870,"installMethods":871,"rationale":872,"selectedPaths":873,"source":327,"sourceLanguage":18,"type":249},"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",[874,875,877,879,881,883,885,887,889,891,893,895,897,899,901,903],{"path":550,"priority":326},{"path":876,"priority":341},"references/dev-server-astro.md",{"path":878,"priority":341},"references/dev-server-detection.md",{"path":880,"priority":341},"references/dev-server-next.md",{"path":882,"priority":341},"references/dev-server-nuxt.md",{"path":884,"priority":341},"references/dev-server-procfile.md",{"path":886,"priority":341},"references/dev-server-rails.md",{"path":888,"priority":341},"references/dev-server-remix.md",{"path":890,"priority":341},"references/dev-server-sveltekit.md",{"path":892,"priority":341},"references/dev-server-vite.md",{"path":894,"priority":341},"references/ide-detection.md",{"path":896,"priority":341},"references/launch-json-schema.md",{"path":898,"priority":553},"scripts/detect-project-type.sh",{"path":900,"priority":553},"scripts/read-launch-json.sh",{"path":902,"priority":553},"scripts/resolve-package-manager.sh",{"path":904,"priority":553},"scripts/resolve-port.sh",{"basePath":906,"description":907,"displayName":908,"installMethods":909,"rationale":910,"selectedPaths":911,"source":327,"sourceLanguage":18,"type":249},"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",[912,913,915],{"path":550,"priority":326},{"path":914,"priority":341},"references/interview.md",{"path":916,"priority":341},"references/report-template.md",{"basePath":918,"description":919,"displayName":920,"installMethods":921,"rationale":922,"selectedPaths":923,"source":327,"sourceLanguage":18,"type":249},"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",[924,925],{"path":550,"priority":326},{"path":926,"priority":341},"references/hitl-review.md",{"basePath":928,"description":929,"displayName":930,"installMethods":931,"rationale":932,"selectedPaths":933,"source":327,"sourceLanguage":18,"type":249},"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",[934,935],{"path":550,"priority":326},{"path":936,"priority":553},"scripts/list-plugin-releases.py",{"basePath":938,"description":939,"displayName":940,"installMethods":941,"rationale":942,"selectedPaths":943,"source":327,"sourceLanguage":18,"type":249},"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",[944],{"path":550,"priority":326},{"basePath":246,"description":10,"displayName":13,"installMethods":946,"rationale":947,"selectedPaths":948,"source":327,"sourceLanguage":18,"type":249},{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-resolve-pr-feedback/SKILL.md",[949,950,952,954,956,958,960],{"path":550,"priority":326},{"path":951,"priority":341},"references/full-mode.md",{"path":953,"priority":341},"references/targeted-mode.md",{"path":955,"priority":553},"scripts/get-pr-comments",{"path":957,"priority":553},"scripts/get-thread-for-comment",{"path":959,"priority":553},"scripts/reply-to-pr-thread",{"path":961,"priority":553},"scripts/resolve-pr-thread",{"basePath":963,"description":964,"displayName":965,"installMethods":966,"rationale":967,"selectedPaths":968,"source":327,"sourceLanguage":18,"type":249},"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",[969,970,972,974,976,978],{"path":550,"priority":326},{"path":971,"priority":341},"references/compound-engineering-feedback-format.md",{"path":973,"priority":341},"references/extensive-analysis.md",{"path":975,"priority":341},"references/install-riffrec.md",{"path":977,"priority":341},"references/quick-bug-report.md",{"path":979,"priority":553},"scripts/analyze_riffrec_zip.py",{"basePath":981,"description":982,"displayName":983,"installMethods":984,"rationale":985,"selectedPaths":986,"source":327,"sourceLanguage":18,"type":249},"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",[987,988,990,992,994],{"path":550,"priority":326},{"path":989,"priority":553},"scripts/discover-sessions.sh",{"path":991,"priority":553},"scripts/extract-errors.py",{"path":993,"priority":553},"scripts/extract-metadata.py",{"path":995,"priority":553},"scripts/extract-skeleton.py",{"basePath":997,"description":998,"displayName":999,"installMethods":1000,"rationale":1001,"selectedPaths":1002,"source":327,"sourceLanguage":18,"type":249},"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",[1003,1004,1006],{"path":550,"priority":326},{"path":1005,"priority":341},"references/config-template.yaml",{"path":1007,"priority":553},"scripts/check-health",{"basePath":1009,"description":1010,"displayName":1011,"installMethods":1012,"rationale":1013,"selectedPaths":1014,"source":327,"sourceLanguage":18,"type":249},"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",[1015],{"path":550,"priority":326},{"basePath":1017,"description":1018,"displayName":1019,"installMethods":1020,"rationale":1021,"selectedPaths":1022,"source":327,"sourceLanguage":18,"type":249},"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",[1023],{"path":550,"priority":326},{"basePath":1025,"description":1026,"displayName":1027,"installMethods":1028,"rationale":1029,"selectedPaths":1030,"source":327,"sourceLanguage":18,"type":249},"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",[1031,1032,1033],{"path":550,"priority":326},{"path":914,"priority":341},{"path":1034,"priority":341},"references/strategy-template.md",{"basePath":1036,"description":1037,"displayName":1038,"installMethods":1039,"rationale":1040,"selectedPaths":1041,"source":327,"sourceLanguage":18,"type":249},"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",[1042],{"path":550,"priority":326},{"basePath":1044,"description":1045,"displayName":1046,"installMethods":1047,"rationale":1048,"selectedPaths":1049,"source":327,"sourceLanguage":18,"type":249},"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",[1050],{"path":550,"priority":326},{"basePath":1052,"description":1053,"displayName":1054,"installMethods":1055,"rationale":1056,"selectedPaths":1057,"source":327,"sourceLanguage":18,"type":249},"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",[1058,1059,1061,1063],{"path":550,"priority":326},{"path":1060,"priority":553},"scripts/currently-loaded-version.sh",{"path":1062,"priority":553},"scripts/marketplace-name.sh",{"path":1064,"priority":553},"scripts/upstream-version.sh",{"basePath":1066,"description":1067,"displayName":1068,"installMethods":1069,"rationale":1070,"selectedPaths":1071,"source":327,"sourceLanguage":18,"type":249},"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",[1072,1073,1075],{"path":550,"priority":326},{"path":1074,"priority":341},"references/shipping-workflow.md",{"path":655,"priority":341},{"basePath":1077,"description":1078,"displayName":1079,"installMethods":1080,"rationale":1081,"selectedPaths":1082,"source":327,"sourceLanguage":18,"type":249},"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",[1083,1084,1086,1087],{"path":550,"priority":326},{"path":1085,"priority":341},"references/codex-delegation-workflow.md",{"path":1074,"priority":341},{"path":655,"priority":341},{"basePath":1089,"description":1090,"displayName":1091,"installMethods":1092,"rationale":1093,"selectedPaths":1094,"source":327,"sourceLanguage":18,"type":249},"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",[1095,1096],{"path":550,"priority":326},{"path":1097,"priority":553},"scripts/worktree-manager.sh",{"basePath":1099,"description":1100,"displayName":1101,"installMethods":1102,"rationale":1103,"selectedPaths":1104,"source":327,"sourceLanguage":18,"type":249},"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",[1105,1106],{"path":550,"priority":326},{"path":655,"priority":341},{"basePath":270,"description":1108,"displayName":1109,"installMethods":1110,"rationale":1111,"selectedPaths":1112,"source":327,"sourceLanguage":18,"type":1129},"Official Compound Engineering plugin for Claude Code, Codex, and more","@every-env/compound-plugin",{"npm":1109},"cli ecosystem detected at /",[1113,1115,1116,1117,1119,1121,1123,1125,1127],{"path":1114,"priority":326},"package.json",{"path":335,"priority":326},{"path":337,"priority":338},{"path":1118,"priority":341},"src/index.ts",{"path":1120,"priority":553},"src/commands/cleanup.ts",{"path":1122,"priority":553},"src/commands/convert.ts",{"path":1124,"priority":553},"src/commands/install.ts",{"path":1126,"priority":553},"src/commands/list.ts",{"path":1128,"priority":553},"src/commands/plugin-path.ts","cli",{"sources":1131},[1132],"manual",{"npmPackage":1109},{"closedIssues90d":232,"description":1135,"forks":233,"homepage":1136,"license":240,"openIssues90d":234,"pushedAt":235,"readmeSize":230,"stars":236,"topics":1137},"Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more","https://every.to/guides/compound-engineering",[1138,1139],"compound","engineering",{"downloads":238},{"classifiedAt":1142,"discoverAt":1143,"extractAt":1144,"githubAt":1144,"npmAt":1145,"updatedAt":1142},1778686639998,1778686632796,1778686635929,1778686638203,[215,214,216,212,213],{"evaluatedAt":244,"extractAt":292,"updatedAt":244},[],[1150,1175,1196,1224,1255,1276],{"_creationTime":1151,"_id":1152,"community":1153,"display":1154,"identity":1159,"providers":1163,"relations":1169,"tags":1171,"workflow":1172},1778697652123.8928,"k171pew5empzzrfghyg9nqrk6n86nqa9",{"reviewCount":8},{"description":1155,"installMethods":1156,"name":212,"sourceUrl":1158},"Use gh for GitHub issues, PR status, CI/logs, comments, reviews, releases, and API queries.",{"claudeCode":1157},"steipete/clawdis","https://github.com/steipete/clawdis",{"basePath":1160,"githubOwner":1161,"githubRepo":1162,"locale":18,"slug":212,"type":249},"skills/github","steipete","clawdis",{"evaluate":1164,"extract":1168},{"promptVersionExtension":205,"promptVersionScoring":206,"score":1165,"tags":1166,"targetMarket":217,"tier":218},100,[212,1129,1167,216,215],"api",{"commitSha":282},{"repoId":1170},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[1167,215,1129,216,212],{"evaluatedAt":1173,"extractAt":1174,"updatedAt":1173},1778698569289,1778697652123,{"_creationTime":1176,"_id":1177,"community":1178,"display":1179,"identity":1183,"providers":1186,"relations":1192,"tags":1193,"workflow":1194},1778697652123.8804,"k173mjn1bp2a67v1h8qjkv7wn186met8",{"reviewCount":8},{"description":1180,"installMethods":1181,"name":1182,"sourceUrl":1158},"Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, commit-review reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed autofix/automerge, GitHub Actions monitoring, permissions, gates, and manual backfills.",{"claudeCode":1157},"ClawSweeper Skill",{"basePath":1184,"githubOwner":1161,"githubRepo":1162,"locale":18,"slug":1185,"type":249},".agents/skills/clawsweeper","clawsweeper",{"evaluate":1187,"extract":1191},{"promptVersionExtension":205,"promptVersionScoring":206,"score":1165,"tags":1188,"targetMarket":217,"tier":218},[212,215,214,1189,1190],"maintenance","ci-cd",{"commitSha":282,"license":240},{"repoId":1170},[215,1190,214,212,1189],{"evaluatedAt":1195,"extractAt":1174,"updatedAt":1195},1778697688364,{"_creationTime":1197,"_id":1198,"community":1199,"display":1200,"identity":1206,"providers":1210,"relations":1217,"tags":1220,"workflow":1221},1778699234184.611,"k179b6dkc777g1rgyecze04wqn86m6y4",{"reviewCount":8},{"description":1201,"installMethods":1202,"name":1204,"sourceUrl":1205},"Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly",{"claudeCode":1203},"Yeachan-Heo/oh-my-claudecode","oh-my-claudecode","https://github.com/Yeachan-Heo/oh-my-claudecode",{"basePath":1207,"githubOwner":1208,"githubRepo":1204,"locale":18,"slug":1209,"type":249},"skills/ask","Yeachan-Heo","ask",{"evaluate":1211,"extract":1216},{"promptVersionExtension":205,"promptVersionScoring":206,"score":1165,"tags":1212,"targetMarket":217,"tier":218},[1129,215,1213,1214,214,1215],"llm","prompting","artifact-generation",{"commitSha":282,"license":240},{"parentExtensionId":1218,"repoId":1219},"k17brg5egdw1jbncj1j4wfv3fh86n639","kd74zv63fryf9prygtq7gf4es986n22y",[1215,215,1129,214,1213,1214],{"evaluatedAt":1222,"extractAt":1223,"updatedAt":1222},1778699303045,1778699234184,{"_creationTime":1225,"_id":1226,"community":1227,"display":1228,"identity":1234,"providers":1240,"relations":1247,"tags":1250,"workflow":1251},1778699368519.5344,"k17ab0jk30pqm4zejpk383w4dn86mj8t",{"reviewCount":8},{"description":1229,"installMethods":1230,"name":1232,"sourceUrl":1233},"Verwenden Sie dies, wenn die Arbeit von den Live-Browsersitzungs- oder gerenderten Zustand des Benutzers abhängt und nicht von statischen Abrufen, insbesondere für Browser-Debugging-Kontexte oder von DevTools ausgewählte Elemente oder Anfragen, angemeldeten Dashboards oder CMS-Flows, localhost-Apps, Formularen, Uploads, Downloads, Medieninspektion, DOM- oder iframe-Inspektion, Shadow DOM oder Browserfehlern, die wie Soft-404s, Authentifizierungswände, Anti-Bot-Prüfungen oder Ratenbegrenzungen aussehen.",{"claudeCode":1231},"xixu-me/skills","Use My Browser","https://github.com/xixu-me/skills",{"basePath":1235,"githubOwner":1236,"githubRepo":1237,"locale":1238,"slug":1239,"type":249},"skills/use-my-browser","xixu-me","skills","de","use-my-browser",{"evaluate":1241,"extract":1246},{"promptVersionExtension":205,"promptVersionScoring":206,"score":1165,"tags":1242,"targetMarket":217,"tier":218},[1243,1244,215,1245,216],"browser","debugging","ux",{"commitSha":282,"license":240},{"repoId":1248,"translatedFrom":1249},"kd77r2vb42jmgam0qbr9f2c6kn86mebv","k179cgk616p3xva37r5jqsfwvh86mcp2",[215,1243,1244,216,1245],{"evaluatedAt":1252,"extractAt":1253,"updatedAt":1254},1778699261239,1778699106670,1778699368519,{"_creationTime":1256,"_id":1257,"community":1258,"display":1259,"identity":1263,"providers":1265,"relations":1272,"tags":1273,"workflow":1274},1778697652123.8845,"k17bexjjjsz81ysk7bd3ggdm8s86mt2t",{"reviewCount":8},{"description":1260,"installMethods":1261,"name":1262,"sourceUrl":1158},"Choose, run, rerun, or debug OpenClaw tests, CI checks, Docker E2E lanes, release validation, and the cheapest safe verification path.",{"claudeCode":1157},"openclaw-testing",{"basePath":1264,"githubOwner":1161,"githubRepo":1162,"locale":18,"slug":1262,"type":249},".agents/skills/openclaw-testing",{"evaluate":1266,"extract":1271},{"promptVersionExtension":205,"promptVersionScoring":206,"score":1165,"tags":1267,"targetMarket":217,"tier":218},[1268,1269,1270,215,216],"testing","ci","validation",{"commitSha":282},{"repoId":1170},[215,1269,216,1268,1270],{"evaluatedAt":1275,"extractAt":1174,"updatedAt":1275},1778697962962,{"_creationTime":1277,"_id":1278,"community":1279,"display":1280,"identity":1286,"providers":1290,"relations":1299,"tags":1302,"workflow":1303},1778695548458.3926,"k172f2ed2j5kxdq8hbw4nszcw186m5xj",{"reviewCount":8},{"description":1281,"installMethods":1282,"name":1284,"sourceUrl":1285},"Review a pull request end-to-end using GitHub CLI. Covers diff analysis, commit history review, CI/CD check verification, severity-leveled feedback (blocking/suggestion/nit/praise), and gh pr review submission. Use when a pull request is assigned for review, performing a self-review before requesting others' input, conducting a second review after feedback is addressed, or auditing a merged PR for post-merge quality assessment.\n",{"claudeCode":1283},"pjt222/agent-almanac","review-pull-request","https://github.com/pjt222/agent-almanac",{"basePath":1287,"githubOwner":1288,"githubRepo":1289,"locale":18,"slug":1284,"type":249},"skills/review-pull-request","pjt222","agent-almanac",{"evaluate":1291,"extract":1298},{"promptVersionExtension":205,"promptVersionScoring":206,"score":1165,"tags":1292,"targetMarket":217,"tier":218},[1293,1294,212,214,1295,1296,1297],"review","pull-request","gh-cli","feedback","pr",{"commitSha":282},{"parentExtensionId":1300,"repoId":1301},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[214,1296,1295,212,1297,1294,1293],{"evaluatedAt":1304,"extractAt":1305,"updatedAt":1304},1778700796502,1778695548458]