[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-EveryInc-ce-test-browser-de":3,"guides-for-EveryInc-ce-test-browser":1167,"similar-k173npg49t3qa1x72jhc9vqadn86mvsq-de":1168},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":263,"isFallback":244,"parentExtension":269,"providers":328,"relations":332,"repo":333,"tags":1165,"workflow":1166},1778686640222.7986,"k173npg49t3qa1x72jhc9vqadn86mvsq",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Run browser tests on pages affected by current PR or branch",{"claudeCode":12},"EveryInc/compound-engineering-plugin","Compound Engineering Browser Test","https://github.com/EveryInc/compound-engineering-plugin",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":242,"workflow":261},1778687496344.4773,"kn755msd21s9fc0287ere9d8zd86mbtk","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"practices":204,"prerequisites":208,"promptVersionExtension":212,"promptVersionScoring":213,"purpose":214,"rationale":215,"score":216,"summary":217,"tags":218,"targetMarket":224,"tier":225,"useCases":226,"workflow":231},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,112,115,120,123,126,129,132,135,138,142,146,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of running browser tests on pages affected by a PR or branch.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill uses a dedicated CLI (`agent-browser`) for browser automation, steering behavior beyond default LLM capabilities and offering value over direct API use.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The extension covers the full lifecycle from setup and dependency checks to test execution, reporting, and human verification steps, making it ready for production workflows.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses on running browser tests using a specific tool (`agent-browser`) and is clearly named for this purpose.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The description accurately reflects the skill's functionality of running browser tests on affected pages.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The skill primarily uses the `agent-browser` CLI, which is a scoped tool, and the workflow specifies distinct commands within it.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","The SKILL.md details prerequisites, setup, workflow steps, and provides a reference for `agent-browser` commands, including port detection logic.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","The primary tool used is `agent-browser`, and the workflow uses descriptive commands like `open`, `snapshot`, `click`, which are clear.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","The `agent-browser` commands specified in the workflow have clear and documented inputs and outputs, focusing on the task at hand.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The extension is licensed under the MIT license, as indicated in the LICENSE file and README.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The repository shows recent commits as of 2026-05-13, indicating active maintenance.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","The project uses npm and includes a lockfile (`package-lock.json` implied by npm presence and `hasLockfile: true`), indicating good dependency management.",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","The skill does not appear to handle or expose secrets; it focuses on browser automation and local development server interaction.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","The skill uses specific CLI commands and processes local files like `git diff` and `package.json`, without loading untrusted external data as instructions.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","The skill relies on committed CLI tools and local file analysis, with no indication of runtime fetching of arbitrary code or content as instructions.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","The skill operates on local files and interacts with a local dev server, with no indication of writing outside the project directory or specified scopes.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","No detached-process spawns or deny-retry loops are evident in the provided scripts or workflow descriptions.",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","The skill focuses on local testing and does not involve sending confidential data to third parties.",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","The bundled content and descriptions appear free of hidden-steering tricks.",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","The bundled scripts and workflow descriptions are plain and readable, with no evidence of obfuscation or eval-based execution.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The skill makes assumptions about local development server setup and Git repository structure, which are standard and documented.",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","The repository shows 25 issues opened and 115 closed in the last 90 days, with a closure rate well above 50%, indicating good maintainer engagement.",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","The presence of npm versioning (`npm install` command, Shields.io badge) and a CHANGELOG indicates proper release management.",{"category":103,"check":104,"severity":24,"summary":105},"Code Execution","Validation","While explicit schema validation libraries aren't shown, the skill uses specific CLI commands and arguments, implying a degree of input validation.",{"category":65,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","The skill is primarily for testing and analysis and does not perform destructive operations like deleting files or modifying critical infrastructure.",{"category":103,"check":110,"severity":24,"summary":111},"Error Handling","The workflow includes steps for handling failures, documenting issues, and asking the user how to proceed, indicating robust error management.",{"category":103,"check":113,"severity":24,"summary":114},"Logging","The workflow includes logging for server startup (`/tmp/dev-server-${PORT}.log`) and indicates screenshots are taken, suggesting auditability.",{"category":116,"check":117,"severity":118,"summary":119},"Compliance","GDPR","not_applicable","The skill operates on local project files and browser automation, not personal data.",{"category":116,"check":121,"severity":24,"summary":122},"Target market","The extension operates on local development environments and is not geographically restricted; targetMarket is 'global'.",{"category":91,"check":124,"severity":24,"summary":125},"Runtime stability","The skill uses standard shell commands and a Node.js CLI (`agent-browser`), making it portable across POSIX-like environments.",{"category":44,"check":127,"severity":24,"summary":128},"README","The README provides a good overview of the project's philosophy, workflow, and installation instructions.",{"category":33,"check":130,"severity":118,"summary":131},"Tool surface size","This is a single-purpose skill focused on browser testing via the `agent-browser` CLI.",{"category":40,"check":133,"severity":24,"summary":134},"Overlapping near-synonym tools","The skill utilizes specific commands from the `agent-browser` CLI, none of which are near-synonyms for core functions.",{"category":44,"check":136,"severity":24,"summary":137},"Phantom features","All advertised features, such as running tests on affected pages and using `agent-browser`, are implemented in the SKILL.md.",{"category":139,"check":140,"severity":24,"summary":141},"Install","Installation instruction","The README provides detailed installation instructions for various platforms (Claude Code, Cursor, Codex, Copilot, etc.) and includes copy-pasteable examples.",{"category":143,"check":144,"severity":24,"summary":145},"Errors","Actionable error messages","The workflow includes specific steps for documenting failures and asking the user how to proceed, providing actionable feedback.",{"category":147,"check":148,"severity":24,"summary":149},"Execution","Pinned dependencies","The presence of npm, `hasLockfile: true`, and the `agent-browser` CLI implies pinned dependencies and a declared interpreter.",{"category":33,"check":151,"severity":118,"summary":152},"Dry-run preview","The skill is focused on testing and does not perform state-changing operations that would necessitate a dry-run preview.",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","The workflow includes a wait loop for the dev server and handles test failures, suggesting retry logic and timeouts are considered.",{"category":116,"check":158,"severity":24,"summary":159},"Telemetry opt-in","The skill does not appear to emit telemetry; its focus is local testing and development.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The skill clearly states it runs browser tests on pages affected by a PR/branch, naming the artifact (pages) and intent (run tests).",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter is concise and clearly defines the skill's purpose and usage arguments.",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md is well-structured and under 500 lines, delegating detailed CLI reference to the end.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The SKILL.md outlines the workflow and provides a CLI reference at the end, effectively using progressive disclosure.",{"category":170,"check":174,"severity":118,"summary":175},"Forked exploration","This skill is not primarily focused on deep exploration or code review that would require forked context.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The README provides clear, ready-to-use examples for testing the current branch, specific PRs, branches, and ports.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The SKILL.md documents failure modes like server not running or `agent-browser` not installed, with recovery steps.",{"category":103,"check":183,"severity":24,"summary":184},"Tool Fallback","The skill handles cases where `agent-browser` is not installed and also provides a fallback for port detection if not explicitly provided.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The skill explicitly checks for prerequisites like `agent-browser` installation and server readiness, halting if they are not met.",{"category":91,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The skill is self-contained and focuses on browser testing via `agent-browser`, without implicit reliance on other skills.",1778687496232,"This skill automates browser testing for changes in a Git PR or branch using the `agent-browser` CLI. It handles dependency checks, server startup, test execution, and reporting.",[195,196,197,198,199],"Run browser tests on PR/branch changes","Integrates with `agent-browser` CLI","Handles headed or headless test execution","Detects and maps affected files to routes","Manages local development server startup and port detection",[201,202,203],"Performing general web scraping","Replacing full end-to-end testing frameworks","Managing remote browser environments",[205,206,207],"Automated Testing","CI/CD Integration","Browser Automation",[209,210,211],"Local development server running","`agent-browser` CLI installed","Git repository with changes to test","3.0.0","4.4.0","To enable developers to automatically run end-to-end browser tests on affected pages for current PRs or branches, ensuring code quality and stability.","The extension is well-documented, production-ready, and covers its scope precisely with clear instructions and error handling. All checks passed or were not applicable.",99,"A high-quality skill for automating browser tests on code changes.",[219,220,221,222,223],"testing","browser-automation","cli","qa","ci","global","verified",[227,228,229,230],"Automate regression testing for a new feature branch","Verify UI stability after code modifications","Ensure visual consistency across key pages before merging","Integrate browser testing into CI/CD pipelines",[232,233,234,235,236,237,238,239,240,241],"Verify agent-browser installation","Ask user for headed or headless mode (if not pipeline mode)","Determine test scope (PR, current branch, or named branch)","Map changed files to testable routes","Detect and claim a free port for the dev server","Start dev server if not running (pipeline mode only)","Navigate to and test each affected page","Perform human verification for critical flows","Handle and document test failures","Present a summary of test results",{"codeQuality":243,"collectedAt":245,"documentation":246,"maintenance":249,"popularity":255,"security":257,"testCoverage":260},{"hasLockfile":244},true,1778687468204,{"descriptionLength":247,"readmeSize":248},59,17582,{"closedIssues90d":250,"forks":251,"hasChangelog":244,"openIssues90d":252,"pushedAt":253,"stars":254},115,1300,25,1778686215000,16666,{"npmDownloads":256},12828,{"hasNpmPackage":244,"license":258,"smitheryVerified":259},"MIT",false,{"hasCi":244,"hasTests":244},{"updatedAt":262},1778687496344,{"basePath":264,"githubOwner":265,"githubRepo":266,"locale":18,"slug":267,"type":268},"plugins/compound-engineering/skills/ce-test-browser","EveryInc","compound-engineering-plugin","ce-test-browser","skill",{"_creationTime":270,"_id":271,"community":272,"display":273,"identity":277,"parentExtension":280,"providers":312,"relations":324,"tags":325,"workflow":326},1778686640222.7903,"k17d893df4em0e3pn8f55h1dxn86n09e",{"reviewCount":8},{"description":274,"installMethods":275,"name":276,"sourceUrl":14},"AI-powered development tools for code review, research, design, and workflow automation.",{"claudeCode":276},"compound-engineering",{"basePath":278,"githubOwner":265,"githubRepo":266,"locale":18,"slug":276,"type":279},"plugins/compound-engineering","plugin",{"_creationTime":281,"_id":282,"community":283,"display":284,"identity":288,"providers":291,"relations":306,"tags":308,"workflow":309},1778686640222.7908,"k17ef8php9wk308mkg59kdp6b186nzhx",{"reviewCount":8},{"description":285,"installMethods":286,"name":287,"sourceUrl":14},"Cursor plugin marketplace for Every Inc plugins",{"claudeCode":12},"Compound Engineering",{"basePath":289,"githubOwner":265,"githubRepo":266,"locale":18,"slug":266,"type":290},"","marketplace",{"evaluate":292,"extract":300},{"promptVersionExtension":293,"promptVersionScoring":213,"score":216,"tags":294,"targetMarket":224,"tier":225},"3.1.0",[295,296,297,298,299],"development-workflow","code-review","planning","documentation","ai-agents",{"commitSha":301,"license":258,"marketplace":302,"plugin":304},"HEAD",{"name":266,"pluginCount":303},2,{"mcpCount":8,"provider":305,"skillCount":8},"classify",{"repoId":307},"kd7e40my1b5g70tg0f60qg85ch86nn08",[299,296,295,298,297],{"evaluatedAt":310,"extractAt":311,"updatedAt":310},1778686722515,1778686640222,{"evaluate":313,"extract":321},{"promptVersionExtension":212,"promptVersionScoring":213,"score":314,"tags":315,"targetMarket":224,"tier":225},98,[316,317,296,318,298,319,297,320],"ai","developer-tools","research","workflow-automation","ideation",{"commitSha":301,"license":258,"plugin":322},{"mcpCount":8,"provider":305,"skillCount":323},37,{"parentExtensionId":282,"repoId":307},[316,296,317,298,320,297,318,319],{"evaluatedAt":327,"extractAt":311,"updatedAt":327},1778686677611,{"evaluate":329,"extract":331},{"promptVersionExtension":212,"promptVersionScoring":213,"score":216,"tags":330,"targetMarket":224,"tier":225},[219,220,221,222,223],{"commitSha":301,"license":258},{"parentExtensionId":271,"repoId":307},{"_creationTime":334,"_id":307,"identity":335,"providers":336,"workflow":1160},1778686632796.9226,{"githubOwner":265,"githubRepo":266,"sourceUrl":14},{"classify":337,"discover":1149,"extract":1152,"github":1153,"npm":1159},{"commitSha":301,"extensions":338},[339,348,536,555,563,580,618,626,644,654,680,688,700,716,730,744,764,784,801,809,827,841,869,887,925,937,947,957,965,985,1003,1019,1031,1039,1047,1058,1063,1071,1085,1096,1108,1118,1127],{"basePath":340,"displayName":266,"installMethods":341,"rationale":342,"selectedPaths":343,"source":347,"sourceLanguage":18,"type":290},".agents/plugins",{"claudeCode":12},"marketplace.json at .agents/plugins/marketplace.json (coalesced with duplicate marketplace at /)",[344],{"path":345,"priority":346},"marketplace.json","mandatory","rule",{"basePath":278,"description":274,"displayName":276,"installMethods":349,"license":258,"rationale":350,"selectedPaths":351,"source":347,"sourceLanguage":18,"type":279},{"claudeCode":276},"plugin manifest at plugins/compound-engineering/.claude-plugin/plugin.json",[352,354,356,359,362,364,366,368,370,372,374,376,378,380,382,384,386,388,390,392,394,396,398,400,402,404,406,408,410,412,414,416,418,420,422,424,426,428,430,432,434,436,438,440,442,444,446,448,450,452,454,456,458,460,462,464,466,468,470,472,474,476,478,480,482,484,486,488,490,492,494,496,498,500,502,504,506,508,510,512,514,516,518,520,522,524,526,528,530,532,534],{"path":353,"priority":346},".claude-plugin/plugin.json",{"path":355,"priority":346},"README.md",{"path":357,"priority":358},"LICENSE","high",{"path":360,"priority":361},"skills/ce-agent-native-architecture/SKILL.md","medium",{"path":363,"priority":361},"skills/ce-agent-native-audit/SKILL.md",{"path":365,"priority":361},"skills/ce-brainstorm/SKILL.md",{"path":367,"priority":361},"skills/ce-clean-gone-branches/SKILL.md",{"path":369,"priority":361},"skills/ce-code-review/SKILL.md",{"path":371,"priority":361},"skills/ce-commit/SKILL.md",{"path":373,"priority":361},"skills/ce-commit-push-pr/SKILL.md",{"path":375,"priority":361},"skills/ce-compound/SKILL.md",{"path":377,"priority":361},"skills/ce-compound-refresh/SKILL.md",{"path":379,"priority":361},"skills/ce-debug/SKILL.md",{"path":381,"priority":361},"skills/ce-demo-reel/SKILL.md",{"path":383,"priority":361},"skills/ce-dhh-rails-style/SKILL.md",{"path":385,"priority":361},"skills/ce-doc-review/SKILL.md",{"path":387,"priority":361},"skills/ce-frontend-design/SKILL.md",{"path":389,"priority":361},"skills/ce-gemini-imagegen/SKILL.md",{"path":391,"priority":361},"skills/ce-ideate/SKILL.md",{"path":393,"priority":361},"skills/ce-optimize/SKILL.md",{"path":395,"priority":361},"skills/ce-plan/SKILL.md",{"path":397,"priority":361},"skills/ce-polish-beta/SKILL.md",{"path":399,"priority":361},"skills/ce-product-pulse/SKILL.md",{"path":401,"priority":361},"skills/ce-proof/SKILL.md",{"path":403,"priority":361},"skills/ce-release-notes/SKILL.md",{"path":405,"priority":361},"skills/ce-report-bug/SKILL.md",{"path":407,"priority":361},"skills/ce-resolve-pr-feedback/SKILL.md",{"path":409,"priority":361},"skills/ce-riffrec-feedback-analysis/SKILL.md",{"path":411,"priority":361},"skills/ce-sessions/SKILL.md",{"path":413,"priority":361},"skills/ce-setup/SKILL.md",{"path":415,"priority":361},"skills/ce-simplify-code/SKILL.md",{"path":417,"priority":361},"skills/ce-slack-research/SKILL.md",{"path":419,"priority":361},"skills/ce-strategy/SKILL.md",{"path":421,"priority":361},"skills/ce-test-browser/SKILL.md",{"path":423,"priority":361},"skills/ce-test-xcode/SKILL.md",{"path":425,"priority":361},"skills/ce-update/SKILL.md",{"path":427,"priority":361},"skills/ce-work/SKILL.md",{"path":429,"priority":361},"skills/ce-work-beta/SKILL.md",{"path":431,"priority":361},"skills/ce-worktree/SKILL.md",{"path":433,"priority":361},"skills/lfg/SKILL.md",{"path":435,"priority":358},"agents/ce-adversarial-document-reviewer.agent.md",{"path":437,"priority":358},"agents/ce-adversarial-reviewer.agent.md",{"path":439,"priority":358},"agents/ce-agent-native-reviewer.agent.md",{"path":441,"priority":358},"agents/ce-ankane-readme-writer.agent.md",{"path":443,"priority":358},"agents/ce-api-contract-reviewer.agent.md",{"path":445,"priority":358},"agents/ce-architecture-strategist.agent.md",{"path":447,"priority":358},"agents/ce-best-practices-researcher.agent.md",{"path":449,"priority":358},"agents/ce-code-simplicity-reviewer.agent.md",{"path":451,"priority":358},"agents/ce-coherence-reviewer.agent.md",{"path":453,"priority":358},"agents/ce-correctness-reviewer.agent.md",{"path":455,"priority":358},"agents/ce-data-integrity-guardian.agent.md",{"path":457,"priority":358},"agents/ce-data-migration-expert.agent.md",{"path":459,"priority":358},"agents/ce-data-migrations-reviewer.agent.md",{"path":461,"priority":358},"agents/ce-deployment-verification-agent.agent.md",{"path":463,"priority":358},"agents/ce-design-implementation-reviewer.agent.md",{"path":465,"priority":358},"agents/ce-design-iterator.agent.md",{"path":467,"priority":358},"agents/ce-design-lens-reviewer.agent.md",{"path":469,"priority":358},"agents/ce-dhh-rails-reviewer.agent.md",{"path":471,"priority":358},"agents/ce-feasibility-reviewer.agent.md",{"path":473,"priority":358},"agents/ce-figma-design-sync.agent.md",{"path":475,"priority":358},"agents/ce-framework-docs-researcher.agent.md",{"path":477,"priority":358},"agents/ce-git-history-analyzer.agent.md",{"path":479,"priority":358},"agents/ce-issue-intelligence-analyst.agent.md",{"path":481,"priority":358},"agents/ce-julik-frontend-races-reviewer.agent.md",{"path":483,"priority":358},"agents/ce-kieran-python-reviewer.agent.md",{"path":485,"priority":358},"agents/ce-kieran-rails-reviewer.agent.md",{"path":487,"priority":358},"agents/ce-kieran-typescript-reviewer.agent.md",{"path":489,"priority":358},"agents/ce-learnings-researcher.agent.md",{"path":491,"priority":358},"agents/ce-maintainability-reviewer.agent.md",{"path":493,"priority":358},"agents/ce-pattern-recognition-specialist.agent.md",{"path":495,"priority":358},"agents/ce-performance-oracle.agent.md",{"path":497,"priority":358},"agents/ce-performance-reviewer.agent.md",{"path":499,"priority":358},"agents/ce-pr-comment-resolver.agent.md",{"path":501,"priority":358},"agents/ce-previous-comments-reviewer.agent.md",{"path":503,"priority":358},"agents/ce-product-lens-reviewer.agent.md",{"path":505,"priority":358},"agents/ce-project-standards-reviewer.agent.md",{"path":507,"priority":358},"agents/ce-reliability-reviewer.agent.md",{"path":509,"priority":358},"agents/ce-repo-research-analyst.agent.md",{"path":511,"priority":358},"agents/ce-schema-drift-detector.agent.md",{"path":513,"priority":358},"agents/ce-scope-guardian-reviewer.agent.md",{"path":515,"priority":358},"agents/ce-security-lens-reviewer.agent.md",{"path":517,"priority":358},"agents/ce-security-reviewer.agent.md",{"path":519,"priority":358},"agents/ce-security-sentinel.agent.md",{"path":521,"priority":358},"agents/ce-session-historian.agent.md",{"path":523,"priority":358},"agents/ce-slack-researcher.agent.md",{"path":525,"priority":358},"agents/ce-spec-flow-analyzer.agent.md",{"path":527,"priority":358},"agents/ce-swift-ios-reviewer.agent.md",{"path":529,"priority":358},"agents/ce-testing-reviewer.agent.md",{"path":531,"priority":358},"agents/ce-web-researcher.agent.md",{"path":533,"priority":358},".codex-plugin/plugin.json",{"path":535,"priority":358},".cursor-plugin/plugin.json",{"basePath":537,"description":538,"displayName":539,"installMethods":540,"rationale":541,"selectedPaths":542,"source":347,"sourceLanguage":18,"type":279},"plugins/coding-tutor","Personalized coding tutorials that use your actual codebase for examples with spaced repetition quizzes","coding-tutor",{"claudeCode":539},"plugin manifest at plugins/coding-tutor/.claude-plugin/plugin.json",[543,544,545,547,549,551,553,554],{"path":353,"priority":346},{"path":355,"priority":346},{"path":546,"priority":361},"skills/coding-tutor/SKILL.md",{"path":548,"priority":358},"commands/quiz-me.md",{"path":550,"priority":358},"commands/sync-tutorials.md",{"path":552,"priority":358},"commands/teach-me.md",{"path":533,"priority":358},{"path":535,"priority":358},{"basePath":289,"description":285,"displayName":276,"installMethods":556,"rationale":557,"selectedPaths":558,"source":347,"sourceLanguage":18,"type":290},{"claudeCode":12},"marketplace.json at .cursor-plugin/marketplace.json",[559,561,562],{"path":560,"priority":346},".cursor-plugin/marketplace.json",{"path":355,"priority":346},{"path":357,"priority":358},{"basePath":564,"description":565,"displayName":539,"installMethods":566,"rationale":567,"selectedPaths":568,"source":347,"sourceLanguage":18,"type":268},"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",[569,571,574,576,578],{"path":570,"priority":346},"SKILL.md",{"path":572,"priority":573},"scripts/create_tutorial.py","low",{"path":575,"priority":573},"scripts/index_tutorials.py",{"path":577,"priority":573},"scripts/quiz_priority.py",{"path":579,"priority":573},"scripts/setup_tutorials.py",{"basePath":581,"description":582,"displayName":583,"installMethods":584,"rationale":585,"selectedPaths":586,"source":347,"sourceLanguage":18,"type":268},"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",[587,588,590,592,594,596,598,600,602,604,606,608,610,612,614,616],{"path":570,"priority":346},{"path":589,"priority":361},"references/action-parity-discipline.md",{"path":591,"priority":361},"references/agent-execution-patterns.md",{"path":593,"priority":361},"references/agent-native-testing.md",{"path":595,"priority":361},"references/architecture-patterns.md",{"path":597,"priority":361},"references/checklists.md",{"path":599,"priority":361},"references/dynamic-context-injection.md",{"path":601,"priority":361},"references/files-universal-interface.md",{"path":603,"priority":361},"references/from-primitives-to-domain-tools.md",{"path":605,"priority":361},"references/mcp-tool-design.md",{"path":607,"priority":361},"references/mobile-patterns.md",{"path":609,"priority":361},"references/product-implications.md",{"path":611,"priority":361},"references/refactoring-to-prompt-native.md",{"path":613,"priority":361},"references/self-modification.md",{"path":615,"priority":361},"references/shared-workspace-architecture.md",{"path":617,"priority":361},"references/system-prompt-design.md",{"basePath":619,"description":620,"displayName":621,"installMethods":622,"rationale":623,"selectedPaths":624,"source":347,"sourceLanguage":18,"type":268},"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",[625],{"path":570,"priority":346},{"basePath":627,"description":628,"displayName":629,"installMethods":630,"rationale":631,"selectedPaths":632,"source":347,"sourceLanguage":18,"type":268},"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",[633,634,636,638,640,642],{"path":570,"priority":346},{"path":635,"priority":361},"references/handoff.md",{"path":637,"priority":361},"references/requirements-capture.md",{"path":639,"priority":361},"references/synthesis-summary.md",{"path":641,"priority":361},"references/universal-brainstorming.md",{"path":643,"priority":361},"references/visual-communication.md",{"basePath":645,"description":646,"displayName":647,"installMethods":648,"rationale":649,"selectedPaths":650,"source":347,"sourceLanguage":18,"type":268},"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",[651,652],{"path":570,"priority":346},{"path":653,"priority":573},"scripts/clean-gone",{"basePath":655,"description":656,"displayName":657,"installMethods":658,"rationale":659,"selectedPaths":660,"source":347,"sourceLanguage":18,"type":268},"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",[661,662,664,666,668,670,672,674,676,678],{"path":570,"priority":346},{"path":663,"priority":361},"references/bulk-preview.md",{"path":665,"priority":361},"references/diff-scope.md",{"path":667,"priority":361},"references/findings-schema.json",{"path":669,"priority":361},"references/persona-catalog.md",{"path":671,"priority":361},"references/review-output-template.md",{"path":673,"priority":361},"references/subagent-template.md",{"path":675,"priority":361},"references/tracker-defer.md",{"path":677,"priority":361},"references/validator-template.md",{"path":679,"priority":361},"references/walkthrough.md",{"basePath":681,"description":682,"displayName":683,"installMethods":684,"rationale":685,"selectedPaths":686,"source":347,"sourceLanguage":18,"type":268},"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",[687],{"path":570,"priority":346},{"basePath":689,"description":690,"displayName":691,"installMethods":692,"rationale":693,"selectedPaths":694,"source":347,"sourceLanguage":18,"type":268},"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",[695,696,698],{"path":570,"priority":346},{"path":697,"priority":361},"references/branch-creation.md",{"path":699,"priority":361},"references/pr-description-writing.md",{"basePath":701,"description":702,"displayName":703,"installMethods":704,"rationale":705,"selectedPaths":706,"source":347,"sourceLanguage":18,"type":268},"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",[707,708,710,712,714],{"path":570,"priority":346},{"path":709,"priority":573},"assets/resolution-template.md",{"path":711,"priority":361},"references/schema.yaml",{"path":713,"priority":361},"references/yaml-schema.md",{"path":715,"priority":573},"scripts/validate-frontmatter.py",{"basePath":717,"description":718,"displayName":719,"installMethods":720,"rationale":721,"selectedPaths":722,"source":347,"sourceLanguage":18,"type":268},"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",[723,724,725,727,728,729],{"path":570,"priority":346},{"path":709,"priority":573},{"path":726,"priority":361},"references/per-action-flows.md",{"path":711,"priority":361},{"path":713,"priority":361},{"path":715,"priority":573},{"basePath":731,"description":732,"displayName":733,"installMethods":734,"rationale":735,"selectedPaths":736,"source":347,"sourceLanguage":18,"type":268},"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",[737,738,740,742],{"path":570,"priority":346},{"path":739,"priority":361},"references/anti-patterns.md",{"path":741,"priority":361},"references/defense-in-depth.md",{"path":743,"priority":361},"references/investigation-techniques.md",{"basePath":745,"description":746,"displayName":747,"installMethods":748,"rationale":749,"selectedPaths":750,"source":347,"sourceLanguage":18,"type":268},"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",[751,752,754,756,758,760,762],{"path":570,"priority":346},{"path":753,"priority":361},"references/tier-browser-reel.md",{"path":755,"priority":361},"references/tier-screenshot-reel.md",{"path":757,"priority":361},"references/tier-static-screenshots.md",{"path":759,"priority":361},"references/tier-terminal-recording.md",{"path":761,"priority":361},"references/upload-and-approval.md",{"path":763,"priority":573},"scripts/capture-demo.py",{"basePath":765,"description":766,"displayName":767,"installMethods":768,"rationale":769,"selectedPaths":770,"source":347,"sourceLanguage":18,"type":268},"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",[771,772,774,776,778,780,782],{"path":570,"priority":346},{"path":773,"priority":361},"references/architecture.md",{"path":775,"priority":361},"references/controllers.md",{"path":777,"priority":361},"references/frontend.md",{"path":779,"priority":361},"references/gems.md",{"path":781,"priority":361},"references/models.md",{"path":783,"priority":361},"references/testing.md",{"basePath":785,"description":786,"displayName":787,"installMethods":788,"rationale":789,"selectedPaths":790,"source":347,"sourceLanguage":18,"type":268},"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",[791,792,793,794,796,797,798,800],{"path":570,"priority":346},{"path":663,"priority":361},{"path":667,"priority":361},{"path":795,"priority":361},"references/open-questions-defer.md",{"path":671,"priority":361},{"path":673,"priority":361},{"path":799,"priority":361},"references/synthesis-and-presentation.md",{"path":679,"priority":361},{"basePath":802,"description":803,"displayName":804,"installMethods":805,"rationale":806,"selectedPaths":807,"source":347,"sourceLanguage":18,"type":268},"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",[808],{"path":570,"priority":346},{"basePath":810,"description":811,"displayName":812,"installMethods":813,"rationale":814,"selectedPaths":815,"source":347,"sourceLanguage":18,"type":268},"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",[816,817,819,821,823,825],{"path":570,"priority":346},{"path":818,"priority":573},"scripts/compose_images.py",{"path":820,"priority":573},"scripts/edit_image.py",{"path":822,"priority":573},"scripts/gemini_images.py",{"path":824,"priority":573},"scripts/generate_image.py",{"path":826,"priority":573},"scripts/multi_turn_chat.py",{"basePath":828,"description":829,"displayName":830,"installMethods":831,"rationale":832,"selectedPaths":833,"source":347,"sourceLanguage":18,"type":268},"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",[834,835,837,839],{"path":570,"priority":346},{"path":836,"priority":361},"references/post-ideation-workflow.md",{"path":838,"priority":361},"references/universal-ideation.md",{"path":840,"priority":361},"references/web-research-cache.md",{"basePath":842,"description":843,"displayName":844,"installMethods":845,"rationale":846,"selectedPaths":847,"source":347,"sourceLanguage":18,"type":268},"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",[848,849,851,853,855,857,859,861,863,865,867],{"path":570,"priority":346},{"path":850,"priority":361},"references/example-hard-spec.yaml",{"path":852,"priority":361},"references/example-judge-spec.yaml",{"path":854,"priority":361},"references/experiment-log-schema.yaml",{"path":856,"priority":361},"references/experiment-prompt-template.md",{"path":858,"priority":361},"references/judge-prompt-template.md",{"path":860,"priority":361},"references/optimize-spec-schema.yaml",{"path":862,"priority":361},"references/usage-guide.md",{"path":864,"priority":573},"scripts/experiment-worktree.sh",{"path":866,"priority":573},"scripts/measure.sh",{"path":868,"priority":573},"scripts/parallel-probe.sh",{"basePath":870,"description":871,"displayName":872,"installMethods":873,"rationale":874,"selectedPaths":875,"source":347,"sourceLanguage":18,"type":268},"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",[876,877,879,881,883,884,886],{"path":570,"priority":346},{"path":878,"priority":361},"references/deepening-workflow.md",{"path":880,"priority":361},"references/plan-handoff.md",{"path":882,"priority":361},"references/plan-template.md",{"path":639,"priority":361},{"path":885,"priority":361},"references/universal-planning.md",{"path":643,"priority":361},{"basePath":888,"description":889,"displayName":890,"installMethods":891,"rationale":892,"selectedPaths":893,"source":347,"sourceLanguage":18,"type":268},"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",[894,895,897,899,901,903,905,907,909,911,913,915,917,919,921,923],{"path":570,"priority":346},{"path":896,"priority":361},"references/dev-server-astro.md",{"path":898,"priority":361},"references/dev-server-detection.md",{"path":900,"priority":361},"references/dev-server-next.md",{"path":902,"priority":361},"references/dev-server-nuxt.md",{"path":904,"priority":361},"references/dev-server-procfile.md",{"path":906,"priority":361},"references/dev-server-rails.md",{"path":908,"priority":361},"references/dev-server-remix.md",{"path":910,"priority":361},"references/dev-server-sveltekit.md",{"path":912,"priority":361},"references/dev-server-vite.md",{"path":914,"priority":361},"references/ide-detection.md",{"path":916,"priority":361},"references/launch-json-schema.md",{"path":918,"priority":573},"scripts/detect-project-type.sh",{"path":920,"priority":573},"scripts/read-launch-json.sh",{"path":922,"priority":573},"scripts/resolve-package-manager.sh",{"path":924,"priority":573},"scripts/resolve-port.sh",{"basePath":926,"description":927,"displayName":928,"installMethods":929,"rationale":930,"selectedPaths":931,"source":347,"sourceLanguage":18,"type":268},"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",[932,933,935],{"path":570,"priority":346},{"path":934,"priority":361},"references/interview.md",{"path":936,"priority":361},"references/report-template.md",{"basePath":938,"description":939,"displayName":940,"installMethods":941,"rationale":942,"selectedPaths":943,"source":347,"sourceLanguage":18,"type":268},"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",[944,945],{"path":570,"priority":346},{"path":946,"priority":361},"references/hitl-review.md",{"basePath":948,"description":949,"displayName":950,"installMethods":951,"rationale":952,"selectedPaths":953,"source":347,"sourceLanguage":18,"type":268},"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",[954,955],{"path":570,"priority":346},{"path":956,"priority":573},"scripts/list-plugin-releases.py",{"basePath":958,"description":959,"displayName":960,"installMethods":961,"rationale":962,"selectedPaths":963,"source":347,"sourceLanguage":18,"type":268},"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",[964],{"path":570,"priority":346},{"basePath":966,"description":967,"displayName":968,"installMethods":969,"rationale":970,"selectedPaths":971,"source":347,"sourceLanguage":18,"type":268},"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",[972,973,975,977,979,981,983],{"path":570,"priority":346},{"path":974,"priority":361},"references/full-mode.md",{"path":976,"priority":361},"references/targeted-mode.md",{"path":978,"priority":573},"scripts/get-pr-comments",{"path":980,"priority":573},"scripts/get-thread-for-comment",{"path":982,"priority":573},"scripts/reply-to-pr-thread",{"path":984,"priority":573},"scripts/resolve-pr-thread",{"basePath":986,"description":987,"displayName":988,"installMethods":989,"rationale":990,"selectedPaths":991,"source":347,"sourceLanguage":18,"type":268},"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",[992,993,995,997,999,1001],{"path":570,"priority":346},{"path":994,"priority":361},"references/compound-engineering-feedback-format.md",{"path":996,"priority":361},"references/extensive-analysis.md",{"path":998,"priority":361},"references/install-riffrec.md",{"path":1000,"priority":361},"references/quick-bug-report.md",{"path":1002,"priority":573},"scripts/analyze_riffrec_zip.py",{"basePath":1004,"description":1005,"displayName":1006,"installMethods":1007,"rationale":1008,"selectedPaths":1009,"source":347,"sourceLanguage":18,"type":268},"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",[1010,1011,1013,1015,1017],{"path":570,"priority":346},{"path":1012,"priority":573},"scripts/discover-sessions.sh",{"path":1014,"priority":573},"scripts/extract-errors.py",{"path":1016,"priority":573},"scripts/extract-metadata.py",{"path":1018,"priority":573},"scripts/extract-skeleton.py",{"basePath":1020,"description":1021,"displayName":1022,"installMethods":1023,"rationale":1024,"selectedPaths":1025,"source":347,"sourceLanguage":18,"type":268},"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",[1026,1027,1029],{"path":570,"priority":346},{"path":1028,"priority":361},"references/config-template.yaml",{"path":1030,"priority":573},"scripts/check-health",{"basePath":1032,"description":1033,"displayName":1034,"installMethods":1035,"rationale":1036,"selectedPaths":1037,"source":347,"sourceLanguage":18,"type":268},"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",[1038],{"path":570,"priority":346},{"basePath":1040,"description":1041,"displayName":1042,"installMethods":1043,"rationale":1044,"selectedPaths":1045,"source":347,"sourceLanguage":18,"type":268},"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",[1046],{"path":570,"priority":346},{"basePath":1048,"description":1049,"displayName":1050,"installMethods":1051,"rationale":1052,"selectedPaths":1053,"source":347,"sourceLanguage":18,"type":268},"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",[1054,1055,1056],{"path":570,"priority":346},{"path":934,"priority":361},{"path":1057,"priority":361},"references/strategy-template.md",{"basePath":264,"description":10,"displayName":267,"installMethods":1059,"rationale":1060,"selectedPaths":1061,"source":347,"sourceLanguage":18,"type":268},{"claudeCode":12},"SKILL.md frontmatter at plugins/compound-engineering/skills/ce-test-browser/SKILL.md",[1062],{"path":570,"priority":346},{"basePath":1064,"description":1065,"displayName":1066,"installMethods":1067,"rationale":1068,"selectedPaths":1069,"source":347,"sourceLanguage":18,"type":268},"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",[1070],{"path":570,"priority":346},{"basePath":1072,"description":1073,"displayName":1074,"installMethods":1075,"rationale":1076,"selectedPaths":1077,"source":347,"sourceLanguage":18,"type":268},"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",[1078,1079,1081,1083],{"path":570,"priority":346},{"path":1080,"priority":573},"scripts/currently-loaded-version.sh",{"path":1082,"priority":573},"scripts/marketplace-name.sh",{"path":1084,"priority":573},"scripts/upstream-version.sh",{"basePath":1086,"description":1087,"displayName":1088,"installMethods":1089,"rationale":1090,"selectedPaths":1091,"source":347,"sourceLanguage":18,"type":268},"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",[1092,1093,1095],{"path":570,"priority":346},{"path":1094,"priority":361},"references/shipping-workflow.md",{"path":675,"priority":361},{"basePath":1097,"description":1098,"displayName":1099,"installMethods":1100,"rationale":1101,"selectedPaths":1102,"source":347,"sourceLanguage":18,"type":268},"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",[1103,1104,1106,1107],{"path":570,"priority":346},{"path":1105,"priority":361},"references/codex-delegation-workflow.md",{"path":1094,"priority":361},{"path":675,"priority":361},{"basePath":1109,"description":1110,"displayName":1111,"installMethods":1112,"rationale":1113,"selectedPaths":1114,"source":347,"sourceLanguage":18,"type":268},"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",[1115,1116],{"path":570,"priority":346},{"path":1117,"priority":573},"scripts/worktree-manager.sh",{"basePath":1119,"description":1120,"displayName":1121,"installMethods":1122,"rationale":1123,"selectedPaths":1124,"source":347,"sourceLanguage":18,"type":268},"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",[1125,1126],{"path":570,"priority":346},{"path":675,"priority":361},{"basePath":289,"description":1128,"displayName":1129,"installMethods":1130,"rationale":1131,"selectedPaths":1132,"source":347,"sourceLanguage":18,"type":221},"Official Compound Engineering plugin for Claude Code, Codex, and more","@every-env/compound-plugin",{"npm":1129},"cli ecosystem detected at /",[1133,1135,1136,1137,1139,1141,1143,1145,1147],{"path":1134,"priority":346},"package.json",{"path":355,"priority":346},{"path":357,"priority":358},{"path":1138,"priority":361},"src/index.ts",{"path":1140,"priority":573},"src/commands/cleanup.ts",{"path":1142,"priority":573},"src/commands/convert.ts",{"path":1144,"priority":573},"src/commands/install.ts",{"path":1146,"priority":573},"src/commands/list.ts",{"path":1148,"priority":573},"src/commands/plugin-path.ts",{"sources":1150},[1151],"manual",{"npmPackage":1129},{"closedIssues90d":250,"description":1154,"forks":251,"homepage":1155,"license":258,"openIssues90d":252,"pushedAt":253,"readmeSize":248,"stars":254,"topics":1156},"Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more","https://every.to/guides/compound-engineering",[1157,1158],"compound","engineering",{"downloads":256},{"classifiedAt":1161,"discoverAt":1162,"extractAt":1163,"githubAt":1163,"npmAt":1164,"updatedAt":1161},1778686639998,1778686632796,1778686635929,1778686638203,[220,223,221,222,219],{"evaluatedAt":262,"extractAt":311,"updatedAt":262},[],[1169,1199,1224,1252,1271,1293],{"_creationTime":1170,"_id":1171,"community":1172,"display":1173,"identity":1179,"providers":1184,"relations":1191,"tags":1194,"workflow":1195},1778697373439.756,"k1735p8vnc44y3ntfepns5m0nx86npbs",{"reviewCount":8},{"description":1174,"installMethods":1175,"name":1177,"sourceUrl":1178},"Browser-automatisierungs-CLI für KI-Agenten. Verwenden Sie diese, wenn der Benutzer mit Websites interagieren muss, einschließlich der Navigation auf Seiten, dem Ausfüllen von Formularen, dem Klicken auf Schaltflächen, dem Aufnehmen von Screenshots, dem Extrahieren von Daten, dem Testen von Webanwendungen oder der Automatisierung beliebiger Browseraufgaben. Auslöser sind Anfragen wie \"öffne eine Website\", \"fülle ein Formular aus\", \"klicke auf eine Schaltfläche\", \"mache einen Screenshot\", \"scrappe Daten von einer Seite\", \"teste diese Web-App\", \"melde dich bei einer Seite an\", \"automatisiere Browser-Aktionen\" oder jede Aufgabe, die eine programmatische Webinteraktion erfordert.",{"claudeCode":1176},"shanraisshan/claude-code-best-practice","agent-browser","https://github.com/shanraisshan/claude-code-best-practice",{"basePath":1180,"githubOwner":1181,"githubRepo":1182,"locale":1183,"slug":1177,"type":268},".claude/skills/agent-browser","shanraisshan","claude-code-best-practice","de",{"evaluate":1185,"extract":1190},{"promptVersionExtension":212,"promptVersionScoring":213,"score":1186,"tags":1187,"targetMarket":224,"tier":225},100,[220,1188,219,221,1189],"web-scraping","automation",{"commitSha":301},{"repoId":1192,"translatedFrom":1193},"kd74710g49kxgwbfjxeb7s132d86myxr","k17ej9360g7468qswf3svnrx9186m1ng",[1189,220,221,219,1188],{"evaluatedAt":1196,"extractAt":1197,"updatedAt":1198},1778697222051,1778697205743,1778697373439,{"_creationTime":1200,"_id":1201,"community":1202,"display":1203,"identity":1209,"providers":1213,"relations":1218,"tags":1220,"workflow":1221},1778697652123.8857,"k179k1n5nw0md1x1j3dak31evn86mb5f",{"reviewCount":8},{"description":1204,"installMethods":1205,"name":1207,"sourceUrl":1208},"Use when reviewing, reproducing, or proving OpenClaw Telegram behavior with a real Telegram user on Crabbox, including PR review workflows that need an agent-controlled Telegram Desktop recording, TDLib user-driver commands, Convex-leased credentials, WebVNC observation, and motion-trimmed artifacts.",{"claudeCode":1206},"steipete/clawdis","telegram-crabbox-e2e-proof","https://github.com/steipete/clawdis",{"basePath":1210,"githubOwner":1211,"githubRepo":1212,"locale":18,"slug":1207,"type":268},".agents/skills/telegram-crabbox-e2e-proof","steipete","clawdis",{"evaluate":1214,"extract":1217},{"promptVersionExtension":212,"promptVersionScoring":213,"score":1186,"tags":1215,"targetMarket":224,"tier":225},[219,1216,1189,222,221],"telegram",{"commitSha":301},{"repoId":1219},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[1189,221,222,1216,219],{"evaluatedAt":1222,"extractAt":1223,"updatedAt":1222},1778698038113,1778697652123,{"_creationTime":1225,"_id":1226,"community":1227,"display":1228,"identity":1234,"providers":1239,"relations":1245,"tags":1248,"workflow":1249},1778683460321.381,"k1707rtzme0qezretvp3gmtfvn86n1k1",{"reviewCount":8},{"description":1229,"installMethods":1230,"name":1232,"sourceUrl":1233},"Self-improving browser automation via the auto-research loop. Iteratively runs a browsing task, reads the trace, and improves the navigation skill (strategy.md) until it reliably passes. Supports parallel runs across multiple tasks using sub-agents. Use when you want to build or improve browser automation skills for specific website tasks.",{"claudeCode":1231},"browserbase/skills","AutoBrowse","https://github.com/browserbase/skills",{"basePath":1235,"githubOwner":1236,"githubRepo":1237,"locale":18,"slug":1238,"type":268},"skills/autobrowse","browserbase","skills","autobrowse",{"evaluate":1240,"extract":1244},{"promptVersionExtension":212,"promptVersionScoring":213,"score":1186,"tags":1241,"targetMarket":224,"tier":225},[220,1188,1242,219,1243],"llm-agent","node-js",{"commitSha":301,"license":258},{"parentExtensionId":1246,"repoId":1247},"k17bx77jb71yrwatep2nb43r0d86m6cb","kd77wvcdm5fq9xp8hk6ppm832s86myxr",[220,1242,1243,219,1188],{"evaluatedAt":1250,"extractAt":1251,"updatedAt":1250},1778683610531,1778683460321,{"_creationTime":1253,"_id":1254,"community":1255,"display":1256,"identity":1260,"providers":1262,"relations":1267,"tags":1268,"workflow":1269},1778697652123.8845,"k17bexjjjsz81ysk7bd3ggdm8s86mt2t",{"reviewCount":8},{"description":1257,"installMethods":1258,"name":1259,"sourceUrl":1208},"Choose, run, rerun, or debug OpenClaw tests, CI checks, Docker E2E lanes, release validation, and the cheapest safe verification path.",{"claudeCode":1206},"openclaw-testing",{"basePath":1261,"githubOwner":1211,"githubRepo":1212,"locale":18,"slug":1259,"type":268},".agents/skills/openclaw-testing",{"evaluate":1263,"extract":1266},{"promptVersionExtension":212,"promptVersionScoring":213,"score":1186,"tags":1264,"targetMarket":224,"tier":225},[219,223,1265,1189,317],"validation",{"commitSha":301},{"repoId":1219},[1189,223,317,219,1265],{"evaluatedAt":1270,"extractAt":1223,"updatedAt":1270},1778697962962,{"_creationTime":1272,"_id":1273,"community":1274,"display":1275,"identity":1279,"providers":1281,"relations":1289,"tags":1290,"workflow":1291},1778697652123.8806,"k17e99n8cb55vm23m26vec6r1586mrwe",{"reviewCount":8},{"description":1276,"installMethods":1277,"name":1278,"sourceUrl":1208},"Use Crabbox for OpenClaw remote validation across Linux, macOS, Windows, and WSL2. Default to Blacksmith Testbox for broad Linux proof; includes direct Blacksmith and owned AWS/Hetzner fallback notes when Crabbox fails.",{"claudeCode":1206},"crabbox",{"basePath":1280,"githubOwner":1211,"githubRepo":1212,"locale":18,"slug":1278,"type":268},".agents/skills/crabbox",{"evaluate":1282,"extract":1288},{"promptVersionExtension":212,"promptVersionScoring":213,"score":1186,"tags":1283,"targetMarket":224,"tier":225},[219,223,1284,1265,1285,1286,1287],"remote-execution","linux","macos","windows",{"commitSha":301},{"repoId":1219},[223,1285,1286,1284,219,1265,1287],{"evaluatedAt":1292,"extractAt":1223,"updatedAt":1292},1778697705804,{"_creationTime":1294,"_id":1295,"community":1296,"display":1297,"identity":1303,"providers":1306,"relations":1313,"tags":1316,"workflow":1317},1778695599741.503,"k1787ebt8mj81ysp5cz5307v1186nbbm",{"reviewCount":8},{"description":1298,"installMethods":1299,"name":1301,"sourceUrl":1302},"Nutzen Sie diese Skill, um Ihre Google NotebookLM-Notizbücher direkt von Claude Code aus abzufragen, für quellengestützte, zitationsgestützte Antworten von Gemini. Browser-Automatisierung, Bibliotheksverwaltung, persistente Authentifizierung. Drastisch reduzierte Halluzinationen durch reine Dokumentenantworten.",{"claudeCode":1300},"PleasePrompto/notebooklm-skill","NotebookLM Skill","https://github.com/PleasePrompto/notebooklm-skill",{"basePath":289,"githubOwner":1304,"githubRepo":1305,"locale":1183,"slug":1305,"type":268},"PleasePrompto","notebooklm-skill",{"evaluate":1307,"extract":1312},{"promptVersionExtension":212,"promptVersionScoring":213,"score":216,"tags":1308,"targetMarket":224,"tier":225},[1309,1310,298,318,222,220,1311],"notebooklm","google","python",{"commitSha":301,"license":258},{"repoId":1314,"translatedFrom":1315},"kd77gpjgrb75m8vdz999898gfx86nmyk","k17a2m4gyjvxe0gagyj92v85b986mdw8",[220,298,1310,1309,1311,222,318],{"evaluatedAt":1318,"extractAt":1319,"updatedAt":1320},1778695578542,1778695552536,1778695599741]