[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-garrytan-gstack-de":3,"guides-for-garrytan-gstack":881,"similar-k17d755jf6vrmx08w86ygys1ds86nm07-de":882},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":248,"isFallback":228,"parentExtension":252,"providers":253,"relations":258,"repo":260,"tags":878,"workflow":879},1778687183932.1838,"k17d755jf6vrmx08w86ygys1ds86nm07",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with\nelements, verify state, diff before/after, take annotated screenshots, test responsive\nlayouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or\ntest a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)\n",{"claudeCode":12},"garrytan/gstack","gstack","https://github.com/garrytan/gstack",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":226,"workflow":246},1778687210010.9211,"kn703xaywt1erkcy5yx6zcpk9d86mr0t","en",{"checks":20,"evaluatedAt":191,"extensionSummary":192,"features":193,"nonGoals":200,"promptVersionExtension":204,"promptVersionScoring":205,"purpose":206,"rationale":207,"score":208,"summary":209,"tags":210,"targetMarket":219,"tier":220,"useCases":221},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,89,93,97,101,105,108,111,114,118,121,124,127,130,133,136,140,144,148,152,156,159,162,165,168,172,175,178,181,184,188],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the extension's purpose: providing a fast headless browser for QA testing and site dogfooding, and outlines specific use cases like testing responsive layouts and filing bugs.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The extension offers significant value over a simple prompt by providing a dedicated, fast headless browser with specialized commands for interaction, verification, and visual capture, going beyond basic browser automation.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The extension appears production-ready, bundling all necessary components for its stated use cases, including navigation, interaction, state verification, and visual capture, covering a complete lifecycle for testing.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The extension focuses on headless browser automation for testing and QA, with a coherent set of tools that all serve this primary domain.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description is concise, readable, and accurately reflects the extension's capabilities as a fast headless browser for QA and dogfooding.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The extension exposes narrow, verb-noun specialized tools like 'goto', 'click', 'snapshot', and 'text', which are easy for the agent to select and reduce attack surface.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","The extensive command reference in BROWSER.md and SKILL.md details all options, parameters, and usage patterns, including interactive elements via '@ref' selectors.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","Tool names like 'goto', 'snapshot', 'click', 'fill', and 'responsive' are descriptive and clearly indicate their function within the domain of browser automation.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","Tools request specific data as needed (e.g., URL for 'goto', selector for 'click') and return focused payloads like text, JSON attributes, or image files without extraneous diagnostic dumps.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The extension is licensed under MIT, a permissive open-source license, as indicated by the bundled LICENSE file.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The repository shows recent commits within the last 3 months, indicating active maintenance.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","The extension appears to use Bun and Playwright, which are standard dependencies managed through package.json and Bun's ecosystem, with measures like version pinning likely in place.",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","Secrets like API keys or browser cookies are handled via environment variables or secure import processes, and the documentation explicitly warns against handling secrets insecurely. The README also warns about cookie safety during import.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","The tool uses Playwright's accessibility tree and ref-based selectors, avoiding DOM manipulation. Untrusted content from web pages is wrapped in markers, and URLs are sanitized, indicating a defense against injection.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","The extension relies on Playwright and Bun, standard, well-vetted dependencies. Runtime downloads are not apparent, and all content appears to stay within the bundled repository or trusted external resources like CDNs for fonts.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","The browse binary operates within its own Chromium context, and standard file paths are relative or managed by Playwright/Bun. No indication of operations outside of expected scopes or direct file system manipulation outside the extension's bundle.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","The codebase and documentation do not reveal any use of detached-process spawns, retry loops around denied calls, or background child processes that could facilitate sandbox escapes.",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","The extension's purpose is browser automation for testing; there are no indications of instructions to read and submit confidential data to third parties. Outbound calls for analytics are opt-in, and documentation is transparent about telemetry.",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","Bundled content appears to be standard JavaScript/TypeScript and Markdown without hidden text tricks, Unicode tags, or bidi overrides designed to steer the model.",{"category":65,"check":87,"severity":24,"summary":88},"Opaque code execution","The extension uses standard TypeScript compilation via Bun, with source maps potentially available for debugging. There's no evidence of base64-encoded payloads, eval(), or minified code without source maps.",{"category":90,"check":91,"severity":24,"summary":92},"Portability","Structural Assumption","The use of Playwright and Bun, along with standard file paths like \b$HOME/.claude/skills/gstack/\b or \b$HOME/.gstack/\b, suggests good portability across standard environments. The setup script handles different OS needs.",{"category":94,"check":95,"severity":24,"summary":96},"Trust","Issues Attention","With 203 open issues and 194 closed issues in 90 days, the closure rate is high and maintainer engagement appears active, suggesting responsiveness to issues.",{"category":98,"check":99,"severity":24,"summary":100},"Versioning","Release Management","The extension clearly signals its version via the \bversion: 1.1.0\b field in SKILL.md frontmatter and recent commit activity, providing a stable versioning signal.",{"category":102,"check":103,"severity":24,"summary":104},"Code Execution","Validation","The extension utilizes Playwright for browser interactions and likely employs robust validation for inputs like URLs and selectors. The command reference suggests strict argument parsing.",{"category":65,"check":106,"severity":24,"summary":107},"Unguarded Destructive Operations","The extension focuses on browser automation for testing and does not expose destructive primitives like \brm -rf\b or direct file system modifications outside its intended scope.",{"category":102,"check":109,"severity":24,"summary":110},"Error Handling","The BROWSER.md and SKILL.md documentation implies robust error handling, with clear messages for timeouts and failed steps, guiding the agent on recovery.",{"category":102,"check":112,"severity":24,"summary":113},"Logging","The extension uses a ring-buffer system for console, network, and dialog logs, flushing asynchronously to disk. This captures audit records per invocation without blocking execution and is opt-in for telemetry.",{"category":115,"check":116,"severity":24,"summary":117},"Compliance","GDPR","The extension operates on web pages and states it handles cookies securely. There's no indication of direct handling or submission of personal data beyond what is inherent to browsing a site.",{"category":115,"check":119,"severity":24,"summary":120},"Target market","The extension's functionality is tied to browser automation and testing, which is globally applicable. No regional or jurisdictional restrictions are apparent, and the target market is implicitly global.",{"category":90,"check":122,"severity":24,"summary":123},"Runtime stability","The extension is built using Bun and Playwright, cross-platform runtimes. It uses standard commands and aims for portability, with specific notes on Windows support.",{"category":44,"check":125,"severity":24,"summary":126},"README","The README is extensive, detailing the project's philosophy, installation, usage, and underlying architecture, clearly stating the extension's purpose and value proposition.",{"category":33,"check":128,"severity":24,"summary":129},"Tool surface size","The extension exposes a rich set of over 70 commands, which is extensive but organized logically within categories, striking a balance between power and usability.",{"category":40,"check":131,"severity":24,"summary":132},"Overlapping near-synonym tools","Tool names are generally distinct and clearly named (e.g., goto, click, fill, snapshot). No obvious near-synonyms are present that would cause confusion for the agent.",{"category":44,"check":134,"severity":24,"summary":135},"Phantom features","All advertised features, from core commands like 'goto' and 'snapshot' to advanced ones like 'pair-agent' and security features, appear to have corresponding implementations detailed in the documentation.",{"category":137,"check":138,"severity":24,"summary":139},"Install","Installation instruction","The README provides clear, copy-pasteable installation instructions, including requirements and optional team mode setup, along with detailed usage examples for various workflows.",{"category":141,"check":142,"severity":24,"summary":143},"Errors","Actionable error messages","The BROWSER.md and SKILL.md documentation indicates that errors are designed to be actionable, providing context and often suggesting remediation steps to the agent.",{"category":145,"check":146,"severity":24,"summary":147},"Execution","Pinned dependencies","The use of Bun and Playwright, along with the self-contained nature of browser-skills, suggests dependencies are managed and likely pinned, ensuring reproducible builds.",{"category":33,"check":149,"severity":150,"summary":151},"Dry-run preview","not_applicable","The extension is primarily focused on browser interactions rather than state-changing commands that would typically benefit from a dry-run mode. Its operations are generally non-destructive.",{"category":153,"check":154,"severity":24,"summary":155},"Protocol","Idempotent retry & timeouts","While not all operations may be strictly idempotent, the system includes features like automatic server restarts on crash and timeout handling for Playwright operations, providing resilience.",{"category":115,"check":157,"severity":24,"summary":158},"Telemetry opt-in","The extension's telemetry is explicitly opt-in, documented transparently, and respects user configuration for disabling it.",{"category":40,"check":160,"severity":24,"summary":161},"Precise Purpose","The skill's purpose is precisely defined as a fast headless browser for QA and dogfooding, with clear triggers and use cases provided in the frontmatter.",{"category":40,"check":163,"severity":24,"summary":164},"Concise Frontmatter","The frontmatter is dense but self-contained, providing a clear summary of core capabilities and triggers without excessive keywords or verbosity.",{"category":44,"check":166,"severity":24,"summary":167},"Concise Body","The SKILL.md body is well-structured and delegates deeper material to separate files like BROWSER.md, practicing progressive disclosure.",{"category":169,"check":170,"severity":24,"summary":171},"Context","Progressive Disclosure","The SKILL.md file outlines the main workflow and links to BROWSER.md for detailed command references, effectively managing complexity.",{"category":169,"check":173,"severity":150,"summary":174},"Forked exploration","The extension does not appear to involve heavy exploration or deep code review that would necessitate the 'context: fork' setting.",{"category":22,"check":176,"severity":24,"summary":177},"Usage examples","The SKILL.md and BROWSER.md files provide numerous end-to-end examples for various QA workflows, demonstrating inputs, invocations, and expected outcomes.",{"category":22,"check":179,"severity":24,"summary":180},"Edge cases","The documentation acknowledges potential issues like stale refs, browser downtime, and user-interaction blocking dialogs, implicitly handling them or providing guidance.",{"category":102,"check":182,"severity":150,"summary":183},"Tool Fallback","The extension appears to be self-contained and does not rely on external MCP servers that would require fallbacks.",{"category":185,"check":186,"severity":24,"summary":187},"Safety","Halt on unexpected state","The documentation implicitly guides the agent to halt workflows if preconditions are not met (e.g., needing to re-run snapshot after navigation) and offers recovery steps like using `handoff`.",{"category":90,"check":189,"severity":24,"summary":190},"Cross-skill coupling","The extension is designed as a standalone tool. While it integrates with Claude Code's skill system, it does not appear to implicitly rely on other specific gstack skills being loaded concurrently.",1778687209073,"This extension provides a fast, persistent headless Chromium browser controlled via a CLI, enabling detailed QA testing, site dogfooding, and automated interaction with web pages.",[194,195,196,197,198,199],"Fast headless browser automation","Interactive element navigation and manipulation","State verification and diffing","Annotated screenshots and responsive layout testing","Form testing, file uploads, and dialog handling","Cross-browser cookie import and authenticated session testing",[201,202,203],"Replacing the agent's judgment with automated decisions","Performing extensive load testing or performance benchmarking (though basic metrics are available)","Acting as a general-purpose web scraping tool outside of the testing context","3.0.0","4.4.0","To provide AI agents with robust, low-latency browser automation capabilities for testing, QA, and development workflows.","The extension is exceptionally well-documented and robust, with a clear purpose, specialized tools, and strong security and portability considerations. The documentation is extensive and provides numerous practical examples. Active maintenance and a large community indicate high quality and reliability.",98,"A powerful and well-documented headless browser tool for comprehensive QA testing and site dogfooding.",[211,212,213,214,215,216,217,218],"browser","testing","qa","automation","headless","puppeteer","playwright","devtools","global","verified",[222,223,224,225],"Testing user flows like login, signup, and checkout","Verifying deployments and checking production sites","Dogfooding new features end-to-end","Filing bug reports with visual evidence and console logs",{"codeQuality":227,"collectedAt":229,"documentation":230,"maintenance":233,"popularity":241,"security":243,"testCoverage":245},{"hasLockfile":228},true,1778687194898,{"descriptionLength":231,"readmeSize":232},357,40680,{"closedIssues90d":234,"forks":235,"hasChangelog":236,"manifestVersion":237,"openIssues90d":238,"pushedAt":239,"stars":240},194,14166,false,"1.1.0",203,1778685252000,95479,{"npmDownloads":242},5893,{"hasNpmPackage":228,"license":244,"smitheryVerified":236},"MIT",{"hasCi":228,"hasTests":228},{"updatedAt":247},1778687210010,{"basePath":249,"githubOwner":250,"githubRepo":13,"locale":18,"slug":13,"type":251},"","garrytan","skill",null,{"evaluate":254,"extract":256},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":255,"targetMarket":219,"tier":220},[211,212,213,214,215,216,217,218],{"commitSha":257},"HEAD",{"repoId":259},"kd73s35xh97m9mmc5nz3pb1f3n86m0an",{"_creationTime":261,"_id":259,"identity":262,"providers":263,"workflow":873},1778687174845.1123,{"githubOwner":250,"githubRepo":13,"sourceUrl":14},{"classify":264,"discover":865,"extract":868,"github":869,"npm":872},{"commitSha":257,"extensions":265},[266,507,514,521,528,539,547,554,561,568,575,582,591,598,605,612,619,626,633,640,647,654,661,668,675,682,689,696,703,711,719,727,735,742,751,758,765,775,782,789,804,811,818,825,834,841,848,855],{"basePath":249,"description":10,"displayName":13,"installMethods":267,"rationale":268,"selectedPaths":269,"source":506,"sourceLanguage":18,"type":251},{"claudeCode":12},"SKILL.md frontmatter at SKILL.md",[270,273,276,278,281,283,285,287,289,291,293,295,297,299,302,304,306,308,310,312,314,316,318,320,322,324,326,328,330,332,334,336,338,340,342,344,346,348,350,352,354,356,358,360,362,364,366,368,370,372,374,376,378,380,382,384,386,388,390,392,394,396,398,400,402,404,406,408,410,412,414,416,418,420,422,424,426,428,430,432,434,436,438,440,442,444,446,448,450,452,454,456,458,460,462,464,466,468,470,472,474,476,478,480,482,484,486,488,490,492,494,496,498,500,502,504],{"path":271,"priority":272},"SKILL.md","mandatory",{"path":274,"priority":275},"README.md","high",{"path":277,"priority":275},"LICENSE",{"path":279,"priority":280},"AGENTS.md","medium",{"path":282,"priority":280},"ARCHITECTURE.md",{"path":284,"priority":280},"BROWSER.md",{"path":286,"priority":280},"CHANGELOG.md",{"path":288,"priority":280},"CLAUDE.md",{"path":290,"priority":280},"CONTRIBUTING.md",{"path":292,"priority":280},"DESIGN.md",{"path":294,"priority":280},"ETHOS.md",{"path":296,"priority":280},"TODOS.md",{"path":298,"priority":280},"USING_GBRAIN_WITH_GSTACK.md",{"path":300,"priority":301},"docs/ADDING_A_HOST.md","low",{"path":303,"priority":301},"docs/ON_THE_LOC_CONTROVERSY.md",{"path":305,"priority":301},"docs/OPENCLAW.md",{"path":307,"priority":301},"docs/REMOTE_BROWSER_ACCESS.md",{"path":309,"priority":301},"docs/designs/BROWSER_SKILLS_V1.md",{"path":311,"priority":301},"docs/designs/BUN_NATIVE_INFERENCE.md",{"path":313,"priority":301},"docs/designs/CHROME_VS_CHROMIUM_EXPLORATION.md",{"path":315,"priority":301},"docs/designs/CONDUCTOR_CHROME_SIDEBAR_INTEGRATION.md",{"path":317,"priority":301},"docs/designs/CONDUCTOR_SESSION_API.md",{"path":319,"priority":301},"docs/designs/DESIGN_SHOTGUN.md",{"path":321,"priority":301},"docs/designs/DESIGN_TOOLS_V1.md",{"path":323,"priority":301},"docs/designs/GCOMPACTION.md",{"path":325,"priority":301},"docs/designs/GSTACK_BROWSER_V0.md",{"path":327,"priority":301},"docs/designs/ML_PROMPT_INJECTION_KILLER.md",{"path":329,"priority":301},"docs/designs/PACING_UPDATES_V0.md",{"path":331,"priority":301},"docs/designs/PLAN_TUNING_V0.md",{"path":333,"priority":301},"docs/designs/PLAN_TUNING_V1.md",{"path":335,"priority":301},"docs/designs/SELF_LEARNING_V0.md",{"path":337,"priority":301},"docs/designs/SESSION_INTELLIGENCE.md",{"path":339,"priority":301},"docs/designs/SIDEBAR_MESSAGE_FLOW.md",{"path":341,"priority":301},"docs/designs/SLATE_HOST.md",{"path":343,"priority":301},"docs/designs/SLOP_SCAN_FOR_REVIEW_SHIP.md",{"path":345,"priority":301},"docs/designs/SYNC_GBRAIN_BATCH_INGEST.md",{"path":347,"priority":301},"docs/domain-skills.md",{"path":349,"priority":301},"docs/evals/security-bench-ensemble-v2.json",{"path":351,"priority":301},"docs/gbrain-sync-errors.md",{"path":353,"priority":301},"docs/gbrain-sync.md",{"path":355,"priority":301},"docs/images/github-2013.png",{"path":357,"priority":301},"docs/images/github-2026.png",{"path":359,"priority":301},"docs/skills.md",{"path":361,"priority":301},"scripts/analytics.ts",{"path":363,"priority":301},"scripts/app/gstack-browser",{"path":365,"priority":301},"scripts/app/icon.icns",{"path":367,"priority":301},"scripts/archetypes.ts",{"path":369,"priority":301},"scripts/build-app.sh",{"path":371,"priority":301},"scripts/compare-pr-version.ts",{"path":373,"priority":301},"scripts/detect-bump.ts",{"path":375,"priority":301},"scripts/dev-skill.ts",{"path":377,"priority":301},"scripts/discover-skills.ts",{"path":379,"priority":301},"scripts/eval-compare.ts",{"path":381,"priority":301},"scripts/eval-list.ts",{"path":383,"priority":301},"scripts/eval-select.ts",{"path":385,"priority":301},"scripts/eval-summary.ts",{"path":387,"priority":301},"scripts/eval-watch.ts",{"path":389,"priority":301},"scripts/garry-output-comparison.ts",{"path":391,"priority":301},"scripts/gen-llms-txt.ts",{"path":393,"priority":301},"scripts/gen-skill-docs.ts",{"path":395,"priority":301},"scripts/host-adapters/openclaw-adapter.ts",{"path":397,"priority":301},"scripts/host-config-export.ts",{"path":399,"priority":301},"scripts/host-config.ts",{"path":401,"priority":301},"scripts/jargon-list.json",{"path":403,"priority":301},"scripts/models.ts",{"path":405,"priority":301},"scripts/one-way-doors.ts",{"path":407,"priority":301},"scripts/preflight-agent-sdk.ts",{"path":409,"priority":301},"scripts/psychographic-signals.ts",{"path":411,"priority":301},"scripts/question-registry.ts",{"path":413,"priority":301},"scripts/resolvers/browse.ts",{"path":415,"priority":301},"scripts/resolvers/codex-helpers.ts",{"path":417,"priority":301},"scripts/resolvers/composition.ts",{"path":419,"priority":301},"scripts/resolvers/confidence.ts",{"path":421,"priority":301},"scripts/resolvers/constants.ts",{"path":423,"priority":301},"scripts/resolvers/design.ts",{"path":425,"priority":301},"scripts/resolvers/dx.ts",{"path":427,"priority":301},"scripts/resolvers/gbrain.ts",{"path":429,"priority":301},"scripts/resolvers/index.ts",{"path":431,"priority":301},"scripts/resolvers/learnings.ts",{"path":433,"priority":301},"scripts/resolvers/make-pdf.ts",{"path":435,"priority":301},"scripts/resolvers/model-overlay.ts",{"path":437,"priority":301},"scripts/resolvers/preamble/generate-ask-user-format.ts",{"path":439,"priority":301},"scripts/resolvers/preamble/generate-brain-health-instruction.ts",{"path":441,"priority":301},"scripts/resolvers/preamble/generate-brain-sync-block.ts",{"path":443,"priority":301},"scripts/resolvers/preamble/generate-completeness-section.ts",{"path":445,"priority":301},"scripts/resolvers/preamble/generate-completion-status.ts",{"path":447,"priority":301},"scripts/resolvers/preamble/generate-confusion-protocol.ts",{"path":449,"priority":301},"scripts/resolvers/preamble/generate-context-health.ts",{"path":451,"priority":301},"scripts/resolvers/preamble/generate-context-recovery.ts",{"path":453,"priority":301},"scripts/resolvers/preamble/generate-continuous-checkpoint.ts",{"path":455,"priority":301},"scripts/resolvers/preamble/generate-lake-intro.ts",{"path":457,"priority":301},"scripts/resolvers/preamble/generate-preamble-bash.ts",{"path":459,"priority":301},"scripts/resolvers/preamble/generate-proactive-prompt.ts",{"path":461,"priority":301},"scripts/resolvers/preamble/generate-repo-mode-section.ts",{"path":463,"priority":301},"scripts/resolvers/preamble/generate-routing-injection.ts",{"path":465,"priority":301},"scripts/resolvers/preamble/generate-search-before-building.ts",{"path":467,"priority":301},"scripts/resolvers/preamble/generate-spawned-session-check.ts",{"path":469,"priority":301},"scripts/resolvers/preamble/generate-telemetry-prompt.ts",{"path":471,"priority":301},"scripts/resolvers/preamble/generate-test-failure-triage.ts",{"path":473,"priority":301},"scripts/resolvers/preamble/generate-upgrade-check.ts",{"path":475,"priority":301},"scripts/resolvers/preamble/generate-vendoring-deprecation.ts",{"path":477,"priority":301},"scripts/resolvers/preamble/generate-voice-directive.ts",{"path":479,"priority":301},"scripts/resolvers/preamble/generate-writing-style-migration.ts",{"path":481,"priority":301},"scripts/resolvers/preamble/generate-writing-style.ts",{"path":483,"priority":301},"scripts/resolvers/preamble.ts",{"path":485,"priority":301},"scripts/resolvers/question-tuning.ts",{"path":487,"priority":301},"scripts/resolvers/review-army.ts",{"path":489,"priority":301},"scripts/resolvers/review.ts",{"path":491,"priority":301},"scripts/resolvers/testing.ts",{"path":493,"priority":301},"scripts/resolvers/types.ts",{"path":495,"priority":301},"scripts/resolvers/utility.ts",{"path":497,"priority":301},"scripts/setup-scc.sh",{"path":499,"priority":301},"scripts/skill-check.ts",{"path":501,"priority":301},"scripts/slop-diff.ts",{"path":503,"priority":301},"scripts/test-free-shards.ts",{"path":505,"priority":301},"scripts/update-readme-throughput.ts","rule",{"basePath":508,"description":509,"displayName":508,"installMethods":510,"rationale":511,"selectedPaths":512,"source":506,"sourceLanguage":18,"type":251},"autoplan","Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk\nand runs them sequentially with auto-decisions using 6 decision principles. Surfaces\ntaste decisions (close approaches, borderline scope, codex disagreements) at a final\napproval gate. One command, fully reviewed plan out.\nUse when asked to \"auto review\", \"autoplan\", \"run all reviews\", \"review this plan\nautomatically\", or \"make the decisions for me\".\nProactively suggest when the user has a plan file and wants to run the full review\ngauntlet without answering 15-30 intermediate questions. (gstack)\nVoice triggers (speech-to-text aliases): \"auto plan\", \"automatic review\".\n",{"claudeCode":12},"SKILL.md frontmatter at autoplan/SKILL.md",[513],{"path":271,"priority":272},{"basePath":515,"description":516,"displayName":515,"installMethods":517,"rationale":518,"selectedPaths":519,"source":506,"sourceLanguage":18,"type":251},"benchmark","Performance regression detection using the browse daemon. Establishes\nbaselines for page load times, Core Web Vitals, and resource sizes.\nCompares before/after on every PR. Tracks performance trends over time.\nUse when: \"performance\", \"benchmark\", \"page speed\", \"lighthouse\", \"web vitals\",\n\"bundle size\", \"load time\". (gstack)\nVoice triggers (speech-to-text aliases): \"speed test\", \"check performance\".\n",{"claudeCode":12},"SKILL.md frontmatter at benchmark/SKILL.md",[520],{"path":271,"priority":272},{"basePath":522,"description":523,"displayName":522,"installMethods":524,"rationale":525,"selectedPaths":526,"source":506,"sourceLanguage":18,"type":251},"benchmark-models","Cross-model benchmark for gstack skills. Runs the same prompt through Claude,\nGPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost,\nand optionally quality via LLM judge. Answers \"which model is actually best\nfor this skill?\" with data instead of vibes. Separate from /benchmark, which\nmeasures web page performance. Use when: \"benchmark models\", \"compare models\",\n\"which model is best for X\", \"cross-model comparison\", \"model shootout\". (gstack)\nVoice triggers (speech-to-text aliases): \"compare models\", \"model shootout\", \"which model is best\".\n",{"claudeCode":12},"SKILL.md frontmatter at benchmark-models/SKILL.md",[527],{"path":271,"priority":272},{"basePath":529,"description":530,"displayName":529,"installMethods":531,"rationale":532,"selectedPaths":533,"source":506,"sourceLanguage":18,"type":251},"browse","Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with\nelements, verify page state, diff before/after actions, take annotated screenshots, check\nresponsive layouts, test forms and uploads, handle dialogs, and assert element states.\n~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a\nuser flow, or file a bug with evidence. Use when asked to \"open in browser\", \"test the\nsite\", \"take a screenshot\", or \"dogfood this\". (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at browse/SKILL.md",[534,535,537],{"path":271,"priority":272},{"path":536,"priority":280},"PLAN-snapshot-dropdown-interactive.md",{"path":538,"priority":301},"scripts/build-node-server.sh",{"basePath":540,"description":541,"displayName":542,"installMethods":543,"rationale":544,"selectedPaths":545,"source":506,"sourceLanguage":18,"type":251},"browser-skills/hackernews-frontpage","Scrape the Hacker News front page (titles, points, comment counts).","hackernews-frontpage",{"claudeCode":12},"SKILL.md frontmatter at browser-skills/hackernews-frontpage/SKILL.md",[546],{"path":271,"priority":272},{"basePath":548,"description":549,"displayName":548,"installMethods":550,"rationale":551,"selectedPaths":552,"source":506,"sourceLanguage":18,"type":251},"canary","Post-deploy canary monitoring. Watches the live app for console errors,\nperformance regressions, and page failures using the browse daemon. Takes\nperiodic screenshots, compares against pre-deploy baselines, and alerts\non anomalies. Use when: \"monitor deploy\", \"canary\", \"post-deploy check\",\n\"watch production\", \"verify deploy\". (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at canary/SKILL.md",[553],{"path":271,"priority":272},{"basePath":555,"description":556,"displayName":555,"installMethods":557,"rationale":558,"selectedPaths":559,"source":506,"sourceLanguage":18,"type":251},"careful","Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE,\nforce-push, git reset --hard, kubectl delete, and similar destructive operations.\nUser can override each warning. Use when touching prod, debugging live systems,\nor working in a shared environment. Use when asked to \"be careful\", \"safety mode\",\n\"prod mode\", or \"careful mode\". (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at careful/SKILL.md",[560],{"path":271,"priority":272},{"basePath":562,"description":563,"displayName":562,"installMethods":564,"rationale":565,"selectedPaths":566,"source":506,"sourceLanguage":18,"type":251},"codex","OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via\ncodex review with pass/fail gate. Challenge: adversarial mode that tries to break\nyour code. Consult: ask codex anything with session continuity for follow-ups.\nThe \"200 IQ autistic developer\" second opinion. Use when asked to \"codex review\",\n\"codex challenge\", \"ask codex\", \"second opinion\", or \"consult codex\". (gstack)\nVoice triggers (speech-to-text aliases): \"code x\", \"code ex\", \"get another opinion\".\n",{"claudeCode":12},"SKILL.md frontmatter at codex/SKILL.md",[567],{"path":271,"priority":272},{"basePath":569,"description":570,"displayName":569,"installMethods":571,"rationale":572,"selectedPaths":573,"source":506,"sourceLanguage":18,"type":251},"context-restore","Restore working context saved earlier by /context-save. Loads the most recent\nsaved state (across all branches by default) so you can pick up where you\nleft off — even across Conductor workspace handoffs.\nUse when asked to \"resume\", \"restore context\", \"where was I\", or\n\"pick up where I left off\". Pair with /context-save.\nFormerly /checkpoint resume — renamed because Claude Code treats /checkpoint\nas a native rewind alias in current environments. (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at context-restore/SKILL.md",[574],{"path":271,"priority":272},{"basePath":576,"description":577,"displayName":576,"installMethods":578,"rationale":579,"selectedPaths":580,"source":506,"sourceLanguage":18,"type":251},"context-save","Save working context. Captures git state, decisions made, and remaining work\nso any future session can pick up without losing a beat.\nUse when asked to \"save progress\", \"save state\", \"context save\", or\n\"save my work\". Pair with /context-restore to resume later.\nFormerly /checkpoint — renamed because Claude Code treats /checkpoint as a\nnative rewind alias in current environments, which was shadowing this skill.\n(gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at context-save/SKILL.md",[581],{"path":271,"priority":272},{"basePath":583,"description":584,"displayName":583,"installMethods":585,"rationale":586,"selectedPaths":587,"source":506,"sourceLanguage":18,"type":251},"cso","Chief Security Officer mode. Infrastructure-first security audit: secrets archaeology,\ndependency supply chain, CI/CD pipeline security, LLM/AI security, skill supply chain\nscanning, plus OWASP Top 10, STRIDE threat modeling, and active verification.\nTwo modes: daily (zero-noise, 8/10 confidence gate) and comprehensive (monthly deep\nscan, 2/10 bar). Trend tracking across audit runs.\nUse when: \"security audit\", \"threat model\", \"pentest review\", \"OWASP\", \"CSO review\". (gstack)\nVoice triggers (speech-to-text aliases): \"see-so\", \"see so\", \"security review\", \"security check\", \"vulnerability scan\", \"run security\".\n",{"claudeCode":12},"SKILL.md frontmatter at cso/SKILL.md",[588,589],{"path":271,"priority":272},{"path":590,"priority":280},"ACKNOWLEDGEMENTS.md",{"basePath":592,"description":593,"displayName":592,"installMethods":594,"rationale":595,"selectedPaths":596,"source":506,"sourceLanguage":18,"type":251},"design-consultation","Design consultation: understands your product, researches the landscape, proposes a\ncomplete design system (aesthetic, typography, color, layout, spacing, motion), and\ngenerates font+color preview pages. Creates DESIGN.md as your project's design source\nof truth. For existing sites, use /plan-design-review to infer the system instead.\nUse when asked to \"design system\", \"brand guidelines\", or \"create DESIGN.md\".\nProactively suggest when starting a new project's UI with no existing\ndesign system or DESIGN.md. (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at design-consultation/SKILL.md",[597],{"path":271,"priority":272},{"basePath":599,"description":600,"displayName":599,"installMethods":601,"rationale":602,"selectedPaths":603,"source":506,"sourceLanguage":18,"type":251},"design-html","Design finalization: generates production-quality Pretext-native HTML/CSS.\nWorks with approved mockups from /design-shotgun, CEO plans from /plan-ceo-review,\ndesign review context from /plan-design-review, or from scratch with a user\ndescription. Text actually reflows, heights are computed, layouts are dynamic.\n30KB overhead, zero deps. Smart API routing: picks the right Pretext patterns\nfor each design type. Use when: \"finalize this design\", \"turn this into HTML\",\n\"build me a page\", \"implement this design\", or after any planning skill.\nProactively suggest when user has approved a design or has a plan ready. (gstack)\nVoice triggers (speech-to-text aliases): \"build the design\", \"code the mockup\", \"make it real\".\n",{"claudeCode":12},"SKILL.md frontmatter at design-html/SKILL.md",[604],{"path":271,"priority":272},{"basePath":606,"description":607,"displayName":606,"installMethods":608,"rationale":609,"selectedPaths":610,"source":506,"sourceLanguage":18,"type":251},"design-review","Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems,\nAI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues\nin source code, committing each fix atomically and re-verifying with before/after\nscreenshots. For plan-mode design review (before implementation), use /plan-design-review.\nUse when asked to \"audit the design\", \"visual QA\", \"check if it looks good\", or \"design polish\".\nProactively suggest when the user mentions visual inconsistencies or\nwants to polish the look of a live site. (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at design-review/SKILL.md",[611],{"path":271,"priority":272},{"basePath":613,"description":614,"displayName":613,"installMethods":615,"rationale":616,"selectedPaths":617,"source":506,"sourceLanguage":18,"type":251},"design-shotgun","Design shotgun: generate multiple AI design variants, open a comparison board,\ncollect structured feedback, and iterate. Standalone design exploration you can\nrun anytime. Use when: \"explore designs\", \"show me options\", \"design variants\",\n\"visual brainstorm\", or \"I don't like how this looks\".\nProactively suggest when the user describes a UI feature but hasn't seen\nwhat it could look like. (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at design-shotgun/SKILL.md",[618],{"path":271,"priority":272},{"basePath":620,"description":621,"displayName":620,"installMethods":622,"rationale":623,"selectedPaths":624,"source":506,"sourceLanguage":18,"type":251},"devex-review","Live developer experience audit. Uses the browse tool to actually TEST the\ndeveloper experience: navigates docs, tries the getting started flow, times\nTTHW, screenshots error messages, evaluates CLI help text. Produces a DX\nscorecard with evidence. Compares against /plan-devex-review scores if they\nexist (the boomerang: plan said 3 minutes, reality says 8). Use when asked to\n\"test the DX\", \"DX audit\", \"developer experience test\", or \"try the\nonboarding\". Proactively suggest after shipping a developer-facing feature. (gstack)\nVoice triggers (speech-to-text aliases): \"dx audit\", \"test the developer experience\", \"try the onboarding\", \"developer experience test\".\n",{"claudeCode":12},"SKILL.md frontmatter at devex-review/SKILL.md",[625],{"path":271,"priority":272},{"basePath":627,"description":628,"displayName":627,"installMethods":629,"rationale":630,"selectedPaths":631,"source":506,"sourceLanguage":18,"type":251},"document-release","Post-ship documentation update. Reads all project docs, cross-references the\ndiff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped,\npolishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION. Use when\nasked to \"update the docs\", \"sync documentation\", or \"post-ship docs\".\nProactively suggest after a PR is merged or code is shipped. (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at document-release/SKILL.md",[632],{"path":271,"priority":272},{"basePath":634,"description":635,"displayName":634,"installMethods":636,"rationale":637,"selectedPaths":638,"source":506,"sourceLanguage":18,"type":251},"freeze","Restrict file edits to a specific directory for the session. Blocks Edit and\nWrite outside the allowed path. Use when debugging to prevent accidentally\n\"fixing\" unrelated code, or when you want to scope changes to one module.\nUse when asked to \"freeze\", \"restrict edits\", \"only edit this folder\",\nor \"lock down edits\". (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at freeze/SKILL.md",[639],{"path":271,"priority":272},{"basePath":641,"description":642,"displayName":641,"installMethods":643,"rationale":644,"selectedPaths":645,"source":506,"sourceLanguage":18,"type":251},"gstack-upgrade","Upgrade gstack to the latest version. Detects global vs vendored install,\nruns the upgrade, and shows what's new. Use when asked to \"upgrade gstack\",\n\"update gstack\", or \"get latest version\".\nVoice triggers (speech-to-text aliases): \"upgrade the tools\", \"update the tools\", \"gee stack upgrade\", \"g stack upgrade\".\n",{"claudeCode":12},"SKILL.md frontmatter at gstack-upgrade/SKILL.md",[646],{"path":271,"priority":272},{"basePath":648,"description":649,"displayName":648,"installMethods":650,"rationale":651,"selectedPaths":652,"source":506,"sourceLanguage":18,"type":251},"guard","Full safety mode: destructive command warnings + directory-scoped edits.\nCombines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with\n/freeze (blocks edits outside a specified directory). Use for maximum safety\nwhen touching prod or debugging live systems. Use when asked to \"guard mode\",\n\"full safety\", \"lock it down\", or \"maximum safety\". (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at guard/SKILL.md",[653],{"path":271,"priority":272},{"basePath":655,"description":656,"displayName":655,"installMethods":657,"rationale":658,"selectedPaths":659,"source":506,"sourceLanguage":18,"type":251},"health","Code quality dashboard. Wraps existing project tools (type checker, linter,\ntest runner, dead code detector, shell linter), computes a weighted composite\n0-10 score, and tracks trends over time. Use when: \"health check\",\n\"code quality\", \"how healthy is the codebase\", \"run all checks\",\n\"quality score\". (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at health/SKILL.md",[660],{"path":271,"priority":272},{"basePath":662,"description":663,"displayName":662,"installMethods":664,"rationale":665,"selectedPaths":666,"source":506,"sourceLanguage":18,"type":251},"investigate","Systematic debugging with root cause investigation. Four phases: investigate,\nanalyze, hypothesize, implement. Iron Law: no fixes without root cause.\nUse when asked to \"debug this\", \"fix this bug\", \"why is this broken\",\n\"investigate this error\", or \"root cause analysis\".\nProactively invoke this skill (do NOT debug directly) when the user reports\nerrors, 500 errors, stack traces, unexpected behavior, \"it was working\nyesterday\", or is troubleshooting why something stopped working. (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at investigate/SKILL.md",[667],{"path":271,"priority":272},{"basePath":669,"description":670,"displayName":669,"installMethods":671,"rationale":672,"selectedPaths":673,"source":506,"sourceLanguage":18,"type":251},"land-and-deploy","Land and deploy workflow. Merges the PR, waits for CI and deploy,\nverifies production health via canary checks. Takes over after /ship\ncreates the PR. Use when: \"merge\", \"land\", \"deploy\", \"merge and verify\",\n\"land it\", \"ship it to production\". (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at land-and-deploy/SKILL.md",[674],{"path":271,"priority":272},{"basePath":676,"description":677,"displayName":676,"installMethods":678,"rationale":679,"selectedPaths":680,"source":506,"sourceLanguage":18,"type":251},"landing-report","Read-only queue dashboard for workspace-aware ship. Shows which VERSION slots\nare currently claimed by open PRs, which sibling Conductor workspaces have\nWIP work likely to ship soon, and what slot /ship would pick next. No\nmutations — just a snapshot. Use when asked to \"landing report\", \"what's in\nthe queue\", \"show me open PRs\", or \"which version do I claim next\". (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at landing-report/SKILL.md",[681],{"path":271,"priority":272},{"basePath":683,"description":684,"displayName":683,"installMethods":685,"rationale":686,"selectedPaths":687,"source":506,"sourceLanguage":18,"type":251},"learn","Manage project learnings. Review, search, prune, and export what gstack\nhas learned across sessions. Use when asked to \"what have we learned\",\n\"show learnings\", \"prune stale learnings\", or \"export learnings\".\nProactively suggest when the user asks about past patterns or wonders\n\"didn't we fix this before?\"\n",{"claudeCode":12},"SKILL.md frontmatter at learn/SKILL.md",[688],{"path":271,"priority":272},{"basePath":690,"description":691,"displayName":690,"installMethods":692,"rationale":693,"selectedPaths":694,"source":506,"sourceLanguage":18,"type":251},"make-pdf","Turn any markdown file into a publication-quality PDF. Proper 1in margins,\nintelligent page breaks, page numbers, cover pages, running headers, curly\nquotes and em dashes, clickable TOC, diagonal DRAFT watermark. Not a draft\nartifact — a finished artifact. Use when asked to \"make a PDF\", \"export to\nPDF\", \"turn this markdown into a PDF\", or \"generate a document\". (gstack)\nVoice triggers (speech-to-text aliases): \"make this a pdf\", \"make it a pdf\", \"export to pdf\", \"turn this into a pdf\", \"turn this markdown into a pdf\", \"generate a pdf\", \"make a pdf from\", \"pdf this markdown\".\n",{"claudeCode":12},"SKILL.md frontmatter at make-pdf/SKILL.md",[695],{"path":271,"priority":272},{"basePath":697,"description":698,"displayName":697,"installMethods":699,"rationale":700,"selectedPaths":701,"source":506,"sourceLanguage":18,"type":251},"open-gstack-browser","Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in.\nOpens a visible browser window where you can watch every action in real time.\nThe sidebar shows a live activity feed and chat. Anti-bot stealth built in.\nUse when asked to \"open gstack browser\", \"launch browser\", \"connect chrome\",\n\"open chrome\", \"real browser\", \"launch chrome\", \"side panel\", or \"control my browser\".\nVoice triggers (speech-to-text aliases): \"show me the browser\".\n",{"claudeCode":12},"SKILL.md frontmatter at open-gstack-browser/SKILL.md",[702],{"path":271,"priority":272},{"basePath":704,"description":705,"displayName":706,"installMethods":707,"rationale":708,"selectedPaths":709,"source":506,"sourceLanguage":18,"type":251},"openclaw/skills/gstack-openclaw-ceo-review","Use when asked to review a plan, challenge a proposal, run a CEO review, poke holes in an approach, think bigger about scope, or decide whether to expand or reduce the plan.","gstack-openclaw-ceo-review",{"claudeCode":12},"SKILL.md frontmatter at openclaw/skills/gstack-openclaw-ceo-review/SKILL.md",[710],{"path":271,"priority":272},{"basePath":712,"description":713,"displayName":714,"installMethods":715,"rationale":716,"selectedPaths":717,"source":506,"sourceLanguage":18,"type":251},"openclaw/skills/gstack-openclaw-investigate","Use when asked to debug, fix a bug, investigate an error, or do root cause analysis, and when users report errors, stack traces, unexpected behavior, or say something stopped working.","gstack-openclaw-investigate",{"claudeCode":12},"SKILL.md frontmatter at openclaw/skills/gstack-openclaw-investigate/SKILL.md",[718],{"path":271,"priority":272},{"basePath":720,"description":721,"displayName":722,"installMethods":723,"rationale":724,"selectedPaths":725,"source":506,"sourceLanguage":18,"type":251},"openclaw/skills/gstack-openclaw-office-hours","Use when asked to brainstorm, evaluate whether an idea is worth building, run office hours, or think through a new product idea or design direction before any code is written.","gstack-openclaw-office-hours",{"claudeCode":12},"SKILL.md frontmatter at openclaw/skills/gstack-openclaw-office-hours/SKILL.md",[726],{"path":271,"priority":272},{"basePath":728,"description":729,"displayName":730,"installMethods":731,"rationale":732,"selectedPaths":733,"source":506,"sourceLanguage":18,"type":251},"openclaw/skills/gstack-openclaw-retro","Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware with per-person contributions, praise, and growth areas. Use when asked for weekly retro, what shipped this week, or engineering retrospective.","gstack-openclaw-retro",{"claudeCode":12},"SKILL.md frontmatter at openclaw/skills/gstack-openclaw-retro/SKILL.md",[734],{"path":271,"priority":272},{"basePath":736,"description":737,"displayName":736,"installMethods":738,"rationale":739,"selectedPaths":740,"source":506,"sourceLanguage":18,"type":251},"pair-agent","Pair a remote AI agent with your browser. One command generates a setup key and\nprints instructions the other agent can follow to connect. Works with OpenClaw,\nHermes, Codex, Cursor, or any agent that can make HTTP requests. The remote agent\ngets its own tab with scoped access (read+write by default, admin on request).\nUse when asked to \"pair agent\", \"connect agent\", \"share browser\", \"remote browser\",\n\"let another agent use my browser\", or \"give browser access\". (gstack)\nVoice triggers (speech-to-text aliases): \"pair agent\", \"connect agent\", \"share my browser\", \"remote browser access\".\n",{"claudeCode":12},"SKILL.md frontmatter at pair-agent/SKILL.md",[741],{"path":271,"priority":272},{"basePath":743,"description":744,"displayName":743,"installMethods":745,"rationale":746,"selectedPaths":747,"source":506,"sourceLanguage":18,"type":251},"plan-devex-review","Interactive developer experience plan review. Explores developer personas,\nbenchmarks against competitors, designs magical moments, and traces friction\npoints before scoring. Three modes: DX EXPANSION (competitive advantage),\nDX POLISH (bulletproof every touchpoint), DX TRIAGE (critical gaps only).\nUse when asked to \"DX review\", \"developer experience audit\", \"devex review\",\nor \"API design review\".\nProactively suggest when the user has a plan for developer-facing products\n(APIs, CLIs, SDKs, libraries, platforms, docs). (gstack)\nVoice triggers (speech-to-text aliases): \"dx review\", \"developer experience review\", \"devex review\", \"devex audit\", \"API design review\", \"onboarding review\".\n",{"claudeCode":12},"SKILL.md frontmatter at plan-devex-review/SKILL.md",[748,749],{"path":271,"priority":272},{"path":750,"priority":280},"dx-hall-of-fame.md",{"basePath":752,"description":753,"displayName":752,"installMethods":754,"rationale":755,"selectedPaths":756,"source":506,"sourceLanguage":18,"type":251},"plan-eng-review","Eng manager-mode plan review. Lock in the execution plan — architecture,\ndata flow, diagrams, edge cases, test coverage, performance. Walks through\nissues interactively with opinionated recommendations. Use when asked to\n\"review the architecture\", \"engineering review\", or \"lock in the plan\".\nProactively suggest when the user has a plan or design doc and is about to\nstart coding — to catch architecture issues before implementation. (gstack)\nVoice triggers (speech-to-text aliases): \"tech review\", \"technical review\", \"plan engineering review\".\n",{"claudeCode":12},"SKILL.md frontmatter at plan-eng-review/SKILL.md",[757],{"path":271,"priority":272},{"basePath":759,"description":760,"displayName":759,"installMethods":761,"rationale":762,"selectedPaths":763,"source":506,"sourceLanguage":18,"type":251},"plan-tune","Self-tuning question sensitivity + developer psychographic for gstack (v1: observational).\nReview which AskUserQuestion prompts fire across gstack skills, set per-question preferences\n(never-ask / always-ask / ask-only-for-one-way), inspect the dual-track\nprofile (what you declared vs what your behavior suggests), and enable/disable\nquestion tuning. Conversational interface — no CLI syntax required.\n\nUse when asked to \"tune questions\", \"stop asking me that\", \"too many questions\",\n\"show my profile\", \"what questions have I been asked\", \"show my vibe\",\n\"developer profile\", or \"turn off question tuning\". (gstack)\n\nProactively suggest when the user says the same gstack question has come up before,\nor when they explicitly override a recommendation for the Nth time.\n",{"claudeCode":12},"SKILL.md frontmatter at plan-tune/SKILL.md",[764],{"path":271,"priority":272},{"basePath":213,"description":766,"displayName":213,"installMethods":767,"rationale":768,"selectedPaths":769,"source":506,"sourceLanguage":18,"type":251},"Systematically QA test a web application and fix bugs found. Runs QA testing,\nthen iteratively fixes bugs in source code, committing each fix atomically and\nre-verifying. Use when asked to \"qa\", \"QA\", \"test this site\", \"find bugs\",\n\"test and fix\", or \"fix what's broken\".\nProactively suggest when the user says a feature is ready for testing\nor asks \"does this work?\". Three tiers: Quick (critical/high only),\nStandard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores,\nfix evidence, and a ship-readiness summary. For report-only mode, use /qa-only. (gstack)\nVoice triggers (speech-to-text aliases): \"quality check\", \"test the app\", \"run QA\".\n",{"claudeCode":12},"SKILL.md frontmatter at qa/SKILL.md",[770,771,773],{"path":271,"priority":272},{"path":772,"priority":280},"references/issue-taxonomy.md",{"path":774,"priority":301},"templates/qa-report-template.md",{"basePath":776,"description":777,"displayName":776,"installMethods":778,"rationale":779,"selectedPaths":780,"source":506,"sourceLanguage":18,"type":251},"qa-only","Report-only QA testing. Systematically tests a web application and produces a\nstructured report with health score, screenshots, and repro steps — but never\nfixes anything. Use when asked to \"just report bugs\", \"qa report only\", or\n\"test but don't fix\". For the full test-fix-verify loop, use /qa instead.\nProactively suggest when the user wants a bug report without any code changes. (gstack)\nVoice triggers (speech-to-text aliases): \"bug report\", \"just check for bugs\".\n",{"claudeCode":12},"SKILL.md frontmatter at qa-only/SKILL.md",[781],{"path":271,"priority":272},{"basePath":783,"description":784,"displayName":783,"installMethods":785,"rationale":786,"selectedPaths":787,"source":506,"sourceLanguage":18,"type":251},"retro","Weekly engineering retrospective. Analyzes commit history, work patterns,\nand code quality metrics with persistent history and trend tracking.\nTeam-aware: breaks down per-person contributions with praise and growth areas.\nUse when asked to \"weekly retro\", \"what did we ship\", or \"engineering retrospective\".\nProactively suggest at the end of a work week or sprint. (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at retro/SKILL.md",[788],{"path":271,"priority":272},{"basePath":790,"description":791,"displayName":790,"installMethods":792,"rationale":793,"selectedPaths":794,"source":506,"sourceLanguage":18,"type":251},"review","Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust\nboundary violations, conditional side effects, and other structural issues. Use when\nasked to \"review this PR\", \"code review\", \"pre-landing review\", or \"check my diff\".\nProactively suggest when the user is about to merge or land code changes. (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at review/SKILL.md",[795,796,798,800,802],{"path":271,"priority":272},{"path":797,"priority":280},"TODOS-format.md",{"path":799,"priority":280},"checklist.md",{"path":801,"priority":280},"design-checklist.md",{"path":803,"priority":280},"greptile-triage.md",{"basePath":805,"description":806,"displayName":805,"installMethods":807,"rationale":808,"selectedPaths":809,"source":506,"sourceLanguage":18,"type":251},"scrape","Pull data from a web page. First call on a new intent prototypes the flow\nvia $B primitives and returns JSON. Subsequent calls on a matching intent\nroute to a codified browser-skill and return in ~200ms. Read-only — for\nmutating flows (form fills, clicks, submissions), use /automate.\nUse when asked to \"scrape\", \"get data from\", \"pull\", \"extract from\", or\n\"what's on\" a page. (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at scrape/SKILL.md",[810],{"path":271,"priority":272},{"basePath":812,"description":813,"displayName":812,"installMethods":814,"rationale":815,"selectedPaths":816,"source":506,"sourceLanguage":18,"type":251},"setup-browser-cookies","Import cookies from your real Chromium browser into the headless browse session.\nOpens an interactive picker UI where you select which cookie domains to import.\nUse before QA testing authenticated pages. Use when asked to \"import cookies\",\n\"login to the site\", or \"authenticate the browser\". (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at setup-browser-cookies/SKILL.md",[817],{"path":271,"priority":272},{"basePath":819,"description":820,"displayName":819,"installMethods":821,"rationale":822,"selectedPaths":823,"source":506,"sourceLanguage":18,"type":251},"setup-deploy","Configure deployment settings for /land-and-deploy. Detects your deploy\nplatform (Fly.io, Render, Vercel, Netlify, Heroku, GitHub Actions, custom),\nproduction URL, health check endpoints, and deploy status commands. Writes\nthe configuration to CLAUDE.md so all future deploys are automatic.\nUse when: \"setup deploy\", \"configure deployment\", \"set up land-and-deploy\",\n\"how do I deploy with gstack\", \"add deploy config\".\n",{"claudeCode":12},"SKILL.md frontmatter at setup-deploy/SKILL.md",[824],{"path":271,"priority":272},{"basePath":826,"description":827,"displayName":826,"installMethods":828,"rationale":829,"selectedPaths":830,"source":506,"sourceLanguage":18,"type":251},"setup-gbrain","Set up gbrain for this coding agent: install the CLI, initialize a\nlocal PGLite or Supabase brain, register MCP, capture per-remote trust\npolicy. One command from zero to \"gbrain is running, and this agent\ncan call it.\" Use when: \"setup gbrain\", \"connect gbrain\", \"start\ngbrain\", \"install gbrain\", \"configure gbrain for this machine\". (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at setup-gbrain/SKILL.md",[831,832],{"path":271,"priority":272},{"path":833,"priority":280},"memory.md",{"basePath":835,"description":836,"displayName":835,"installMethods":837,"rationale":838,"selectedPaths":839,"source":506,"sourceLanguage":18,"type":251},"skillify","Codify the most recent successful /scrape flow into a permanent\nbrowser-skill on disk. Future /scrape calls with the same intent run\nthe codified script in ~200ms instead of re-driving the page. Walks\nback through the conversation, synthesizes script.ts + script.test.ts\n+ fixture, runs the test in a temp dir, and asks before committing.\nUse when asked to \"skillify\", \"codify\", \"save this scrape\", or\n\"make this permanent\". (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at skillify/SKILL.md",[840],{"path":271,"priority":272},{"basePath":842,"description":843,"displayName":842,"installMethods":844,"rationale":845,"selectedPaths":846,"source":506,"sourceLanguage":18,"type":251},"sync-gbrain","Keep gbrain current with this repo's code and refresh agent search\nguidance in CLAUDE.md. Wraps the gstack-gbrain-sync orchestrator with\nstate probing, native code-surface registration, capability checks,\nand a verdict block. Re-runnable, idempotent. Use when: \"sync gbrain\",\n\"refresh gbrain\", \"re-index this repo\", \"gbrain search isn't finding\nthings\". (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at sync-gbrain/SKILL.md",[847],{"path":271,"priority":272},{"basePath":849,"description":850,"displayName":849,"installMethods":851,"rationale":852,"selectedPaths":853,"source":506,"sourceLanguage":18,"type":251},"unfreeze","Clear the freeze boundary set by /freeze, allowing edits to all directories\nagain. Use when you want to widen edit scope without ending the session.\nUse when asked to \"unfreeze\", \"unlock edits\", \"remove freeze\", or\n\"allow all edits\". (gstack)\n",{"claudeCode":12},"SKILL.md frontmatter at unfreeze/SKILL.md",[854],{"path":271,"priority":272},{"basePath":249,"description":856,"displayName":13,"installMethods":857,"license":244,"rationale":858,"selectedPaths":859,"source":506,"sourceLanguage":18,"type":864},"Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",{"npm":13},"cli ecosystem detected at /",[860,862,863],{"path":861,"priority":272},"package.json",{"path":274,"priority":272},{"path":277,"priority":275},"cli",{"sources":866},[867],"manual",{"npmPackage":13},{"closedIssues90d":234,"description":870,"forks":235,"license":244,"openIssues90d":238,"pushedAt":239,"readmeSize":232,"stars":240,"topics":871},"Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA",[],{"downloads":242},{"classifiedAt":874,"discoverAt":875,"extractAt":876,"githubAt":876,"npmAt":877,"updatedAt":874},1778687183243,1778687174845,1778687179160,1778687181363,[214,211,218,215,217,216,213,212],{"evaluatedAt":247,"extractAt":880,"updatedAt":247},1778687183932,[],[883,909,940,960,988,1017],{"_creationTime":884,"_id":885,"community":886,"display":887,"identity":893,"providers":897,"relations":903,"tags":905,"workflow":906},1778697652123.8857,"k179k1n5nw0md1x1j3dak31evn86mb5f",{"reviewCount":8},{"description":888,"installMethods":889,"name":891,"sourceUrl":892},"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":890},"steipete/clawdis","telegram-crabbox-e2e-proof","https://github.com/steipete/clawdis",{"basePath":894,"githubOwner":895,"githubRepo":896,"locale":18,"slug":891,"type":251},".agents/skills/telegram-crabbox-e2e-proof","steipete","clawdis",{"evaluate":898,"extract":902},{"promptVersionExtension":204,"promptVersionScoring":205,"score":899,"tags":900,"targetMarket":219,"tier":220},100,[212,901,214,213,864],"telegram",{"commitSha":257},{"repoId":904},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[214,864,213,901,212],{"evaluatedAt":907,"extractAt":908,"updatedAt":907},1778698038113,1778697652123,{"_creationTime":910,"_id":911,"community":912,"display":913,"identity":919,"providers":925,"relations":932,"tags":935,"workflow":936},1778699368519.5344,"k17ab0jk30pqm4zejpk383w4dn86mj8t",{"reviewCount":8},{"description":914,"installMethods":915,"name":917,"sourceUrl":918},"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":916},"xixu-me/skills","Use My Browser","https://github.com/xixu-me/skills",{"basePath":920,"githubOwner":921,"githubRepo":922,"locale":923,"slug":924,"type":251},"skills/use-my-browser","xixu-me","skills","de","use-my-browser",{"evaluate":926,"extract":931},{"promptVersionExtension":204,"promptVersionScoring":205,"score":899,"tags":927,"targetMarket":219,"tier":220},[211,928,214,929,930],"debugging","ux","developer-tools",{"commitSha":257,"license":244},{"repoId":933,"translatedFrom":934},"kd77r2vb42jmgam0qbr9f2c6kn86mebv","k179cgk616p3xva37r5jqsfwvh86mcp2",[214,211,928,930,929],{"evaluatedAt":937,"extractAt":938,"updatedAt":939},1778699261239,1778699106670,1778699368519,{"_creationTime":941,"_id":942,"community":943,"display":944,"identity":948,"providers":950,"relations":956,"tags":957,"workflow":958},1778697652123.8845,"k17bexjjjsz81ysk7bd3ggdm8s86mt2t",{"reviewCount":8},{"description":945,"installMethods":946,"name":947,"sourceUrl":892},"Choose, run, rerun, or debug OpenClaw tests, CI checks, Docker E2E lanes, release validation, and the cheapest safe verification path.",{"claudeCode":890},"openclaw-testing",{"basePath":949,"githubOwner":895,"githubRepo":896,"locale":18,"slug":947,"type":251},".agents/skills/openclaw-testing",{"evaluate":951,"extract":955},{"promptVersionExtension":204,"promptVersionScoring":205,"score":899,"tags":952,"targetMarket":219,"tier":220},[212,953,954,214,930],"ci","validation",{"commitSha":257},{"repoId":904},[214,953,930,212,954],{"evaluatedAt":959,"extractAt":908,"updatedAt":959},1778697962962,{"_creationTime":961,"_id":962,"community":963,"display":964,"identity":970,"providers":974,"relations":980,"tags":983,"workflow":984},1778697373439.756,"k1735p8vnc44y3ntfepns5m0nx86npbs",{"reviewCount":8},{"description":965,"installMethods":966,"name":968,"sourceUrl":969},"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":967},"shanraisshan/claude-code-best-practice","agent-browser","https://github.com/shanraisshan/claude-code-best-practice",{"basePath":971,"githubOwner":972,"githubRepo":973,"locale":923,"slug":968,"type":251},".claude/skills/agent-browser","shanraisshan","claude-code-best-practice",{"evaluate":975,"extract":979},{"promptVersionExtension":204,"promptVersionScoring":205,"score":899,"tags":976,"targetMarket":219,"tier":220},[977,978,212,864,214],"browser-automation","web-scraping",{"commitSha":257},{"repoId":981,"translatedFrom":982},"kd74710g49kxgwbfjxeb7s132d86myxr","k17ej9360g7468qswf3svnrx9186m1ng",[214,977,864,212,978],{"evaluatedAt":985,"extractAt":986,"updatedAt":987},1778697222051,1778697205743,1778697373439,{"_creationTime":989,"_id":990,"community":991,"display":992,"identity":998,"providers":1002,"relations":1010,"tags":1013,"workflow":1014},1778690831986.3767,"k17fjjgdng9c2xwz18cc594g0986n7wy",{"reviewCount":8},{"description":993,"installMethods":994,"name":996,"sourceUrl":997},"Use for Vue.js testing. Covers Vitest, Vue Test Utils, component testing, mocking, testing patterns, and Playwright for E2E testing.",{"claudeCode":995},"hyf0/vue-skills","vue-testing-best-practices","https://github.com/hyf0/vue-skills",{"basePath":999,"githubOwner":1000,"githubRepo":1001,"locale":18,"slug":996,"type":251},"skills/vue-testing-best-practices","hyf0","vue-skills",{"evaluate":1003,"extract":1009},{"promptVersionExtension":204,"promptVersionScoring":205,"score":899,"tags":1004,"targetMarket":219,"tier":220},[1005,212,1006,217,1007,1008],"vue-js","vitest","component-testing","e2e-testing",{"commitSha":257},{"parentExtensionId":1011,"repoId":1012},"k17fvvpt61wrah7aepwqhgjp4d86n8jx","kd7a1a0bdc2ez150x3razht61n86m6a8",[1007,1008,217,212,1006,1005],{"evaluatedAt":1015,"extractAt":1016,"updatedAt":1015},1778691195044,1778690831986,{"_creationTime":1018,"_id":1019,"community":1020,"display":1021,"identity":1027,"providers":1031,"relations":1039,"tags":1041,"workflow":1042},1778685991755.7456,"k17djff3pz3wam5kpz7pkg92h586menn",{"reviewCount":8},{"description":1022,"installMethods":1023,"name":1025,"sourceUrl":1026},"Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.",{"claudeCode":1024},"davila7/claude-code-templates","develop-web-game","https://github.com/davila7/claude-code-templates",{"basePath":1028,"githubOwner":1029,"githubRepo":1030,"locale":18,"slug":1025,"type":251},"cli-tool/components/skills/creative-design/develop-web-game","davila7","claude-code-templates",{"evaluate":1032,"extract":1038},{"promptVersionExtension":204,"promptVersionScoring":205,"score":899,"tags":1033,"targetMarket":219,"tier":220},[1034,1035,1036,1037,217,212,214],"web-development","game-development","javascript","html",{"commitSha":257},{"repoId":1040},"kd71fzn4s7r0269fkw47wt670n86ndz0",[214,1035,1037,1036,217,212,1034],{"evaluatedAt":1043,"extractAt":1044,"updatedAt":1043},1778690648090,1778685991755]