[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-garrytan-setup-browser-cookies-en":3,"guides-for-garrytan-setup-browser-cookies":877,"similar-k170wzjh7jrww3586pqyxkkeb186mmqn-en":878},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":244,"isFallback":232,"parentExtension":248,"providers":249,"relations":254,"repo":256,"tags":874,"workflow":875},1778687183932.1938,"k170wzjh7jrww3586pqyxkkeb186mmqn",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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},"garrytan/gstack","setup-browser-cookies","https://github.com/garrytan/gstack",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":222,"workflow":242},1778688370246.697,"kn792d6j76xr9mzz50fh3x20q586njyj","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"promptVersionExtension":204,"promptVersionScoring":205,"purpose":206,"rationale":207,"score":208,"summary":209,"tags":210,"targetMarket":216,"tier":217,"useCases":218},[21,26,29,32,36,39,43,48,51,54,58,62,65,69,72,75,78,81,84,87,90,94,99,103,107,110,113,116,120,123,126,129,132,135,138,142,146,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of importing cookies for authenticated testing and provides specific triggers like 'import cookies' or 'login to the site'.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers a specific, interactive UI for selecting cookie domains, which goes beyond a simple prompt and provides direct value for testing authenticated pages.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill appears fully implemented and covers the described use case of importing cookies for testing authenticated pages, with clear steps and alternatives.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill is focused solely on importing browser cookies into a headless session, a single, well-defined responsibility.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The description is concise, accurate, and accurately reflects the skill's behavior, including interactive elements and use cases.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The skill uses narrow, specific tools like 'cookie-import-browser' and 'gstack-config', avoiding generalist execution commands.",{"category":44,"check":45,"severity":46,"summary":47},"Documentation","Configuration & parameter reference","not_applicable","The skill does not expose any explicit configuration options or parameters beyond what is implicitly handled by the underlying gstack/browse infrastructure.",{"category":33,"check":49,"severity":24,"summary":50},"Tool naming","Tools like 'cookie-import-browser' and '$B cookies' are descriptive and clearly indicate their function.",{"category":33,"check":52,"severity":24,"summary":53},"Minimal I/O surface","Inputs are handled implicitly or via user interaction; outputs summarize cookie counts, which is minimal and relevant to the task.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The extension is licensed under the MIT license, which is permissive and widely usable.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The repository shows recent commits, indicating active maintenance.",{"category":59,"check":63,"severity":24,"summary":64},"Dependency Management","The `package.json` file indicates dependencies are managed, and the setup script appears to handle necessary installations like Bun.",{"category":66,"check":67,"severity":24,"summary":68},"Security","Secret Management","The skill does not appear to handle or expose secrets directly; it interacts with browser cookie stores which are managed by the browser itself.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill relies on the underlying 'gstack-browse' binary and browser mechanisms for cookie handling, which are presumed to be secure and do not involve arbitrary code execution from loaded data.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill's functionality is self-contained and does not appear to fetch or execute external scripts at runtime.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill operates within the gstack environment and interacts with browser mechanisms; it does not appear to modify files outside its designated scope.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","No evidence of detached processes or deny-retry loops that could indicate sandbox escape attempts.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill's purpose is to import cookies, not to exfiltrate confidential data. Cookie values are handled by the browser's secure store and selectively imported.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled SKILL.md and README do not contain any hidden steering characters or obfuscated content.",{"category":66,"check":88,"severity":24,"summary":89},"Opaque code execution","The script files included in the bundle appear to be plain, readable bash and TypeScript, without obfuscation or runtime fetches.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The skill correctly identifies the browse binary location relative to the skill directory or home directory, avoiding rigid path assumptions.",{"category":95,"check":96,"severity":97,"summary":98},"Trust","Issues Attention","info","The repository has a high number of open issues (203) compared to closed issues (194) in the last 90 days, suggesting maintainers may be slow to address them.",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","The SKILL.md frontmatter clearly declares the version as 1.0.0, aligning with semantic versioning practices.",{"category":104,"check":105,"severity":24,"summary":106},"Code Execution","Validation","Input validation is handled by the underlying gstack-browse tool and browser mechanisms, which are presumed to validate domain inputs.",{"category":66,"check":108,"severity":24,"summary":109},"Unguarded Destructive Operations","The skill is primarily for importing data and does not perform destructive operations like deletions or modifications outside of its intended scope.",{"category":104,"check":111,"severity":24,"summary":112},"Error Handling","The script includes error handling for setup steps (e.g., checksum validation for Bun) and provides informative messages for potential issues.",{"category":104,"check":114,"severity":24,"summary":115},"Logging","The skill includes telemetry and timeline logging for usage tracking and debugging, as expected for gstack utilities.",{"category":117,"check":118,"severity":24,"summary":119},"Compliance","GDPR","The skill imports cookies based on user selection and does not inherently operate on personal data without user interaction or consent.",{"category":117,"check":121,"severity":24,"summary":122},"Target market","The skill's functionality is not geographically restricted and is applicable globally.",{"category":91,"check":124,"severity":24,"summary":125},"Runtime stability","The setup script handles dependency installation (Bun) and the skill is designed to work across common operating systems via gstack/browse.",{"category":44,"check":127,"severity":24,"summary":128},"README","The README is comprehensive, well-structured, and clearly explains the project's purpose, installation, and usage.",{"category":33,"check":130,"severity":46,"summary":131},"Tool surface size","This is a single-purpose skill, not an extension with multiple distinct tools.",{"category":40,"check":133,"severity":24,"summary":134},"Overlapping near-synonym tools","The skill uses distinct commands for its operations, with no near-synonyms causing ambiguity.",{"category":44,"check":136,"severity":24,"summary":137},"Phantom features","All features described in the README and SKILL.md (cookie import, picker UI, direct domain import) have corresponding implementations.",{"category":139,"check":140,"severity":24,"summary":141},"Install","Installation instruction","Installation instructions are clear, copy-pasteable, and include details for both local and team modes.",{"category":143,"check":144,"severity":24,"summary":145},"Errors","Actionable error messages","Error messages in the setup scripts and skill logic provide clear explanations and remediation steps.",{"category":147,"check":148,"severity":24,"summary":149},"Execution","Pinned dependencies","Dependencies like Bun are handled by the setup script, and the project structure suggests a managed environment.",{"category":33,"check":151,"severity":46,"summary":152},"Dry-run preview","The skill's primary function is interactive cookie import; a dry-run is not applicable or meaningful for this operation.",{"category":154,"check":155,"severity":46,"summary":156},"Protocol","Idempotent retry & timeouts","The skill does not involve remote calls or state-changing operations that would require idempotency or specific timeouts beyond standard browser interaction.",{"category":117,"check":158,"severity":24,"summary":159},"Telemetry opt-in","Telemetry is clearly documented as opt-in and provides options for community, anonymous, or off modes.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The skill clearly defines its purpose (importing cookies) and provides specific use cases (testing authenticated pages, handling login requests).",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter in SKILL.md is concise, clearly stating the skill's name, description, and triggers without excessive verbosity.",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md is well-organized, with core instructions upfront and detailed explanations deferred to the README or specific sections, adhering to progressive disclosure.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","Detailed explanations, such as for browser setup and advanced usage, are linked from the SKILL.md and README, following progressive disclosure principles.",{"category":170,"check":174,"severity":46,"summary":175},"Forked exploration","This skill is not an exploration or audit-style skill that would necessitate 'context: fork'.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The README provides clear examples of how to use the skill, including the interactive picker and direct domain import.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The skill documentation addresses potential issues like Keychain prompts on macOS, Linux cookie variations, and notes on the picker's security and persistence.",{"category":104,"check":183,"severity":46,"summary":184},"Tool Fallback","The skill relies on the gstack-browse binary, which is bundled and set up as part of the installation process, so no external fallback is expected.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The setup script includes checks for dependencies and potential errors, halting execution with informative messages if prerequisites are not met.",{"category":91,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The skill is self-contained and does not rely on other gstack skills being loaded in the same session.",1778688370119,"This skill imports cookies from a user's Chromium-based browser into a headless session for testing authenticated web pages. It provides an interactive UI for selecting domains or can import specific domains directly, and verifies the import.",[195,196,197,198,199],"Import cookies from Chromium browsers","Interactive domain selection UI","Direct domain import via CLI","Verify imported cookies summary","Integrates with gstack browse functionality",[201,202,203],"Managing user accounts or credentials directly","Performing actions within the browser beyond cookie import","Handling non-Chromium based browsers","3.0.0","4.4.0","Import logged-in sessions from your real Chromium browser into the headless browse session to test authenticated pages without manual login.","The skill is well-documented, robustly implemented, and adheres to best practices. The only minor finding is related to issue attention on the main gstack repository.",98,"Excellent skill for importing browser cookies into headless sessions for authenticated testing.",[211,212,213,214,215],"cookies","testing","browser","automation","qa","global","verified",[219,220,221],"Testing authenticated pages in QA environments","Automating login flows for testing purposes","Setting up authenticated browser sessions for automated scripts",{"codeQuality":223,"collectedAt":225,"documentation":226,"maintenance":229,"popularity":237,"security":239,"testCoverage":241},{"hasLockfile":224},true,1778688351760,{"descriptionLength":227,"readmeSize":228},301,40680,{"closedIssues90d":230,"forks":231,"hasChangelog":232,"manifestVersion":233,"openIssues90d":234,"pushedAt":235,"stars":236},194,14166,false,"1.0.0",203,1778685252000,95479,{"npmDownloads":238},5893,{"hasNpmPackage":224,"license":240,"smitheryVerified":232},"MIT",{"hasCi":224,"hasTests":224},{"updatedAt":243},1778688370246,{"basePath":13,"githubOwner":245,"githubRepo":246,"locale":18,"slug":13,"type":247},"garrytan","gstack","skill",null,{"evaluate":250,"extract":252},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":251,"targetMarket":216,"tier":217},[211,212,213,214,215],{"commitSha":253},"HEAD",{"repoId":255},"kd73s35xh97m9mmc5nz3pb1f3n86m0an",{"_creationTime":257,"_id":255,"identity":258,"providers":259,"workflow":869},1778687174845.1123,{"githubOwner":245,"githubRepo":246,"sourceUrl":14},{"classify":260,"discover":861,"extract":864,"github":865,"npm":868},{"commitSha":253,"extensions":261},[262,505,512,519,526,537,545,552,559,566,573,580,589,596,603,610,617,624,631,638,645,652,659,666,673,680,687,694,701,709,717,725,733,740,749,756,763,773,780,787,802,809,814,821,830,837,844,851],{"basePath":263,"description":264,"displayName":246,"installMethods":265,"rationale":266,"selectedPaths":267,"source":504,"sourceLanguage":18,"type":247},"","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},"SKILL.md frontmatter at SKILL.md",[268,271,274,276,279,281,283,285,287,289,291,293,295,297,300,302,304,306,308,310,312,314,316,318,320,322,324,326,328,330,332,334,336,338,340,342,344,346,348,350,352,354,356,358,360,362,364,366,368,370,372,374,376,378,380,382,384,386,388,390,392,394,396,398,400,402,404,406,408,410,412,414,416,418,420,422,424,426,428,430,432,434,436,438,440,442,444,446,448,450,452,454,456,458,460,462,464,466,468,470,472,474,476,478,480,482,484,486,488,490,492,494,496,498,500,502],{"path":269,"priority":270},"SKILL.md","mandatory",{"path":272,"priority":273},"README.md","high",{"path":275,"priority":273},"LICENSE",{"path":277,"priority":278},"AGENTS.md","medium",{"path":280,"priority":278},"ARCHITECTURE.md",{"path":282,"priority":278},"BROWSER.md",{"path":284,"priority":278},"CHANGELOG.md",{"path":286,"priority":278},"CLAUDE.md",{"path":288,"priority":278},"CONTRIBUTING.md",{"path":290,"priority":278},"DESIGN.md",{"path":292,"priority":278},"ETHOS.md",{"path":294,"priority":278},"TODOS.md",{"path":296,"priority":278},"USING_GBRAIN_WITH_GSTACK.md",{"path":298,"priority":299},"docs/ADDING_A_HOST.md","low",{"path":301,"priority":299},"docs/ON_THE_LOC_CONTROVERSY.md",{"path":303,"priority":299},"docs/OPENCLAW.md",{"path":305,"priority":299},"docs/REMOTE_BROWSER_ACCESS.md",{"path":307,"priority":299},"docs/designs/BROWSER_SKILLS_V1.md",{"path":309,"priority":299},"docs/designs/BUN_NATIVE_INFERENCE.md",{"path":311,"priority":299},"docs/designs/CHROME_VS_CHROMIUM_EXPLORATION.md",{"path":313,"priority":299},"docs/designs/CONDUCTOR_CHROME_SIDEBAR_INTEGRATION.md",{"path":315,"priority":299},"docs/designs/CONDUCTOR_SESSION_API.md",{"path":317,"priority":299},"docs/designs/DESIGN_SHOTGUN.md",{"path":319,"priority":299},"docs/designs/DESIGN_TOOLS_V1.md",{"path":321,"priority":299},"docs/designs/GCOMPACTION.md",{"path":323,"priority":299},"docs/designs/GSTACK_BROWSER_V0.md",{"path":325,"priority":299},"docs/designs/ML_PROMPT_INJECTION_KILLER.md",{"path":327,"priority":299},"docs/designs/PACING_UPDATES_V0.md",{"path":329,"priority":299},"docs/designs/PLAN_TUNING_V0.md",{"path":331,"priority":299},"docs/designs/PLAN_TUNING_V1.md",{"path":333,"priority":299},"docs/designs/SELF_LEARNING_V0.md",{"path":335,"priority":299},"docs/designs/SESSION_INTELLIGENCE.md",{"path":337,"priority":299},"docs/designs/SIDEBAR_MESSAGE_FLOW.md",{"path":339,"priority":299},"docs/designs/SLATE_HOST.md",{"path":341,"priority":299},"docs/designs/SLOP_SCAN_FOR_REVIEW_SHIP.md",{"path":343,"priority":299},"docs/designs/SYNC_GBRAIN_BATCH_INGEST.md",{"path":345,"priority":299},"docs/domain-skills.md",{"path":347,"priority":299},"docs/evals/security-bench-ensemble-v2.json",{"path":349,"priority":299},"docs/gbrain-sync-errors.md",{"path":351,"priority":299},"docs/gbrain-sync.md",{"path":353,"priority":299},"docs/images/github-2013.png",{"path":355,"priority":299},"docs/images/github-2026.png",{"path":357,"priority":299},"docs/skills.md",{"path":359,"priority":299},"scripts/analytics.ts",{"path":361,"priority":299},"scripts/app/gstack-browser",{"path":363,"priority":299},"scripts/app/icon.icns",{"path":365,"priority":299},"scripts/archetypes.ts",{"path":367,"priority":299},"scripts/build-app.sh",{"path":369,"priority":299},"scripts/compare-pr-version.ts",{"path":371,"priority":299},"scripts/detect-bump.ts",{"path":373,"priority":299},"scripts/dev-skill.ts",{"path":375,"priority":299},"scripts/discover-skills.ts",{"path":377,"priority":299},"scripts/eval-compare.ts",{"path":379,"priority":299},"scripts/eval-list.ts",{"path":381,"priority":299},"scripts/eval-select.ts",{"path":383,"priority":299},"scripts/eval-summary.ts",{"path":385,"priority":299},"scripts/eval-watch.ts",{"path":387,"priority":299},"scripts/garry-output-comparison.ts",{"path":389,"priority":299},"scripts/gen-llms-txt.ts",{"path":391,"priority":299},"scripts/gen-skill-docs.ts",{"path":393,"priority":299},"scripts/host-adapters/openclaw-adapter.ts",{"path":395,"priority":299},"scripts/host-config-export.ts",{"path":397,"priority":299},"scripts/host-config.ts",{"path":399,"priority":299},"scripts/jargon-list.json",{"path":401,"priority":299},"scripts/models.ts",{"path":403,"priority":299},"scripts/one-way-doors.ts",{"path":405,"priority":299},"scripts/preflight-agent-sdk.ts",{"path":407,"priority":299},"scripts/psychographic-signals.ts",{"path":409,"priority":299},"scripts/question-registry.ts",{"path":411,"priority":299},"scripts/resolvers/browse.ts",{"path":413,"priority":299},"scripts/resolvers/codex-helpers.ts",{"path":415,"priority":299},"scripts/resolvers/composition.ts",{"path":417,"priority":299},"scripts/resolvers/confidence.ts",{"path":419,"priority":299},"scripts/resolvers/constants.ts",{"path":421,"priority":299},"scripts/resolvers/design.ts",{"path":423,"priority":299},"scripts/resolvers/dx.ts",{"path":425,"priority":299},"scripts/resolvers/gbrain.ts",{"path":427,"priority":299},"scripts/resolvers/index.ts",{"path":429,"priority":299},"scripts/resolvers/learnings.ts",{"path":431,"priority":299},"scripts/resolvers/make-pdf.ts",{"path":433,"priority":299},"scripts/resolvers/model-overlay.ts",{"path":435,"priority":299},"scripts/resolvers/preamble/generate-ask-user-format.ts",{"path":437,"priority":299},"scripts/resolvers/preamble/generate-brain-health-instruction.ts",{"path":439,"priority":299},"scripts/resolvers/preamble/generate-brain-sync-block.ts",{"path":441,"priority":299},"scripts/resolvers/preamble/generate-completeness-section.ts",{"path":443,"priority":299},"scripts/resolvers/preamble/generate-completion-status.ts",{"path":445,"priority":299},"scripts/resolvers/preamble/generate-confusion-protocol.ts",{"path":447,"priority":299},"scripts/resolvers/preamble/generate-context-health.ts",{"path":449,"priority":299},"scripts/resolvers/preamble/generate-context-recovery.ts",{"path":451,"priority":299},"scripts/resolvers/preamble/generate-continuous-checkpoint.ts",{"path":453,"priority":299},"scripts/resolvers/preamble/generate-lake-intro.ts",{"path":455,"priority":299},"scripts/resolvers/preamble/generate-preamble-bash.ts",{"path":457,"priority":299},"scripts/resolvers/preamble/generate-proactive-prompt.ts",{"path":459,"priority":299},"scripts/resolvers/preamble/generate-repo-mode-section.ts",{"path":461,"priority":299},"scripts/resolvers/preamble/generate-routing-injection.ts",{"path":463,"priority":299},"scripts/resolvers/preamble/generate-search-before-building.ts",{"path":465,"priority":299},"scripts/resolvers/preamble/generate-spawned-session-check.ts",{"path":467,"priority":299},"scripts/resolvers/preamble/generate-telemetry-prompt.ts",{"path":469,"priority":299},"scripts/resolvers/preamble/generate-test-failure-triage.ts",{"path":471,"priority":299},"scripts/resolvers/preamble/generate-upgrade-check.ts",{"path":473,"priority":299},"scripts/resolvers/preamble/generate-vendoring-deprecation.ts",{"path":475,"priority":299},"scripts/resolvers/preamble/generate-voice-directive.ts",{"path":477,"priority":299},"scripts/resolvers/preamble/generate-writing-style-migration.ts",{"path":479,"priority":299},"scripts/resolvers/preamble/generate-writing-style.ts",{"path":481,"priority":299},"scripts/resolvers/preamble.ts",{"path":483,"priority":299},"scripts/resolvers/question-tuning.ts",{"path":485,"priority":299},"scripts/resolvers/review-army.ts",{"path":487,"priority":299},"scripts/resolvers/review.ts",{"path":489,"priority":299},"scripts/resolvers/testing.ts",{"path":491,"priority":299},"scripts/resolvers/types.ts",{"path":493,"priority":299},"scripts/resolvers/utility.ts",{"path":495,"priority":299},"scripts/setup-scc.sh",{"path":497,"priority":299},"scripts/skill-check.ts",{"path":499,"priority":299},"scripts/slop-diff.ts",{"path":501,"priority":299},"scripts/test-free-shards.ts",{"path":503,"priority":299},"scripts/update-readme-throughput.ts","rule",{"basePath":506,"description":507,"displayName":506,"installMethods":508,"rationale":509,"selectedPaths":510,"source":504,"sourceLanguage":18,"type":247},"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",[511],{"path":269,"priority":270},{"basePath":513,"description":514,"displayName":513,"installMethods":515,"rationale":516,"selectedPaths":517,"source":504,"sourceLanguage":18,"type":247},"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",[518],{"path":269,"priority":270},{"basePath":520,"description":521,"displayName":520,"installMethods":522,"rationale":523,"selectedPaths":524,"source":504,"sourceLanguage":18,"type":247},"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",[525],{"path":269,"priority":270},{"basePath":527,"description":528,"displayName":527,"installMethods":529,"rationale":530,"selectedPaths":531,"source":504,"sourceLanguage":18,"type":247},"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",[532,533,535],{"path":269,"priority":270},{"path":534,"priority":278},"PLAN-snapshot-dropdown-interactive.md",{"path":536,"priority":299},"scripts/build-node-server.sh",{"basePath":538,"description":539,"displayName":540,"installMethods":541,"rationale":542,"selectedPaths":543,"source":504,"sourceLanguage":18,"type":247},"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",[544],{"path":269,"priority":270},{"basePath":546,"description":547,"displayName":546,"installMethods":548,"rationale":549,"selectedPaths":550,"source":504,"sourceLanguage":18,"type":247},"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",[551],{"path":269,"priority":270},{"basePath":553,"description":554,"displayName":553,"installMethods":555,"rationale":556,"selectedPaths":557,"source":504,"sourceLanguage":18,"type":247},"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",[558],{"path":269,"priority":270},{"basePath":560,"description":561,"displayName":560,"installMethods":562,"rationale":563,"selectedPaths":564,"source":504,"sourceLanguage":18,"type":247},"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",[565],{"path":269,"priority":270},{"basePath":567,"description":568,"displayName":567,"installMethods":569,"rationale":570,"selectedPaths":571,"source":504,"sourceLanguage":18,"type":247},"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",[572],{"path":269,"priority":270},{"basePath":574,"description":575,"displayName":574,"installMethods":576,"rationale":577,"selectedPaths":578,"source":504,"sourceLanguage":18,"type":247},"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",[579],{"path":269,"priority":270},{"basePath":581,"description":582,"displayName":581,"installMethods":583,"rationale":584,"selectedPaths":585,"source":504,"sourceLanguage":18,"type":247},"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",[586,587],{"path":269,"priority":270},{"path":588,"priority":278},"ACKNOWLEDGEMENTS.md",{"basePath":590,"description":591,"displayName":590,"installMethods":592,"rationale":593,"selectedPaths":594,"source":504,"sourceLanguage":18,"type":247},"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",[595],{"path":269,"priority":270},{"basePath":597,"description":598,"displayName":597,"installMethods":599,"rationale":600,"selectedPaths":601,"source":504,"sourceLanguage":18,"type":247},"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",[602],{"path":269,"priority":270},{"basePath":604,"description":605,"displayName":604,"installMethods":606,"rationale":607,"selectedPaths":608,"source":504,"sourceLanguage":18,"type":247},"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",[609],{"path":269,"priority":270},{"basePath":611,"description":612,"displayName":611,"installMethods":613,"rationale":614,"selectedPaths":615,"source":504,"sourceLanguage":18,"type":247},"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",[616],{"path":269,"priority":270},{"basePath":618,"description":619,"displayName":618,"installMethods":620,"rationale":621,"selectedPaths":622,"source":504,"sourceLanguage":18,"type":247},"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",[623],{"path":269,"priority":270},{"basePath":625,"description":626,"displayName":625,"installMethods":627,"rationale":628,"selectedPaths":629,"source":504,"sourceLanguage":18,"type":247},"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",[630],{"path":269,"priority":270},{"basePath":632,"description":633,"displayName":632,"installMethods":634,"rationale":635,"selectedPaths":636,"source":504,"sourceLanguage":18,"type":247},"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",[637],{"path":269,"priority":270},{"basePath":639,"description":640,"displayName":639,"installMethods":641,"rationale":642,"selectedPaths":643,"source":504,"sourceLanguage":18,"type":247},"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",[644],{"path":269,"priority":270},{"basePath":646,"description":647,"displayName":646,"installMethods":648,"rationale":649,"selectedPaths":650,"source":504,"sourceLanguage":18,"type":247},"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",[651],{"path":269,"priority":270},{"basePath":653,"description":654,"displayName":653,"installMethods":655,"rationale":656,"selectedPaths":657,"source":504,"sourceLanguage":18,"type":247},"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",[658],{"path":269,"priority":270},{"basePath":660,"description":661,"displayName":660,"installMethods":662,"rationale":663,"selectedPaths":664,"source":504,"sourceLanguage":18,"type":247},"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",[665],{"path":269,"priority":270},{"basePath":667,"description":668,"displayName":667,"installMethods":669,"rationale":670,"selectedPaths":671,"source":504,"sourceLanguage":18,"type":247},"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",[672],{"path":269,"priority":270},{"basePath":674,"description":675,"displayName":674,"installMethods":676,"rationale":677,"selectedPaths":678,"source":504,"sourceLanguage":18,"type":247},"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",[679],{"path":269,"priority":270},{"basePath":681,"description":682,"displayName":681,"installMethods":683,"rationale":684,"selectedPaths":685,"source":504,"sourceLanguage":18,"type":247},"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",[686],{"path":269,"priority":270},{"basePath":688,"description":689,"displayName":688,"installMethods":690,"rationale":691,"selectedPaths":692,"source":504,"sourceLanguage":18,"type":247},"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",[693],{"path":269,"priority":270},{"basePath":695,"description":696,"displayName":695,"installMethods":697,"rationale":698,"selectedPaths":699,"source":504,"sourceLanguage":18,"type":247},"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",[700],{"path":269,"priority":270},{"basePath":702,"description":703,"displayName":704,"installMethods":705,"rationale":706,"selectedPaths":707,"source":504,"sourceLanguage":18,"type":247},"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",[708],{"path":269,"priority":270},{"basePath":710,"description":711,"displayName":712,"installMethods":713,"rationale":714,"selectedPaths":715,"source":504,"sourceLanguage":18,"type":247},"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",[716],{"path":269,"priority":270},{"basePath":718,"description":719,"displayName":720,"installMethods":721,"rationale":722,"selectedPaths":723,"source":504,"sourceLanguage":18,"type":247},"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",[724],{"path":269,"priority":270},{"basePath":726,"description":727,"displayName":728,"installMethods":729,"rationale":730,"selectedPaths":731,"source":504,"sourceLanguage":18,"type":247},"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",[732],{"path":269,"priority":270},{"basePath":734,"description":735,"displayName":734,"installMethods":736,"rationale":737,"selectedPaths":738,"source":504,"sourceLanguage":18,"type":247},"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",[739],{"path":269,"priority":270},{"basePath":741,"description":742,"displayName":741,"installMethods":743,"rationale":744,"selectedPaths":745,"source":504,"sourceLanguage":18,"type":247},"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",[746,747],{"path":269,"priority":270},{"path":748,"priority":278},"dx-hall-of-fame.md",{"basePath":750,"description":751,"displayName":750,"installMethods":752,"rationale":753,"selectedPaths":754,"source":504,"sourceLanguage":18,"type":247},"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",[755],{"path":269,"priority":270},{"basePath":757,"description":758,"displayName":757,"installMethods":759,"rationale":760,"selectedPaths":761,"source":504,"sourceLanguage":18,"type":247},"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",[762],{"path":269,"priority":270},{"basePath":215,"description":764,"displayName":215,"installMethods":765,"rationale":766,"selectedPaths":767,"source":504,"sourceLanguage":18,"type":247},"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",[768,769,771],{"path":269,"priority":270},{"path":770,"priority":278},"references/issue-taxonomy.md",{"path":772,"priority":299},"templates/qa-report-template.md",{"basePath":774,"description":775,"displayName":774,"installMethods":776,"rationale":777,"selectedPaths":778,"source":504,"sourceLanguage":18,"type":247},"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",[779],{"path":269,"priority":270},{"basePath":781,"description":782,"displayName":781,"installMethods":783,"rationale":784,"selectedPaths":785,"source":504,"sourceLanguage":18,"type":247},"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",[786],{"path":269,"priority":270},{"basePath":788,"description":789,"displayName":788,"installMethods":790,"rationale":791,"selectedPaths":792,"source":504,"sourceLanguage":18,"type":247},"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",[793,794,796,798,800],{"path":269,"priority":270},{"path":795,"priority":278},"TODOS-format.md",{"path":797,"priority":278},"checklist.md",{"path":799,"priority":278},"design-checklist.md",{"path":801,"priority":278},"greptile-triage.md",{"basePath":803,"description":804,"displayName":803,"installMethods":805,"rationale":806,"selectedPaths":807,"source":504,"sourceLanguage":18,"type":247},"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",[808],{"path":269,"priority":270},{"basePath":13,"description":10,"displayName":13,"installMethods":810,"rationale":811,"selectedPaths":812,"source":504,"sourceLanguage":18,"type":247},{"claudeCode":12},"SKILL.md frontmatter at setup-browser-cookies/SKILL.md",[813],{"path":269,"priority":270},{"basePath":815,"description":816,"displayName":815,"installMethods":817,"rationale":818,"selectedPaths":819,"source":504,"sourceLanguage":18,"type":247},"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",[820],{"path":269,"priority":270},{"basePath":822,"description":823,"displayName":822,"installMethods":824,"rationale":825,"selectedPaths":826,"source":504,"sourceLanguage":18,"type":247},"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",[827,828],{"path":269,"priority":270},{"path":829,"priority":278},"memory.md",{"basePath":831,"description":832,"displayName":831,"installMethods":833,"rationale":834,"selectedPaths":835,"source":504,"sourceLanguage":18,"type":247},"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",[836],{"path":269,"priority":270},{"basePath":838,"description":839,"displayName":838,"installMethods":840,"rationale":841,"selectedPaths":842,"source":504,"sourceLanguage":18,"type":247},"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",[843],{"path":269,"priority":270},{"basePath":845,"description":846,"displayName":845,"installMethods":847,"rationale":848,"selectedPaths":849,"source":504,"sourceLanguage":18,"type":247},"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",[850],{"path":269,"priority":270},{"basePath":263,"description":852,"displayName":246,"installMethods":853,"license":240,"rationale":854,"selectedPaths":855,"source":504,"sourceLanguage":18,"type":860},"Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",{"npm":246},"cli ecosystem detected at /",[856,858,859],{"path":857,"priority":270},"package.json",{"path":272,"priority":270},{"path":275,"priority":273},"cli",{"sources":862},[863],"manual",{"npmPackage":246},{"closedIssues90d":230,"description":866,"forks":231,"license":240,"openIssues90d":234,"pushedAt":235,"readmeSize":228,"stars":236,"topics":867},"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":238},{"classifiedAt":870,"discoverAt":871,"extractAt":872,"githubAt":872,"npmAt":873,"updatedAt":870},1778687183243,1778687174845,1778687179160,1778687181363,[214,213,211,215,212],{"evaluatedAt":243,"extractAt":876,"updatedAt":243},1778687183932,[],[879,905,934,954,981,1008],{"_creationTime":880,"_id":881,"community":882,"display":883,"identity":889,"providers":893,"relations":899,"tags":901,"workflow":902},1778697652123.8857,"k179k1n5nw0md1x1j3dak31evn86mb5f",{"reviewCount":8},{"description":884,"installMethods":885,"name":887,"sourceUrl":888},"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":886},"steipete/clawdis","telegram-crabbox-e2e-proof","https://github.com/steipete/clawdis",{"basePath":890,"githubOwner":891,"githubRepo":892,"locale":18,"slug":887,"type":247},".agents/skills/telegram-crabbox-e2e-proof","steipete","clawdis",{"evaluate":894,"extract":898},{"promptVersionExtension":204,"promptVersionScoring":205,"score":895,"tags":896,"targetMarket":216,"tier":217},100,[212,897,214,215,860],"telegram",{"commitSha":253},{"repoId":900},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[214,860,215,897,212],{"evaluatedAt":903,"extractAt":904,"updatedAt":903},1778698038113,1778697652123,{"_creationTime":906,"_id":907,"community":908,"display":909,"identity":915,"providers":920,"relations":927,"tags":929,"workflow":930},1778699106670.4268,"k179cgk616p3xva37r5jqsfwvh86mcp2",{"reviewCount":8},{"description":910,"installMethods":911,"name":913,"sourceUrl":914},"Use when work depends on the user's live browser session or visible rendered state rather than static fetches, especially for browser debugging contexts or DevTools-selected elements or requests, logged-in dashboards or CMS flows, localhost apps, forms, uploads, downloads, media inspection, DOM or iframe inspection, Shadow DOM, or browser failures that look like soft 404s, auth walls, anti-bot checks, or rate limits.",{"claudeCode":912},"xixu-me/skills","Use My Browser","https://github.com/xixu-me/skills",{"basePath":916,"githubOwner":917,"githubRepo":918,"locale":18,"slug":919,"type":247},"skills/use-my-browser","xixu-me","skills","use-my-browser",{"evaluate":921,"extract":926},{"promptVersionExtension":204,"promptVersionScoring":205,"score":895,"tags":922,"targetMarket":216,"tier":217},[213,923,214,924,925],"debugging","ux","developer-tools",{"commitSha":253,"license":240},{"repoId":928},"kd77r2vb42jmgam0qbr9f2c6kn86mebv",[214,213,923,925,924],{"evaluatedAt":931,"extractAt":932,"updatedAt":933},1778699261239,1778699106670,1778699384978,{"_creationTime":935,"_id":936,"community":937,"display":938,"identity":942,"providers":944,"relations":950,"tags":951,"workflow":952},1778697652123.8845,"k17bexjjjsz81ysk7bd3ggdm8s86mt2t",{"reviewCount":8},{"description":939,"installMethods":940,"name":941,"sourceUrl":888},"Choose, run, rerun, or debug OpenClaw tests, CI checks, Docker E2E lanes, release validation, and the cheapest safe verification path.",{"claudeCode":886},"openclaw-testing",{"basePath":943,"githubOwner":891,"githubRepo":892,"locale":18,"slug":941,"type":247},".agents/skills/openclaw-testing",{"evaluate":945,"extract":949},{"promptVersionExtension":204,"promptVersionScoring":205,"score":895,"tags":946,"targetMarket":216,"tier":217},[212,947,948,214,925],"ci","validation",{"commitSha":253},{"repoId":900},[214,947,925,212,948],{"evaluatedAt":953,"extractAt":904,"updatedAt":953},1778697962962,{"_creationTime":955,"_id":956,"community":957,"display":958,"identity":964,"providers":968,"relations":974,"tags":976,"workflow":977},1778697205743.894,"k17ej9360g7468qswf3svnrx9186m1ng",{"reviewCount":8},{"description":959,"installMethods":960,"name":962,"sourceUrl":963},"Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.",{"claudeCode":961},"shanraisshan/claude-code-best-practice","agent-browser","https://github.com/shanraisshan/claude-code-best-practice",{"basePath":965,"githubOwner":966,"githubRepo":967,"locale":18,"slug":962,"type":247},".claude/skills/agent-browser","shanraisshan","claude-code-best-practice",{"evaluate":969,"extract":973},{"promptVersionExtension":204,"promptVersionScoring":205,"score":895,"tags":970,"targetMarket":216,"tier":217},[971,972,212,860,214],"browser-automation","web-scraping",{"commitSha":253},{"repoId":975},"kd74710g49kxgwbfjxeb7s132d86myxr",[214,971,860,212,972],{"evaluatedAt":978,"extractAt":979,"updatedAt":980},1778697222051,1778697205743,1778697438718,{"_creationTime":982,"_id":983,"community":984,"display":985,"identity":991,"providers":994,"relations":1001,"tags":1003,"workflow":1004},1778698388090.9082,"k171cdw0ztmq4pqj5tmf0b8yj586mx7k",{"reviewCount":8},{"description":986,"installMethods":987,"name":989,"sourceUrl":990},"Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app/site/platform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.",{"claudeCode":988},"vercel-labs/agent-browser","dogfood","https://github.com/vercel-labs/agent-browser",{"basePath":992,"githubOwner":993,"githubRepo":962,"locale":18,"slug":989,"type":247},"skill-data/dogfood","vercel-labs",{"evaluate":995,"extract":1000},{"promptVersionExtension":204,"promptVersionScoring":205,"score":996,"tags":997,"targetMarket":216,"tier":217},99,[998,215,214,213,923,999],"web-testing","reporting",{"commitSha":253},{"repoId":1002},"kd74a6sfc26xa0ec2tpntj8r2986mn0a",[214,213,923,215,999,998],{"evaluatedAt":1005,"extractAt":1006,"updatedAt":1007},1778698472899,1778698388091,1778698676235,{"_creationTime":1009,"_id":1010,"community":1011,"display":1012,"identity":1018,"providers":1023,"relations":1032,"tags":1035,"workflow":1036},1778699234184.6157,"k177tdbfgqmwhtaqv771f2ych586nne9",{"reviewCount":8},{"description":1013,"installMethods":1014,"name":1016,"sourceUrl":1017},"Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions",{"claudeCode":1015},"Yeachan-Heo/oh-my-claudecode","Project Session Manager","https://github.com/Yeachan-Heo/oh-my-claudecode",{"basePath":1019,"githubOwner":1020,"githubRepo":1021,"locale":18,"slug":1022,"type":247},"skills/project-session-manager","Yeachan-Heo","oh-my-claudecode","project-session-manager",{"evaluate":1024,"extract":1031},{"promptVersionExtension":204,"promptVersionScoring":205,"score":895,"tags":1025,"targetMarket":216,"tier":217},[1026,1027,1028,1029,214,860,1030],"git","development-environment","workflow","tmux","developer-tool",{"commitSha":253,"license":240},{"parentExtensionId":1033,"repoId":1034},"k17brg5egdw1jbncj1j4wfv3fh86n639","kd74zv63fryf9prygtq7gf4es986n22y",[214,860,1030,1027,1026,1029,1028],{"evaluatedAt":1037,"extractAt":1038,"updatedAt":1037},1778699613343,1778699234184]