[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-vercel-labs-dogfood-en":3,"guides-for-vercel-labs-dogfood":411,"similar-k171cdw0ztmq4pqj5tmf0b8yj586mx7k-en":412},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":245,"isFallback":241,"parentExtension":250,"providers":251,"relations":256,"repo":258,"tags":407,"workflow":408},1778698388090.9082,"k171cdw0ztmq4pqj5tmf0b8yj586mx7k",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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":12},"vercel-labs/agent-browser","dogfood","https://github.com/vercel-labs/agent-browser",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":224,"workflow":243},1778698472899.1143,"kn78vd0j6q6pk1qjvr7eanxk1d86ngbr","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":217,"tier":218,"useCases":219},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,113,116,120,123,126,129,133,136,139,143,147,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly articulates the problem of systematically exploring and testing web applications to find bugs and UX issues, providing specific use cases and triggers.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The extension offers significant value over a simple prompt by providing a structured workflow, automated evidence collection (screenshots, videos), and a detailed report format, going beyond basic browser interaction.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The tool is production-ready, covering the complete lifecycle of exploratory testing from setup and authentication to exploration, detailed documentation, and session wrap-up with a structured report.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The extension focuses solely on web application testing and bug reporting, aligning with its name and description without branching into unrelated domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the tool's capabilities, clearly outlining its purpose, use cases, and output format.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The extension uses specific, narrow tools like `agent-browser open`, `click`, `fill`, `snapshot`, `screenshot`, and `errors`, avoiding a single generalist command.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","All parameters (Target URL, Session name, Output directory, Scope, Authentication) are clearly documented with defaults and examples in the SKILL.md setup section.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","Tool names like `open`, `click`, `fill`, `snapshot`, `screenshot`, `errors`, and `console` are descriptive and adhere to the domain.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","Commands like `snapshot -i` and `screenshot --annotate` request only necessary data, and outputs like the structured report and video files are focused on the stated task.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The project is licensed under the Apache-2.0 license, as confirmed by the bundled LICENSE file and the trust signals.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The repository has recent commits, indicating active maintenance.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","The project uses npm and has a lockfile (`package-lock.json` implied by `npm install -g` and `hasLockfile: true`), indicating suitable dependency management.",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","The tool handles authentication securely, as described in the README's Authentication section, using state files and options like `--session-name` and `--profile`, with encryption options available. It does not echo secrets to stdout or debug logs.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","The skill operates directly via `agent-browser` commands and does not appear to load or execute untrusted third-party code or data that could lead to injection vulnerabilities.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","The extension relies on the `agent-browser` CLI, which is installed globally or locally. It does not fetch remote content at runtime to be executed as instructions.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","The `agent-browser` CLI is designed for safe browser automation. The provided SKILL.md uses commands that operate within the browser context and output files to specified directories, adhering to sandbox isolation principles.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","The SKILL.md does not contain any instructions or scripts that suggest sandbox escape primitives like detached processes or deny-retry loops.",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","The extension's workflow focuses on capturing browser state and issues, with no indication of reading or submitting confidential data to third parties.",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","The SKILL.md and README do not contain any hidden text tricks, invisible Unicode characters, or obfuscated content.",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","The SKILL.md and README do not use obfuscated code, base64 payloads, `eval`, or runtime script fetching.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The skill assumes output directories exist but creates them. Paths are relative (`./dogfood-output/`), and commands are executed via `agent-browser`, which handles its own environment.",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","The repository shows a healthy ratio of closed to opened issues (155 closed vs. 142 opened in 90 days), indicating active maintenance and responsiveness.",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","The project has a `CHANGELOG.md` and recent commits, and the `agent-browser` CLI likely has versioning managed through npm/cargo, indicating good release management practices.",{"category":103,"check":104,"severity":24,"summary":105},"Execution","Validation","The `agent-browser` CLI itself likely handles input validation. The SKILL.md does not expose complex parameters that would require custom validation logic within the skill.",{"category":65,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","The skill primarily interacts with the browser and saves files to specified directories. Destructive operations like file deletion are not part of its core workflow, and the underlying `agent-browser` has security features like action policies and confirmation prompts.",{"category":110,"check":111,"severity":24,"summary":112},"Code Execution","Error Handling","The SKILL.md outlines clear steps and uses `agent-browser` commands, which are expected to provide structured errors. The documentation emphasizes capturing console errors and handling issues systematically.",{"category":110,"check":114,"severity":24,"summary":115},"Logging","The workflow involves saving screenshots, videos, and a report to a local directory, serving as a form of audit log for the testing process.",{"category":117,"check":118,"severity":24,"summary":119},"Compliance","GDPR","The skill operates on web applications and generates reports, without explicitly handling or submitting personal data beyond what is incidentally captured during browser testing, which aligns with GDPR principles.",{"category":117,"check":121,"severity":24,"summary":122},"Target market","The extension is a general-purpose web testing tool and has no regional or jurisdictional limitations, making it globally applicable.",{"category":91,"check":124,"severity":24,"summary":125},"Runtime stability","The extension relies on the `agent-browser` CLI, which is cross-platform (macOS, Linux, Windows) and aims for broad compatibility. The SKILL.md explicitly states to use `agent-browser` directly, implying it's the intended runtime.",{"category":44,"check":127,"severity":24,"summary":128},"README","A comprehensive README exists, detailing installation, usage, commands, and integrations.",{"category":33,"check":130,"severity":131,"summary":132},"Tool surface size","not_applicable","This check is not applicable as the skill primarily orchestrates commands from the `agent-browser` CLI rather than exposing its own distinct tools.",{"category":40,"check":134,"severity":24,"summary":135},"Overlapping near-synonym tools","The `agent-browser` commands used (e.g., `open`, `click`, `fill`, `snapshot`) are distinct and do not present near-synonym overlap for similar actions.",{"category":44,"check":137,"severity":24,"summary":138},"Phantom features","All features described in the SKILL.md and README (e.g., systematic exploration, report generation, evidence collection) are directly implemented via `agent-browser` commands.",{"category":140,"check":141,"severity":24,"summary":142},"Install","Installation instruction","The README provides clear, copy-pasteable installation instructions for multiple platforms (npm, Homebrew, Cargo, source) and includes a quick start example.",{"category":144,"check":145,"severity":24,"summary":146},"Errors","Actionable error messages","The SKILL.md instructs to check for console errors and failed network requests, and the underlying `agent-browser` is designed to provide detailed error reporting.",{"category":103,"check":148,"severity":24,"summary":149},"Pinned dependencies","The project uses npm and has lockfile detection (`hasLockfile: true`), indicating that third-party dependencies are managed and pinned.",{"category":33,"check":151,"severity":131,"summary":152},"Dry-run preview","This skill does not perform state-changing operations or send data outward in a way that would typically require a dry-run preview. Its primary function is to capture and report existing states.",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","The `agent-browser` CLI itself manages timeouts and retries for its operations. The SKILL.md workflow does not involve complex state-changing operations that would require specific idempotency considerations beyond what the CLI provides.",{"category":117,"check":158,"severity":24,"summary":159},"Telemetry opt-in","The extension's workflow focuses on local reporting and does not include telemetry or outbound calls for tracking purposes. The README also details security features like content boundaries and domain allowlists, emphasizing opt-in controls.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The SKILL.md clearly defines the purpose (exploring web apps for bugs/UX issues) and when to use it ('dogfood', 'QA', 'exploratory test'), including explicit boundaries.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter is concise and effectively summarizes the core capability and provides clear trigger phrases.",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md is well-structured and stays within a reasonable length, deferring detailed procedures to sections and references.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The SKILL.md outlines the workflow and links to detailed steps and references like `issue-taxonomy.md`, demonstrating progressive disclosure.",{"category":170,"check":174,"severity":131,"summary":175},"Forked exploration","This skill's exploration is within the browser context and does not involve deep code review or file system exploration that would necessitate a `context: fork` setting.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The README provides numerous examples for core commands, and the SKILL.md details workflow steps with corresponding `agent-browser` commands, illustrating concrete usage.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The SKILL.md includes guidance on handling issues like authentication, OTP codes, and provides a detailed issue taxonomy with severity levels and categories, covering various failure modes.",{"category":110,"check":183,"severity":131,"summary":184},"Tool Fallback","The skill uses only the `agent-browser` CLI, which is the primary tool and does not have external dependencies requiring fallback mechanisms.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The SKILL.md emphasizes documenting issues as they are found and avoiding destructive operations mid-session, promoting a cautious approach to unexpected states.",{"category":91,"check":190,"severity":131,"summary":191},"Cross-skill coupling","This skill is self-contained and orchestrates the `agent-browser` CLI. It does not rely on other skills being loaded in the same session.",1778698472783,"This skill utilizes the agent-browser CLI to perform exploratory testing on web applications, systematically finding bugs and UX issues. It captures detailed evidence like screenshots, videos, and console logs, producing a structured report for bug tracking.",[195,196,197,198,199],"Systematic web application exploration","Automated bug and UX issue detection","Step-by-step reproduction evidence (screenshots, videos)","Structured issue reporting","Browser console error and network request logging",[201,202,203],"Automated end-to-end test script generation (focus is exploratory).","Performance load testing.","Security vulnerability scanning (beyond functional/visual issues).","3.0.0","4.4.0","To systematically explore and test web applications to uncover bugs, UX issues, and other problems, providing detailed, reproducible evidence for easy handover to development teams.","The extension is highly polished with comprehensive documentation, clear purpose, robust security features via the underlying agent-browser CLI, and active maintenance, leading to a verified tier.",99,"An expert-level skill for systematic web application testing and bug reporting.",[211,212,213,214,215,216],"web-testing","qa","automation","browser","debugging","reporting","global","verified",[220,221,222,223],"Use when asked to 'dogfood' an application.","Use when asked to perform QA or exploratory testing.","Use when asked to find issues or bug hunt on a web platform.","Use when asked to review the quality of a web application.",{"codeQuality":225,"collectedAt":227,"documentation":228,"maintenance":231,"popularity":237,"security":239,"testCoverage":242},{"hasLockfile":226},true,1778698453352,{"descriptionLength":229,"readmeSize":230},460,61552,{"closedIssues90d":232,"forks":233,"hasChangelog":226,"openIssues90d":234,"pushedAt":235,"stars":236},155,2035,142,1778168700000,32896,{"npmDownloads":238},2851726,{"hasNpmPackage":226,"license":240,"smitheryVerified":241},"Apache-2.0",false,{"hasCi":226,"hasTests":226},{"updatedAt":244},1778698472899,{"basePath":246,"githubOwner":247,"githubRepo":248,"locale":18,"slug":13,"type":249},"skill-data/dogfood","vercel-labs","agent-browser","skill",null,{"evaluate":252,"extract":254},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":253,"targetMarket":217,"tier":218},[211,212,213,214,215,216],{"commitSha":255},"HEAD",{"repoId":257},"kd74a6sfc26xa0ec2tpntj8r2986mn0a",{"_creationTime":259,"_id":257,"identity":260,"providers":261,"workflow":402},1778698380039.9202,{"githubOwner":247,"githubRepo":248,"sourceUrl":14},{"classify":262,"discover":394,"extract":397,"github":398,"npm":401},{"commitSha":255,"extensions":263},[264,280,291,300,331,340,348,360,368,375,386],{"basePath":265,"description":266,"displayName":248,"installMethods":267,"rationale":268,"selectedPaths":269,"source":278,"sourceLanguage":18,"type":279},"","Browser automation for AI agents",{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[270,273,275],{"path":271,"priority":272},".claude-plugin/marketplace.json","mandatory",{"path":274,"priority":272},"README.md",{"path":276,"priority":277},"LICENSE","high","rule","marketplace",{"basePath":265,"description":281,"displayName":248,"installMethods":282,"rationale":283,"selectedPaths":284,"source":278,"sourceLanguage":18,"type":290},"Automates browser interactions for web testing, form filling, screenshots, and data extraction",{"claudeCode":248},"inline plugin source from marketplace.json at /",[285,286,287],{"path":274,"priority":272},{"path":276,"priority":277},{"path":288,"priority":289},"bin/agent-browser.js","low","plugin",{"basePath":292,"description":293,"displayName":294,"installMethods":295,"rationale":296,"selectedPaths":297,"source":278,"sourceLanguage":18,"type":249},"skill-data/agentcore","Run agent-browser on AWS Bedrock AgentCore cloud browsers. Use when the user wants to use AgentCore, run browser automation on AWS, use a cloud browser with AWS credentials, or needs a managed browser session backed by AWS infrastructure. Triggers include \"use agentcore\", \"run on AWS\", \"cloud browser with AWS\", \"bedrock browser\", \"agentcore session\", or any task requiring AWS-hosted browser automation.","agentcore",{"claudeCode":12},"SKILL.md frontmatter at skill-data/agentcore/SKILL.md",[298],{"path":299,"priority":272},"SKILL.md",{"basePath":301,"description":302,"displayName":303,"installMethods":304,"rationale":305,"selectedPaths":306,"source":278,"sourceLanguage":18,"type":249},"skill-data/core","Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple browser sessions in parallel, and troubleshooting common failures. Use when the user asks to interact with a website, fill a form, click something, extract data, take a screenshot, log into a site, test a web app, or automate any browser task.","core",{"claudeCode":12},"SKILL.md frontmatter at skill-data/core/SKILL.md",[307,308,311,313,315,317,319,321,323,325,327,329],{"path":299,"priority":272},{"path":309,"priority":310},"references/authentication.md","medium",{"path":312,"priority":310},"references/commands.md",{"path":314,"priority":310},"references/profiling.md",{"path":316,"priority":310},"references/proxy-support.md",{"path":318,"priority":310},"references/session-management.md",{"path":320,"priority":310},"references/snapshot-refs.md",{"path":322,"priority":310},"references/trust-boundaries.md",{"path":324,"priority":310},"references/video-recording.md",{"path":326,"priority":289},"templates/authenticated-session.sh",{"path":328,"priority":289},"templates/capture-workflow.sh",{"path":330,"priority":289},"templates/form-automation.sh",{"basePath":246,"description":10,"displayName":13,"installMethods":332,"rationale":333,"selectedPaths":334,"source":278,"sourceLanguage":18,"type":249},{"claudeCode":12},"SKILL.md frontmatter at skill-data/dogfood/SKILL.md",[335,336,338],{"path":299,"priority":272},{"path":337,"priority":310},"references/issue-taxonomy.md",{"path":339,"priority":289},"templates/dogfood-report-template.md",{"basePath":341,"description":342,"displayName":343,"installMethods":344,"rationale":345,"selectedPaths":346,"source":278,"sourceLanguage":18,"type":249},"skill-data/electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","electron",{"claudeCode":12},"SKILL.md frontmatter at skill-data/electron/SKILL.md",[347],{"path":299,"priority":272},{"basePath":349,"description":350,"displayName":351,"installMethods":352,"rationale":353,"selectedPaths":354,"source":278,"sourceLanguage":18,"type":249},"skill-data/slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","slack",{"claudeCode":12},"SKILL.md frontmatter at skill-data/slack/SKILL.md",[355,356,358],{"path":299,"priority":272},{"path":357,"priority":310},"references/slack-tasks.md",{"path":359,"priority":289},"templates/slack-report-template.md",{"basePath":361,"description":362,"displayName":363,"installMethods":364,"rationale":365,"selectedPaths":366,"source":278,"sourceLanguage":18,"type":249},"skill-data/vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","vercel-sandbox",{"claudeCode":12},"SKILL.md frontmatter at skill-data/vercel-sandbox/SKILL.md",[367],{"path":299,"priority":272},{"basePath":369,"description":370,"displayName":248,"installMethods":371,"rationale":372,"selectedPaths":373,"source":278,"sourceLanguage":18,"type":249},"skills/agent-browser","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. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.",{"claudeCode":12},"SKILL.md frontmatter at skills/agent-browser/SKILL.md",[374],{"path":299,"priority":272},{"basePath":265,"description":376,"displayName":248,"installMethods":377,"license":240,"rationale":378,"selectedPaths":379,"source":278,"sourceLanguage":18,"type":385},"Browser automation CLI for AI agents",{"npm":248},"cli ecosystem detected at /",[380,382,383,384],{"path":381,"priority":272},"package.json",{"path":274,"priority":272},{"path":276,"priority":277},{"path":288,"priority":310},"cli",{"basePath":385,"installMethods":387,"rationale":388,"selectedPaths":389,"source":278,"sourceLanguage":18,"type":385},{"cargo":248},"cli ecosystem detected at cli",[390,392],{"path":391,"priority":272},"Cargo.toml",{"path":393,"priority":310},"src/main.rs",{"sources":395},[396],"manual",{"npmPackage":248},{"closedIssues90d":232,"description":376,"forks":233,"homepage":399,"license":240,"openIssues90d":234,"pushedAt":235,"readmeSize":230,"stars":236,"topics":400},"https://agent-browser.dev",[],{"downloads":238},{"classifiedAt":403,"discoverAt":404,"extractAt":405,"githubAt":405,"npmAt":406,"updatedAt":403},1778698387373,1778698380040,1778698383100,1778698385198,[213,214,215,212,216,211],{"evaluatedAt":244,"extractAt":409,"updatedAt":410},1778698388091,1778698676235,[],[413,443,469,498,529,556],{"_creationTime":414,"_id":415,"community":416,"display":417,"identity":423,"providers":428,"relations":436,"tags":438,"workflow":439},1778699106670.4268,"k179cgk616p3xva37r5jqsfwvh86mcp2",{"reviewCount":8},{"description":418,"installMethods":419,"name":421,"sourceUrl":422},"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":420},"xixu-me/skills","Use My Browser","https://github.com/xixu-me/skills",{"basePath":424,"githubOwner":425,"githubRepo":426,"locale":18,"slug":427,"type":249},"skills/use-my-browser","xixu-me","skills","use-my-browser",{"evaluate":429,"extract":434},{"promptVersionExtension":204,"promptVersionScoring":205,"score":430,"tags":431,"targetMarket":217,"tier":218},100,[214,215,213,432,433],"ux","developer-tools",{"commitSha":255,"license":435},"MIT",{"repoId":437},"kd77r2vb42jmgam0qbr9f2c6kn86mebv",[213,214,215,433,432],{"evaluatedAt":440,"extractAt":441,"updatedAt":442},1778699261239,1778699106670,1778699384978,{"_creationTime":444,"_id":445,"community":446,"display":447,"identity":453,"providers":457,"relations":463,"tags":465,"workflow":466},1778697652123.8857,"k179k1n5nw0md1x1j3dak31evn86mb5f",{"reviewCount":8},{"description":448,"installMethods":449,"name":451,"sourceUrl":452},"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":450},"steipete/clawdis","telegram-crabbox-e2e-proof","https://github.com/steipete/clawdis",{"basePath":454,"githubOwner":455,"githubRepo":456,"locale":18,"slug":451,"type":249},".agents/skills/telegram-crabbox-e2e-proof","steipete","clawdis",{"evaluate":458,"extract":462},{"promptVersionExtension":204,"promptVersionScoring":205,"score":430,"tags":459,"targetMarket":217,"tier":218},[460,461,213,212,385],"testing","telegram",{"commitSha":255},{"repoId":464},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[213,385,212,461,460],{"evaluatedAt":467,"extractAt":468,"updatedAt":467},1778698038113,1778697652123,{"_creationTime":470,"_id":471,"community":472,"display":473,"identity":479,"providers":483,"relations":491,"tags":494,"workflow":495},1778699018122.7856,"k170rwpkqsz8b50gnytayw5zj986maex",{"reviewCount":8},{"description":474,"installMethods":475,"name":477,"sourceUrl":478},"Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.",{"claudeCode":476},"wshobson/agents","screen-reader-testing","https://github.com/wshobson/agents",{"basePath":480,"githubOwner":481,"githubRepo":482,"locale":18,"slug":477,"type":249},"plugins/accessibility-compliance/skills/screen-reader-testing","wshobson","agents",{"evaluate":484,"extract":490},{"promptVersionExtension":204,"promptVersionScoring":205,"score":485,"tags":486,"targetMarket":217,"tier":218},98,[487,211,488,489,212],"accessibility","screen-reader","a11y",{"commitSha":255},{"parentExtensionId":492,"repoId":493},"k172w4j8rxzh1f0hc5qhwye5xx86msks","kd74de64zj0axtg5b8t7eqqe2x86nske",[489,487,212,488,211],{"evaluatedAt":496,"extractAt":497,"updatedAt":496},1778700360545,1778699018122,{"_creationTime":499,"_id":500,"community":501,"display":502,"identity":508,"providers":513,"relations":522,"tags":525,"workflow":526},1778699234184.6157,"k177tdbfgqmwhtaqv771f2ych586nne9",{"reviewCount":8},{"description":503,"installMethods":504,"name":506,"sourceUrl":507},"Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions",{"claudeCode":505},"Yeachan-Heo/oh-my-claudecode","Project Session Manager","https://github.com/Yeachan-Heo/oh-my-claudecode",{"basePath":509,"githubOwner":510,"githubRepo":511,"locale":18,"slug":512,"type":249},"skills/project-session-manager","Yeachan-Heo","oh-my-claudecode","project-session-manager",{"evaluate":514,"extract":521},{"promptVersionExtension":204,"promptVersionScoring":205,"score":430,"tags":515,"targetMarket":217,"tier":218},[516,517,518,519,213,385,520],"git","development-environment","workflow","tmux","developer-tool",{"commitSha":255,"license":435},{"parentExtensionId":523,"repoId":524},"k17brg5egdw1jbncj1j4wfv3fh86n639","kd74zv63fryf9prygtq7gf4es986n22y",[213,385,520,517,516,519,518],{"evaluatedAt":527,"extractAt":528,"updatedAt":527},1778699613343,1778699234184,{"_creationTime":530,"_id":531,"community":532,"display":533,"identity":539,"providers":541,"relations":549,"tags":551,"workflow":552},1778699468747.1746,"k1707pszx7h026a651dp5tvaxd86m3ag",{"reviewCount":8},{"description":534,"installMethods":535,"name":537,"sourceUrl":538},"Create public Google Docs or Google Sheet files without requiring OAuth. Use this skill to create and edit Google Docs and Sheets, no Google sign-in required. Documents are viewable at shareable links. Registration is automatic on first use.",{"claudeCode":536},"zagmoai/public-google-drive","public-google-drive","https://github.com/zagmoai/public-google-drive",{"basePath":265,"githubOwner":540,"githubRepo":537,"locale":18,"slug":537,"type":249},"zagmoai",{"evaluate":542,"extract":548},{"promptVersionExtension":204,"promptVersionScoring":205,"score":430,"tags":543,"targetMarket":217,"tier":218},[544,545,546,213,547],"google-docs","google-sheets","productivity","api-client",{"commitSha":255},{"repoId":550},"kd776ynh73t0d6samn4bnxdf3x86n8mj",[547,213,544,545,546],{"evaluatedAt":553,"extractAt":554,"updatedAt":555},1778699485884,1778699468747,1778699509178,{"_creationTime":557,"_id":558,"community":559,"display":560,"identity":563,"providers":566,"relations":574,"tags":575,"workflow":576},1778699234184.611,"k179b6dkc777g1rgyecze04wqn86m6y4",{"reviewCount":8},{"description":561,"installMethods":562,"name":511,"sourceUrl":507},"Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly",{"claudeCode":505},{"basePath":564,"githubOwner":510,"githubRepo":511,"locale":18,"slug":565,"type":249},"skills/ask","ask",{"evaluate":567,"extract":573},{"promptVersionExtension":204,"promptVersionScoring":205,"score":430,"tags":568,"targetMarket":217,"tier":218},[385,213,569,570,571,572],"llm","prompting","code-review","artifact-generation",{"commitSha":255,"license":435},{"parentExtensionId":523,"repoId":524},[572,213,385,571,569,570],{"evaluatedAt":577,"extractAt":528,"updatedAt":577},1778699303045]