[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-vercel-labs-agent-browser-en":3,"guides-for-vercel-labs-agent-browser":452,"similar-k1747f35gjnz60tye52m1aa5fh86nszq-en":453},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":246,"isFallback":242,"parentExtension":250,"providers":300,"relations":304,"repo":305,"tags":449,"workflow":450},1778698388090.9092,"k1747f35gjnz60tye52m1aa5fh86nszq",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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},"vercel-labs/agent-browser","agent-browser","https://github.com/vercel-labs/agent-browser",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":225,"workflow":244},1778698546309.7344,"kn774hsx9n7bp6ma11rt3wjth586n11k","en",{"checks":20,"evaluatedAt":195,"extensionSummary":196,"features":197,"nonGoals":203,"promptVersionExtension":206,"promptVersionScoring":207,"purpose":208,"rationale":209,"score":210,"summary":211,"tags":212,"targetMarket":218,"tier":219,"useCases":220},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,107,110,113,116,120,123,126,129,132,135,138,142,146,150,153,157,160,163,166,169,173,176,179,182,185,188,192],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of browser automation for AI agents and provides specific use cases and triggers.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The CLI is presented as a fast native Rust tool that works with any AI agent and offers features beyond typical browser automation wrappers, such as accessibility-tree snapshots and specialized skills.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The extension provides a complete lifecycle for browser automation, including installation, a wide range of commands, session management, authentication persistence, and debugging tools, making it production-ready.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The extension focuses on browser automation and related tasks like Electron app automation and Slack integration, which are coherently grouped under the umbrella of agent-driven web and desktop interaction.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the extension's capabilities as described in the SKILL.md and README files, detailing its purpose, triggers, and scope.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The CLI commands are generally narrow verb-noun specialists (e.g., `open`, `click`, `snapshot`), promoting precise selection by the agent.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","The README provides a comprehensive list of all commands, options, and parameters with detailed explanations and examples.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","Tool names are descriptive, verb-noun based, and follow kebab-case convention, clearly indicating their function.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","Command parameters are generally specific flags or structured arguments, and output is typically focused on the requested information, avoiding unnecessary dumps.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The project is licensed under Apache-2.0, a permissive open-source license, as indicated by the bundled LICENSE file and trust signals.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The last commit was 7 days ago, indicating active maintenance.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","The project uses npm and lists dependencies, and the presence of a lockfile (`codeQuality.hasLockfile: true`) suggests a mechanism for managing them.",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","The documentation details security features like an authentication vault, content boundary markers, and domain allowlisting, indicating appropriate measures for handling secrets.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","The documentation emphasizes content boundary markers (`--content-boundaries`) and security best practices, suggesting an approach to treat loaded data as untrusted.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","The project does not appear to fetch remote code or data at runtime; installation involves downloading a pre-built binary or dependencies managed by package managers, and the README indicates system dependencies can be installed separately.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","The extension operates as a CLI tool and its documentation focuses on browser automation within controlled sessions, with no indications of attempting to modify files outside its designated scope.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","No evidence of detached process spawns or deny-retry loops was found in the provided documentation or README.",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","Security documentation highlights features like content boundaries and domain allowlisting, indicating a focus on preventing unauthorized data exfiltration. No undocumented outbound calls are mentioned.",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","The bundled content and documentation appear to be free of hidden text tricks, Unicode tag characters, or other obfuscation methods.",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","The CLI is a native Rust binary, and any scripts or init files mentioned are likely plain JavaScript, with no indications of obfuscated code or runtime fetching of executable content.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The extension primarily interacts with web pages via selectors and CDP, and its installation and configuration mechanisms are standard, avoiding assumptions about specific user project structures.",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","With 142 issues opened and 155 closed in the last 90 days, the closure rate is above 50%, indicating good maintainer engagement.",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","The project has a `CHANGELOG.md` file and the trust signals indicate a recent `pushedAt` date, suggesting a clear versioning and release process.",{"category":103,"check":104,"severity":105,"summary":106},"Code Execution","Validation","not_applicable","As a CLI tool, validation of input arguments and output is handled by the Rust binary itself, rather than a schema library in the typical sense. No specific schema library usage is evident, but the CLI's structured commands imply internal validation.",{"category":65,"check":108,"severity":24,"summary":109},"Unguarded Destructive Operations","The documentation highlights security features like an action policy and confirmation prompts for sensitive actions, suggesting destructive operations are guarded.",{"category":103,"check":111,"severity":24,"summary":112},"Error Handling","The CLI structure and documentation for commands like `doctor` with a `--fix` option, as well as the use of `--json` for structured output, suggest robust error handling with clear messages and potential recovery steps.",{"category":103,"check":114,"severity":105,"summary":115},"Logging","As a CLI tool, logging of actions is typically handled by the shell's command history or explicit redirection, rather than an internal audit file for every invocation.",{"category":117,"check":118,"severity":24,"summary":119},"Compliance","GDPR","The extension's focus on browser automation and its security features like content boundaries suggest it does not inherently operate on personal data without appropriate handling, and direct submission of personal data is discouraged.",{"category":117,"check":121,"severity":24,"summary":122},"Target market","The extension is designed for general browser automation and AI agent integration, with no specific regional or jurisdictional logic detected, making it global in scope.",{"category":91,"check":124,"severity":24,"summary":125},"Runtime stability","The CLI is a native Rust binary and aims for cross-platform compatibility (macOS, Linux, Windows), with clear installation instructions for different environments.",{"category":44,"check":127,"severity":24,"summary":128},"README","The README file is extensive, well-organized, and clearly states the extension's purpose and capabilities.",{"category":33,"check":130,"severity":24,"summary":131},"Tool surface size","The CLI exposes a comprehensive set of tools, likely within the target range of 3-10 main commands with numerous options, fitting for its broad utility.",{"category":40,"check":133,"severity":24,"summary":134},"Overlapping near-synonym tools","While there are many commands, they appear to cover distinct functionalities, and commonly overlapping synonyms like 'search'/'find' are not present in a redundant manner.",{"category":44,"check":136,"severity":24,"summary":137},"Phantom features","All advertised features, such as command-line tools, specialized skills, and integration options, appear to have corresponding implementations described in the documentation.",{"category":139,"check":140,"severity":24,"summary":141},"Install","Installation instruction","The README provides clear, copy-pasteable installation instructions for multiple platforms (npm, Homebrew, Cargo, source) and includes invocation examples.",{"category":143,"check":144,"severity":24,"summary":145},"Errors","Actionable error messages","The `doctor` command with a `--fix` option and the general structure of CLI commands suggest that errors are likely to be actionable, providing guidance or remediation steps.",{"category":147,"check":148,"severity":24,"summary":149},"Execution","Pinned dependencies","The presence of a lockfile (`codeQuality.hasLockfile: true`) and the use of npm indicate that dependencies are likely pinned. Scripts would typically have shebangs for interpreters.",{"category":33,"check":151,"severity":105,"summary":152},"Dry-run preview","Many commands are state-changing, but the documentation does not explicitly mention a `--dry-run` flag for all of them; however, the focus on safety features suggests awareness of this concept.",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","The default operation timeout is documented as 25 seconds, and the CLI's architecture with a persistent daemon suggests commands are processed sequentially, allowing for timeouts and structured error handling.",{"category":117,"check":158,"severity":24,"summary":159},"Telemetry opt-in","The documentation emphasizes opt-in security features and user control, with no mention of default telemetry collection, implying any such feature would be opt-in.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The description clearly defines the extension as a browser automation CLI for AI agents and specifies numerous triggers and use cases, providing a precise understanding of its purpose.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter in SKILL.md is concise and self-contained, providing a summary of the core capability and trigger phrases without excessive verbosity.",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md file is a stub that directs users to load full content via the CLI, keeping the file itself concise and avoiding bloat.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The SKILL.md acts as a discovery stub, directing users to load detailed content via `agent-browser skills get core`, embodying progressive disclosure.",{"category":170,"check":174,"severity":105,"summary":175},"Forked exploration","This is a CLI tool, not a skill that performs deep exploration within a conversation context requiring `context: fork`.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The README provides extensive, end-to-end examples for almost every command and feature, demonstrating inputs, invocations, and expected outcomes.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The documentation covers various scenarios, including authentication, session management, error handling, and browser engine choices, implying handling of edge cases and limitations.",{"category":103,"check":183,"severity":24,"summary":184},"Tool Fallback","The README details integrations with cloud providers (Browserless, Browserbase, Kernel, AgentCore) and mentions using a custom executable path, suggesting flexibility and potential fallbacks or clear requirements.",{"category":91,"check":186,"severity":24,"summary":187},"Stack assumptions","Installation instructions cover multiple platforms and dependencies, and the native Rust CLI is platform-agnostic, minimizing stack assumptions.",{"category":189,"check":190,"severity":24,"summary":191},"Safety","Halt on unexpected state","The presence of a `doctor` command with a `--fix` option and the CLI's structured command execution suggest mechanisms to detect and report unexpected states.",{"category":91,"check":193,"severity":24,"summary":194},"Cross-skill coupling","The extension is a standalone CLI tool and does not appear to rely on other specific skills being loaded in the same session.",1778698546194,"This is a fast, native Rust CLI tool for browser automation, designed to work with AI agents. It supports Chrome/Chromium via CDP, offers accessibility-tree snapshots, specialized skills for Electron apps and Slack, and robust features for authentication, session persistence, and debugging.",[198,199,200,201,202],"Browser automation via CLI","Accessibility tree snapshots with element refs","Specialized skills for Electron, Slack, cloud providers","Session persistence and authentication vault","Extensive command set for web interaction",[204,205],"Replacing built-in browser automation or web tools","Acting as a general-purpose shell or scripting tool outside of browser automation","3.0.0","4.4.0","To provide AI agents with a powerful and reliable tool for interacting with websites and automating browser-based tasks.","The extension is a mature, well-documented, and actively maintained CLI tool with a strong focus on security and usability. All checks passed or were not applicable, indicating high quality.",98,"A highly polished and feature-rich browser automation CLI for AI agents.",[213,214,215,216,217],"browser-automation","cli","web-testing","automation","ai-agent","global","verified",[221,222,223,224],"Automating web navigation, form filling, and button clicks","Scraping data from web pages","Testing web applications and exploratory testing","Automating Electron desktop applications",{"codeQuality":226,"collectedAt":228,"documentation":229,"maintenance":232,"popularity":238,"security":240,"testCoverage":243},{"hasLockfile":227},true,1778698527980,{"descriptionLength":230,"readmeSize":231},925,61552,{"closedIssues90d":233,"forks":234,"hasChangelog":227,"openIssues90d":235,"pushedAt":236,"stars":237},155,2035,142,1778168700000,32896,{"npmDownloads":239},2851726,{"hasNpmPackage":227,"license":241,"smitheryVerified":242},"Apache-2.0",false,{"hasCi":227,"hasTests":227},{"updatedAt":245},1778698546309,{"basePath":247,"githubOwner":248,"githubRepo":13,"locale":18,"slug":13,"type":249},"skills/agent-browser","vercel-labs","skill",{"_creationTime":251,"_id":252,"community":253,"display":254,"identity":257,"parentExtension":260,"providers":289,"relations":295,"tags":296,"workflow":297},1778698388090.9075,"k175gma4kma3radvem5pa46wgn86nd1b",{"reviewCount":8},{"description":255,"installMethods":256,"name":13,"sourceUrl":14},"Automates browser interactions for web testing, form filling, screenshots, and data extraction",{"claudeCode":13},{"basePath":258,"githubOwner":248,"githubRepo":13,"locale":18,"slug":13,"type":259},"","plugin",{"_creationTime":261,"_id":262,"community":263,"display":264,"identity":267,"providers":269,"relations":282,"tags":284,"workflow":285},1778698388090.9072,"k171hvn0e2t3jzczxm3vzspj3186mgj7",{"reviewCount":8},{"description":265,"installMethods":266,"name":13,"sourceUrl":14},"Browser automation for AI agents",{"claudeCode":12},{"basePath":258,"githubOwner":248,"githubRepo":13,"locale":18,"slug":13,"type":268},"marketplace",{"evaluate":270,"extract":276},{"promptVersionExtension":271,"promptVersionScoring":207,"score":272,"tags":273,"targetMarket":218,"tier":219},"3.1.0",99,[213,214,274,275,217],"webdriver","testing",{"commitSha":277,"marketplace":278,"plugin":280},"HEAD",{"name":13,"pluginCount":279},1,{"mcpCount":8,"provider":281,"skillCount":8},"classify",{"repoId":283},"kd74a6sfc26xa0ec2tpntj8r2986mn0a",[217,213,214,275,274],{"evaluatedAt":286,"extractAt":287,"updatedAt":288},1778698406247,1778698388091,1778698675865,{"evaluate":290,"extract":293},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":291,"targetMarket":218,"tier":219},[213,215,214,216,292],"web-scraping",{"commitSha":277,"plugin":294},{"mcpCount":8,"provider":281,"skillCount":279},{"parentExtensionId":262,"repoId":283},[216,213,214,292,215],{"evaluatedAt":298,"extractAt":287,"updatedAt":299},1778698422911,1778698675646,{"evaluate":301,"extract":303},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":302,"targetMarket":218,"tier":219},[213,214,215,216,217],{"commitSha":277},{"parentExtensionId":252,"repoId":283},{"_creationTime":306,"_id":283,"identity":307,"providers":308,"workflow":444},1778698380039.9202,{"githubOwner":248,"githubRepo":13,"sourceUrl":14},{"classify":309,"discover":436,"extract":439,"github":440,"npm":443},{"commitSha":277,"extensions":310},[311,324,333,342,373,385,393,405,413,418,428],{"basePath":258,"description":265,"displayName":13,"installMethods":312,"rationale":313,"selectedPaths":314,"source":323,"sourceLanguage":18,"type":268},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[315,318,320],{"path":316,"priority":317},".claude-plugin/marketplace.json","mandatory",{"path":319,"priority":317},"README.md",{"path":321,"priority":322},"LICENSE","high","rule",{"basePath":258,"description":255,"displayName":13,"installMethods":325,"rationale":326,"selectedPaths":327,"source":323,"sourceLanguage":18,"type":259},{"claudeCode":13},"inline plugin source from marketplace.json at /",[328,329,330],{"path":319,"priority":317},{"path":321,"priority":322},{"path":331,"priority":332},"bin/agent-browser.js","low",{"basePath":334,"description":335,"displayName":336,"installMethods":337,"rationale":338,"selectedPaths":339,"source":323,"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",[340],{"path":341,"priority":317},"SKILL.md",{"basePath":343,"description":344,"displayName":345,"installMethods":346,"rationale":347,"selectedPaths":348,"source":323,"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",[349,350,353,355,357,359,361,363,365,367,369,371],{"path":341,"priority":317},{"path":351,"priority":352},"references/authentication.md","medium",{"path":354,"priority":352},"references/commands.md",{"path":356,"priority":352},"references/profiling.md",{"path":358,"priority":352},"references/proxy-support.md",{"path":360,"priority":352},"references/session-management.md",{"path":362,"priority":352},"references/snapshot-refs.md",{"path":364,"priority":352},"references/trust-boundaries.md",{"path":366,"priority":352},"references/video-recording.md",{"path":368,"priority":332},"templates/authenticated-session.sh",{"path":370,"priority":332},"templates/capture-workflow.sh",{"path":372,"priority":332},"templates/form-automation.sh",{"basePath":374,"description":375,"displayName":376,"installMethods":377,"rationale":378,"selectedPaths":379,"source":323,"sourceLanguage":18,"type":249},"skill-data/dogfood","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.","dogfood",{"claudeCode":12},"SKILL.md frontmatter at skill-data/dogfood/SKILL.md",[380,381,383],{"path":341,"priority":317},{"path":382,"priority":352},"references/issue-taxonomy.md",{"path":384,"priority":332},"templates/dogfood-report-template.md",{"basePath":386,"description":387,"displayName":388,"installMethods":389,"rationale":390,"selectedPaths":391,"source":323,"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",[392],{"path":341,"priority":317},{"basePath":394,"description":395,"displayName":396,"installMethods":397,"rationale":398,"selectedPaths":399,"source":323,"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",[400,401,403],{"path":341,"priority":317},{"path":402,"priority":352},"references/slack-tasks.md",{"path":404,"priority":332},"templates/slack-report-template.md",{"basePath":406,"description":407,"displayName":408,"installMethods":409,"rationale":410,"selectedPaths":411,"source":323,"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",[412],{"path":341,"priority":317},{"basePath":247,"description":10,"displayName":13,"installMethods":414,"rationale":415,"selectedPaths":416,"source":323,"sourceLanguage":18,"type":249},{"claudeCode":12},"SKILL.md frontmatter at skills/agent-browser/SKILL.md",[417],{"path":341,"priority":317},{"basePath":258,"description":419,"displayName":13,"installMethods":420,"license":241,"rationale":421,"selectedPaths":422,"source":323,"sourceLanguage":18,"type":214},"Browser automation CLI for AI agents",{"npm":13},"cli ecosystem detected at /",[423,425,426,427],{"path":424,"priority":317},"package.json",{"path":319,"priority":317},{"path":321,"priority":322},{"path":331,"priority":352},{"basePath":214,"installMethods":429,"rationale":430,"selectedPaths":431,"source":323,"sourceLanguage":18,"type":214},{"cargo":13},"cli ecosystem detected at cli",[432,434],{"path":433,"priority":317},"Cargo.toml",{"path":435,"priority":352},"src/main.rs",{"sources":437},[438],"manual",{"npmPackage":13},{"closedIssues90d":233,"description":419,"forks":234,"homepage":441,"license":241,"openIssues90d":235,"pushedAt":236,"readmeSize":231,"stars":237,"topics":442},"https://agent-browser.dev",[],{"downloads":239},{"classifiedAt":445,"discoverAt":446,"extractAt":447,"githubAt":447,"npmAt":448,"updatedAt":445},1778698387373,1778698380040,1778698383100,1778698385198,[217,216,213,214,215],{"evaluatedAt":245,"extractAt":287,"updatedAt":451},1778698677055,[],[454,479,507,539,561,587],{"_creationTime":455,"_id":456,"community":457,"display":458,"identity":463,"providers":467,"relations":472,"tags":474,"workflow":475},1778697205743.894,"k17ej9360g7468qswf3svnrx9186m1ng",{"reviewCount":8},{"description":459,"installMethods":460,"name":13,"sourceUrl":462},"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":461},"shanraisshan/claude-code-best-practice","https://github.com/shanraisshan/claude-code-best-practice",{"basePath":464,"githubOwner":465,"githubRepo":466,"locale":18,"slug":13,"type":249},".claude/skills/agent-browser","shanraisshan","claude-code-best-practice",{"evaluate":468,"extract":471},{"promptVersionExtension":206,"promptVersionScoring":207,"score":469,"tags":470,"targetMarket":218,"tier":219},100,[213,292,275,214,216],{"commitSha":277},{"repoId":473},"kd74710g49kxgwbfjxeb7s132d86myxr",[216,213,214,275,292],{"evaluatedAt":476,"extractAt":477,"updatedAt":478},1778697222051,1778697205743,1778697438718,{"_creationTime":480,"_id":481,"community":482,"display":483,"identity":489,"providers":493,"relations":500,"tags":503,"workflow":504},1778696833339.6243,"k174g80xa9zxhydbncvpf0xzy986nvx5",{"reviewCount":8},{"description":484,"installMethods":485,"name":487,"sourceUrl":488},"Delegate complex, long-running tasks to Manus AI agent for autonomous execution. Use when user says 'use manus', 'delegate to manus', 'send to manus', 'have manus do', 'ask manus', 'check manus sessions', or when tasks require deep web research, market analysis, product comparisons, stock analysis, competitive research, document generation, data analysis, or multi-step workflows that benefit from autonomous agent execution with parallel processing.",{"claudeCode":486},"sanjay3290/ai-skills","manus","https://github.com/sanjay3290/ai-skills",{"basePath":490,"githubOwner":491,"githubRepo":492,"locale":18,"slug":487,"type":249},"skills/manus","sanjay3290","ai-skills",{"evaluate":494,"extract":499},{"promptVersionExtension":206,"promptVersionScoring":207,"score":469,"tags":495,"targetMarket":218,"tier":219},[217,496,497,216,498],"autonomous-execution","research","api-integration",{"commitSha":277},{"parentExtensionId":501,"repoId":502},"k17es37z10n1sw6t2m3f0vsydx86mnje","kd71np0fyqg23qg8w2hcfw0h0h86nkn0",[217,498,216,496,497],{"evaluatedAt":505,"extractAt":506,"updatedAt":505},1778697107270,1778696833339,{"_creationTime":508,"_id":509,"community":510,"display":511,"identity":517,"providers":522,"relations":532,"tags":535,"workflow":536},1778699234184.6157,"k177tdbfgqmwhtaqv771f2ych586nne9",{"reviewCount":8},{"description":512,"installMethods":513,"name":515,"sourceUrl":516},"Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions",{"claudeCode":514},"Yeachan-Heo/oh-my-claudecode","Project Session Manager","https://github.com/Yeachan-Heo/oh-my-claudecode",{"basePath":518,"githubOwner":519,"githubRepo":520,"locale":18,"slug":521,"type":249},"skills/project-session-manager","Yeachan-Heo","oh-my-claudecode","project-session-manager",{"evaluate":523,"extract":530},{"promptVersionExtension":206,"promptVersionScoring":207,"score":469,"tags":524,"targetMarket":218,"tier":219},[525,526,527,528,216,214,529],"git","development-environment","workflow","tmux","developer-tool",{"commitSha":277,"license":531},"MIT",{"parentExtensionId":533,"repoId":534},"k17brg5egdw1jbncj1j4wfv3fh86n639","kd74zv63fryf9prygtq7gf4es986n22y",[216,214,529,526,525,528,527],{"evaluatedAt":537,"extractAt":538,"updatedAt":537},1778699613343,1778699234184,{"_creationTime":540,"_id":541,"community":542,"display":543,"identity":546,"providers":549,"relations":557,"tags":558,"workflow":559},1778699234184.611,"k179b6dkc777g1rgyecze04wqn86m6y4",{"reviewCount":8},{"description":544,"installMethods":545,"name":520,"sourceUrl":516},"Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly",{"claudeCode":514},{"basePath":547,"githubOwner":519,"githubRepo":520,"locale":18,"slug":548,"type":249},"skills/ask","ask",{"evaluate":550,"extract":556},{"promptVersionExtension":206,"promptVersionScoring":207,"score":469,"tags":551,"targetMarket":218,"tier":219},[214,216,552,553,554,555],"llm","prompting","code-review","artifact-generation",{"commitSha":277,"license":531},{"parentExtensionId":533,"repoId":534},[555,216,214,554,552,553],{"evaluatedAt":560,"extractAt":538,"updatedAt":560},1778699303045,{"_creationTime":562,"_id":563,"community":564,"display":565,"identity":571,"providers":575,"relations":581,"tags":583,"workflow":584},1778697652123.8928,"k171pew5empzzrfghyg9nqrk6n86nqa9",{"reviewCount":8},{"description":566,"installMethods":567,"name":569,"sourceUrl":570},"Use gh for GitHub issues, PR status, CI/logs, comments, reviews, releases, and API queries.",{"claudeCode":568},"steipete/clawdis","github","https://github.com/steipete/clawdis",{"basePath":572,"githubOwner":573,"githubRepo":574,"locale":18,"slug":569,"type":249},"skills/github","steipete","clawdis",{"evaluate":576,"extract":580},{"promptVersionExtension":206,"promptVersionScoring":207,"score":469,"tags":577,"targetMarket":218,"tier":219},[569,214,578,579,216],"api","developer-tools",{"commitSha":277},{"repoId":582},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[578,216,214,579,569],{"evaluatedAt":585,"extractAt":586,"updatedAt":585},1778698569289,1778697652123,{"_creationTime":588,"_id":589,"community":590,"display":591,"identity":595,"providers":597,"relations":603,"tags":604,"workflow":605},1778697652123.8857,"k179k1n5nw0md1x1j3dak31evn86mb5f",{"reviewCount":8},{"description":592,"installMethods":593,"name":594,"sourceUrl":570},"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":568},"telegram-crabbox-e2e-proof",{"basePath":596,"githubOwner":573,"githubRepo":574,"locale":18,"slug":594,"type":249},".agents/skills/telegram-crabbox-e2e-proof",{"evaluate":598,"extract":602},{"promptVersionExtension":206,"promptVersionScoring":207,"score":469,"tags":599,"targetMarket":218,"tier":219},[275,600,216,601,214],"telegram","qa",{"commitSha":277},{"repoId":582},[216,214,601,600,275],{"evaluatedAt":606,"extractAt":586,"updatedAt":606},1778698038113]