[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-vercel-labs-slack-en":3,"guides-for-vercel-labs-slack":417,"similar-k175jjsqj2p1he1cnp97qv600x86m87w-en":418},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":253,"isFallback":249,"parentExtension":257,"providers":258,"relations":263,"repo":265,"tags":413,"workflow":414},1778698388090.9087,"k175jjsqj2p1he1cnp97qv600x86m87w",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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.",{"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":232,"workflow":251},1778698509141.3208,"kn74jnff0jtyjakh9wk0y9347x86negc","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"practices":205,"prerequisites":209,"promptVersionExtension":212,"promptVersionScoring":213,"purpose":214,"rationale":215,"score":216,"summary":217,"tags":218,"targetMarket":224,"tier":225,"useCases":226},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,113,116,121,124,127,130,133,136,139,143,147,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of interacting with Slack workspaces using browser automation and provides specific use cases and triggers.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers significant value beyond basic LLM capabilities by providing a specialized tool for browser automation specifically tailored for Slack, enabling complex interactions not easily achievable with general prompts.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The extension provides a complete lifecycle for interacting with Slack via browser automation, from connection and navigation to data extraction and reporting, making it ready for use in real workflows.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill is focused solely on browser automation for Slack, aligning with its name and description without venturing into unrelated domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the skill's capabilities, is concise, readable, and includes relevant triggers and use cases.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The skill exposes narrow verb-noun tools like 'connect', 'open', 'click', 'snapshot', etc., which are specific to browser automation tasks.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","The SKILL.md provides comprehensive documentation for its commands, including parameters and usage examples.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","The tool names like 'connect', 'open', 'click', 'snapshot', 'fill' are descriptive, follow kebab-case, and are clearly related to browser automation.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","Input parameters like selectors, text, and URLs are specific to the task, and output, such as JSON snapshots or screenshots, is focused and documented.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The extension is licensed under Apache-2.0, a permissive open-source license, with the license text provided in a dedicated LICENSE file.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The repository shows recent commits within the last 90 days, indicating active maintenance.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","The project uses npm for package management and has a lockfile, indicating good dependency management practices.",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","The tool does not appear to handle secrets directly; it automates browser interactions and does not echo resolved secret values.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","The tool's design focuses on executing browser commands and does not appear to load or execute arbitrary third-party data as instructions.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","The tool relies on bundled dependencies and does not fetch external code or data at runtime for execution.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","The tool operates within the browser sandbox and does not modify files outside its designated scope.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","No detached process spawns or retry loops around denied tool calls were found in the scripts.",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","The tool automates browser actions and does not include instructions to read or submit confidential data to third parties.",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","Bundled content and descriptions are free of hidden steering tricks, invisible Unicode characters, or other obfuscation techniques.",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","The bundled scripts are in plain, readable Rust and JavaScript, with no obfuscation like base64 decoding or runtime fetches.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The tool's scripts and instructions do not make structural assumptions about user project organization, using relative paths or placeholders where necessary.",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","The number of open and closed issues in the last 90 days, along with the closure rate, indicates active maintainer engagement.",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","The project uses npm for installation and management, has a clear LICENSE file, and the README indicates version updates are managed.",{"category":103,"check":104,"severity":24,"summary":105},"Execution","Validation","The tool uses selectors and parameters that are well-defined and validated, ensuring predictable behavior.",{"category":65,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","The tool is primarily for browser automation and does not expose destructive primitives like 'rm -rf' or 'git push --force'.",{"category":110,"check":111,"severity":24,"summary":112},"Code Execution","Error Handling","The tool is designed with clear commands and expected outputs, and errors are likely to be reported through standard mechanisms.",{"category":110,"check":114,"severity":24,"summary":115},"Logging","While not explicitly detailed, the CLI nature and integration with AI agents suggest logging capabilities for auditing actions.",{"category":117,"check":118,"severity":119,"summary":120},"Compliance","GDPR","not_applicable","The tool automates browser interactions and does not inherently operate on personal data without user action or configuration.",{"category":117,"check":122,"severity":24,"summary":123},"Target market","The tool is a general-purpose browser automation utility with no apparent regional or jurisdictional restrictions, making it global.",{"category":91,"check":125,"severity":24,"summary":126},"Runtime stability","The tool is written in Rust and is designed to be cross-platform, with clear installation instructions for various OS.",{"category":44,"check":128,"severity":24,"summary":129},"README","A comprehensive README exists and clearly states the extension's purpose, installation, and usage.",{"category":33,"check":131,"severity":24,"summary":132},"Tool surface size","The CLI exposes a well-defined set of commands within the expected range for a tool of this nature.",{"category":40,"check":134,"severity":24,"summary":135},"Overlapping near-synonym tools","The tool commands are distinct and do not suffer from near-synonym names that would cause confusion.",{"category":44,"check":137,"severity":24,"summary":138},"Phantom features","All features advertised in the README, such as browser automation commands and AI integration, have corresponding implementations.",{"category":140,"check":141,"severity":24,"summary":142},"Install","Installation instruction","The README provides clear, copy-pasteable installation and invocation examples for multiple platforms, including authentication details.",{"category":144,"check":145,"severity":24,"summary":146},"Errors","Actionable error messages","The tool provides detailed CLI output and errors, which are crucial for debugging automation scripts.",{"category":103,"check":148,"severity":24,"summary":149},"Pinned dependencies","The project utilizes npm and includes a lockfile, indicating that dependencies are pinned.",{"category":33,"check":151,"severity":119,"summary":152},"Dry-run preview","The tool's primary function is browser automation, which inherently involves direct interaction and state changes, making a dry-run preview not applicable for most commands.",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","The tool allows for command chaining and specifies default timeouts, supporting robust automation workflows.",{"category":117,"check":158,"severity":24,"summary":159},"Telemetry opt-in","The tool's documentation does not indicate any telemetry collection, and any such features would likely be opt-in based on its design principles.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The skill clearly defines its purpose as Slack automation via browser interaction and provides specific triggers and use cases.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter is dense and directly states the core capability and triggers, adhering to routing precision guidelines.",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md is well-structured and utilizes linked reference files for deeper explanations, keeping the main body concise.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The SKILL.md effectively uses linked reference files for detailed task procedures, demonstrating good progressive disclosure.",{"category":170,"check":174,"severity":119,"summary":175},"Forked exploration","This skill is for direct browser automation and does not involve deep code review or multi-file inspection requiring a forked exploration context.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The SKILL.md and README provide numerous end-to-end examples for common Slack tasks and agent-browser commands, demonstrating plausible output.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The documentation addresses limitations such as Slack API access, session specificity, and rate limiting, with suggested recovery steps.",{"category":110,"check":183,"severity":119,"summary":184},"Tool Fallback","This skill is a standalone CLI tool and does not rely on optional external MCP servers with fallback paths.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The documentation implies that unexpected states or missing elements would result in script failures or errors, implicitly halting the workflow.",{"category":91,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The skill is self-contained for Slack automation and does not implicitly rely on other skills; any cross-references would be explicit.",1778698508298,"This is a command-line interface (CLI) tool built in Rust that uses browser automation to interact with Slack workspaces. It allows users to perform tasks such as checking unread channels, navigating Slack, sending messages, extracting data, searching conversations, and automating other Slack-related workflows.",[195,196,197,198,199],"Browser automation for Slack","Navigate and interact with Slack UI","Extract data and search conversations","Automate Slack tasks","Generate reports from Slack data",[201,202,203,204],"Interacting with the Slack API directly.","Performing cross-workspace automation.","Replacing official Slack clients for direct user interaction.","Automating tasks outside of the browser context.",[206,207,208],"Browser Automation","Web Scraping","Task Automation",[210,211],"A browser (Chrome/Chromium recommended, downloaded via `agent-browser install`)","A Slack workspace accessible via web browser","3.0.0","4.4.0","To enable programmatic interaction with Slack workspaces through browser automation, facilitating tasks that are difficult or tedious to perform manually.","The extension is exceptionally well-documented with clear examples, robust error handling, and a strong focus on security and usability. No critical or warning findings were identified.",99,"A high-quality CLI tool for automating Slack interactions via browser automation.",[219,220,221,222,223],"browser-automation","slack","cli","automation","web-scraping","global","verified",[227,228,229,230,231],"Checking unread channels and messages.","Navigating to specific channels or conversations.","Searching Slack for information or messages.","Extracting data from Slack conversations or user profiles.","Automating repetitive Slack interactions.",{"codeQuality":233,"collectedAt":235,"documentation":236,"maintenance":239,"popularity":245,"security":247,"testCoverage":250},{"hasLockfile":234},true,1778698489688,{"descriptionLength":237,"readmeSize":238},418,61552,{"closedIssues90d":240,"forks":241,"hasChangelog":234,"openIssues90d":242,"pushedAt":243,"stars":244},155,2035,142,1778168700000,32896,{"npmDownloads":246},2851726,{"hasNpmPackage":234,"license":248,"smitheryVerified":249},"Apache-2.0",false,{"hasCi":234,"hasTests":234},{"updatedAt":252},1778698509141,{"basePath":254,"githubOwner":255,"githubRepo":13,"locale":18,"slug":220,"type":256},"skill-data/slack","vercel-labs","skill",null,{"evaluate":259,"extract":261},{"promptVersionExtension":212,"promptVersionScoring":213,"score":216,"tags":260,"targetMarket":224,"tier":225},[219,220,221,222,223],{"commitSha":262,"license":248},"HEAD",{"repoId":264},"kd74a6sfc26xa0ec2tpntj8r2986mn0a",{"_creationTime":266,"_id":264,"identity":267,"providers":268,"workflow":408},1778698380039.9202,{"githubOwner":255,"githubRepo":13,"sourceUrl":14},{"classify":269,"discover":400,"extract":403,"github":404,"npm":407},{"commitSha":262,"extensions":270},[271,287,298,307,338,350,358,367,375,382,392],{"basePath":272,"description":273,"displayName":13,"installMethods":274,"rationale":275,"selectedPaths":276,"source":285,"sourceLanguage":18,"type":286},"","Browser automation for AI agents",{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[277,280,282],{"path":278,"priority":279},".claude-plugin/marketplace.json","mandatory",{"path":281,"priority":279},"README.md",{"path":283,"priority":284},"LICENSE","high","rule","marketplace",{"basePath":272,"description":288,"displayName":13,"installMethods":289,"rationale":290,"selectedPaths":291,"source":285,"sourceLanguage":18,"type":297},"Automates browser interactions for web testing, form filling, screenshots, and data extraction",{"claudeCode":13},"inline plugin source from marketplace.json at /",[292,293,294],{"path":281,"priority":279},{"path":283,"priority":284},{"path":295,"priority":296},"bin/agent-browser.js","low","plugin",{"basePath":299,"description":300,"displayName":301,"installMethods":302,"rationale":303,"selectedPaths":304,"source":285,"sourceLanguage":18,"type":256},"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",[305],{"path":306,"priority":279},"SKILL.md",{"basePath":308,"description":309,"displayName":310,"installMethods":311,"rationale":312,"selectedPaths":313,"source":285,"sourceLanguage":18,"type":256},"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",[314,315,318,320,322,324,326,328,330,332,334,336],{"path":306,"priority":279},{"path":316,"priority":317},"references/authentication.md","medium",{"path":319,"priority":317},"references/commands.md",{"path":321,"priority":317},"references/profiling.md",{"path":323,"priority":317},"references/proxy-support.md",{"path":325,"priority":317},"references/session-management.md",{"path":327,"priority":317},"references/snapshot-refs.md",{"path":329,"priority":317},"references/trust-boundaries.md",{"path":331,"priority":317},"references/video-recording.md",{"path":333,"priority":296},"templates/authenticated-session.sh",{"path":335,"priority":296},"templates/capture-workflow.sh",{"path":337,"priority":296},"templates/form-automation.sh",{"basePath":339,"description":340,"displayName":341,"installMethods":342,"rationale":343,"selectedPaths":344,"source":285,"sourceLanguage":18,"type":256},"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",[345,346,348],{"path":306,"priority":279},{"path":347,"priority":317},"references/issue-taxonomy.md",{"path":349,"priority":296},"templates/dogfood-report-template.md",{"basePath":351,"description":352,"displayName":353,"installMethods":354,"rationale":355,"selectedPaths":356,"source":285,"sourceLanguage":18,"type":256},"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",[357],{"path":306,"priority":279},{"basePath":254,"description":10,"displayName":220,"installMethods":359,"rationale":360,"selectedPaths":361,"source":285,"sourceLanguage":18,"type":256},{"claudeCode":12},"SKILL.md frontmatter at skill-data/slack/SKILL.md",[362,363,365],{"path":306,"priority":279},{"path":364,"priority":317},"references/slack-tasks.md",{"path":366,"priority":296},"templates/slack-report-template.md",{"basePath":368,"description":369,"displayName":370,"installMethods":371,"rationale":372,"selectedPaths":373,"source":285,"sourceLanguage":18,"type":256},"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",[374],{"path":306,"priority":279},{"basePath":376,"description":377,"displayName":13,"installMethods":378,"rationale":379,"selectedPaths":380,"source":285,"sourceLanguage":18,"type":256},"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",[381],{"path":306,"priority":279},{"basePath":272,"description":383,"displayName":13,"installMethods":384,"license":248,"rationale":385,"selectedPaths":386,"source":285,"sourceLanguage":18,"type":221},"Browser automation CLI for AI agents",{"npm":13},"cli ecosystem detected at /",[387,389,390,391],{"path":388,"priority":279},"package.json",{"path":281,"priority":279},{"path":283,"priority":284},{"path":295,"priority":317},{"basePath":221,"installMethods":393,"rationale":394,"selectedPaths":395,"source":285,"sourceLanguage":18,"type":221},{"cargo":13},"cli ecosystem detected at cli",[396,398],{"path":397,"priority":279},"Cargo.toml",{"path":399,"priority":317},"src/main.rs",{"sources":401},[402],"manual",{"npmPackage":13},{"closedIssues90d":240,"description":383,"forks":241,"homepage":405,"license":248,"openIssues90d":242,"pushedAt":243,"readmeSize":238,"stars":244,"topics":406},"https://agent-browser.dev",[],{"downloads":246},{"classifiedAt":409,"discoverAt":410,"extractAt":411,"githubAt":411,"npmAt":412,"updatedAt":409},1778698387373,1778698380040,1778698383100,1778698385198,[222,219,221,220,223],{"evaluatedAt":252,"extractAt":415,"updatedAt":416},1778698388091,1778698676695,[],[419,445,477,499,525,544],{"_creationTime":420,"_id":421,"community":422,"display":423,"identity":428,"providers":432,"relations":438,"tags":440,"workflow":441},1778697205743.894,"k17ej9360g7468qswf3svnrx9186m1ng",{"reviewCount":8},{"description":424,"installMethods":425,"name":13,"sourceUrl":427},"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":426},"shanraisshan/claude-code-best-practice","https://github.com/shanraisshan/claude-code-best-practice",{"basePath":429,"githubOwner":430,"githubRepo":431,"locale":18,"slug":13,"type":256},".claude/skills/agent-browser","shanraisshan","claude-code-best-practice",{"evaluate":433,"extract":437},{"promptVersionExtension":212,"promptVersionScoring":213,"score":434,"tags":435,"targetMarket":224,"tier":225},100,[219,223,436,221,222],"testing",{"commitSha":262},{"repoId":439},"kd74710g49kxgwbfjxeb7s132d86myxr",[222,219,221,436,223],{"evaluatedAt":442,"extractAt":443,"updatedAt":444},1778697222051,1778697205743,1778697438718,{"_creationTime":446,"_id":447,"community":448,"display":449,"identity":455,"providers":460,"relations":470,"tags":473,"workflow":474},1778699234184.6157,"k177tdbfgqmwhtaqv771f2ych586nne9",{"reviewCount":8},{"description":450,"installMethods":451,"name":453,"sourceUrl":454},"Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions",{"claudeCode":452},"Yeachan-Heo/oh-my-claudecode","Project Session Manager","https://github.com/Yeachan-Heo/oh-my-claudecode",{"basePath":456,"githubOwner":457,"githubRepo":458,"locale":18,"slug":459,"type":256},"skills/project-session-manager","Yeachan-Heo","oh-my-claudecode","project-session-manager",{"evaluate":461,"extract":468},{"promptVersionExtension":212,"promptVersionScoring":213,"score":434,"tags":462,"targetMarket":224,"tier":225},[463,464,465,466,222,221,467],"git","development-environment","workflow","tmux","developer-tool",{"commitSha":262,"license":469},"MIT",{"parentExtensionId":471,"repoId":472},"k17brg5egdw1jbncj1j4wfv3fh86n639","kd74zv63fryf9prygtq7gf4es986n22y",[222,221,467,464,463,466,465],{"evaluatedAt":475,"extractAt":476,"updatedAt":475},1778699613343,1778699234184,{"_creationTime":478,"_id":479,"community":480,"display":481,"identity":484,"providers":487,"relations":495,"tags":496,"workflow":497},1778699234184.611,"k179b6dkc777g1rgyecze04wqn86m6y4",{"reviewCount":8},{"description":482,"installMethods":483,"name":458,"sourceUrl":454},"Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly",{"claudeCode":452},{"basePath":485,"githubOwner":457,"githubRepo":458,"locale":18,"slug":486,"type":256},"skills/ask","ask",{"evaluate":488,"extract":494},{"promptVersionExtension":212,"promptVersionScoring":213,"score":434,"tags":489,"targetMarket":224,"tier":225},[221,222,490,491,492,493],"llm","prompting","code-review","artifact-generation",{"commitSha":262,"license":469},{"parentExtensionId":471,"repoId":472},[493,222,221,492,490,491],{"evaluatedAt":498,"extractAt":476,"updatedAt":498},1778699303045,{"_creationTime":500,"_id":501,"community":502,"display":503,"identity":508,"providers":512,"relations":519,"tags":521,"workflow":522},1778697652123.8982,"k175ckmrqc4x6sjm90k7ejbj3s86ntxs",{"reviewCount":8},{"description":504,"installMethods":505,"name":220,"sourceUrl":507},"Use the Slack tool to react, pin/unpin, send, edit, delete messages, or fetch Slack member info.",{"claudeCode":506},"steipete/clawdis","https://github.com/steipete/clawdis",{"basePath":509,"githubOwner":510,"githubRepo":511,"locale":18,"slug":220,"type":256},"skills/slack","steipete","clawdis",{"evaluate":513,"extract":518},{"promptVersionExtension":212,"promptVersionScoring":213,"score":434,"tags":514,"targetMarket":224,"tier":225},[220,515,516,222,517],"messaging","communication","api",{"commitSha":262},{"repoId":520},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[517,222,516,515,220],{"evaluatedAt":523,"extractAt":524,"updatedAt":523},1778698950505,1778697652123,{"_creationTime":526,"_id":527,"community":528,"display":529,"identity":533,"providers":535,"relations":540,"tags":541,"workflow":542},1778697652123.8928,"k171pew5empzzrfghyg9nqrk6n86nqa9",{"reviewCount":8},{"description":530,"installMethods":531,"name":532,"sourceUrl":507},"Use gh for GitHub issues, PR status, CI/logs, comments, reviews, releases, and API queries.",{"claudeCode":506},"github",{"basePath":534,"githubOwner":510,"githubRepo":511,"locale":18,"slug":532,"type":256},"skills/github",{"evaluate":536,"extract":539},{"promptVersionExtension":212,"promptVersionScoring":213,"score":434,"tags":537,"targetMarket":224,"tier":225},[532,221,517,538,222],"developer-tools",{"commitSha":262},{"repoId":520},[517,222,221,538,532],{"evaluatedAt":543,"extractAt":524,"updatedAt":543},1778698569289,{"_creationTime":545,"_id":546,"community":547,"display":548,"identity":552,"providers":554,"relations":560,"tags":561,"workflow":562},1778697652123.8857,"k179k1n5nw0md1x1j3dak31evn86mb5f",{"reviewCount":8},{"description":549,"installMethods":550,"name":551,"sourceUrl":507},"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":506},"telegram-crabbox-e2e-proof",{"basePath":553,"githubOwner":510,"githubRepo":511,"locale":18,"slug":551,"type":256},".agents/skills/telegram-crabbox-e2e-proof",{"evaluate":555,"extract":559},{"promptVersionExtension":212,"promptVersionScoring":213,"score":434,"tags":556,"targetMarket":224,"tier":225},[436,557,222,558,221],"telegram","qa",{"commitSha":262},{"repoId":520},[222,221,558,557,436],{"evaluatedAt":563,"extractAt":524,"updatedAt":563},1778698038113]