[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-vercel-labs-hypothesis-validation":3,"mdc--3k4zim-key":42,"related-repo-vercel-labs-hypothesis-validation":192,"related-org-vercel-labs-hypothesis-validation":244},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":28,"repoUrl":29,"updatedAt":30,"license":31,"forks":32,"topics":33,"repo":37,"sourceUrl":40,"mdContent":41},"hypothesis-validation","validate operational hypotheses through investigation","Given a hypothesis, take the necessary investigation steps to validate, invalidate, or reach an inconclusive result for the hypothesis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"vercel-labs","Vercel Labs","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fvercel-labs.png",[12,16,19,22,25],{"name":13,"slug":14,"type":15},"SRE","sre","tag",{"name":17,"slug":18,"type":15},"Operations","operations",{"name":20,"slug":21,"type":15},"Analysis","analysis",{"name":23,"slug":24,"type":15},"Diagnostics","diagnostics",{"name":26,"slug":27,"type":15},"Engineering","engineering",6,"https:\u002F\u002Fgithub.com\u002Fvercel-labs\u002Feve-sre-agent-template","2026-08-27T13:33:16.558074",null,1,[34,35,36],"agent","ai","vercel",{"repoUrl":29,"stars":28,"forks":32,"topics":38,"description":39},[34,35,36],"Meet sre, an eve incident response agent.","https:\u002F\u002Fgithub.com\u002Fvercel-labs\u002Feve-sre-agent-template\u002Ftree\u002FHEAD\u002Fagent\u002Fskills\u002Fhypothesis-validation","---\nname: hypothesis-validation\ndescription: Given a hypothesis, take the necessary investigation steps to validate, invalidate, or reach an inconclusive result for the hypothesis.\n---\n\n# Hypothesis Validation\n\nInvestigate the related context for a given hypothesis holistically. Record evidence and conclude whether the hypothesis is validated, invalidated, or inconclusive.\n\n## Procedure\n\n### 1: Context hydration\n\nScan the conversation for:\n\n- alert or incident metadata\n- service names, environment names, region hints\n- timestamps or time ranges\n- symptoms (errors, latency, downtime)\n- links to external pieces of context\n\nThe goal here is getting a quick hydration of possibly relevant context for the hypothesis before doing a deeper dive.\n\n### 2: Dig deep\n\nAfter identifying possibly relevant context, dig deep into the most relevant pieces of context to gather enough evidence to validate, invalidate, or reach an inconclusive result for the hypothesis.\n\nRecord findings as you dig. Follow the Evidence rules in the agent instructions. Call `evidence_record`, `evidence_remove`, and `evidence_list` as those rules say.\n\n### 3: Draw conclusions\n\nAfter gathering enough evidence, draw a final conclusion about the hypothesis. The conclusion for the hypothesis should be \"validated\", \"invalidated\", or \"inconclusive\". Include a description that cites the most important pieces of evidence used to draw the conclusion.\n\n## Result\n\nA synthesized conclusion for the hypothesis.\n\n## Boundaries\n\n- Do not use this skill to run a full investigation. Use the deep investigation skill.\n",{"data":43,"body":44},{"name":4,"description":6},{"type":45,"children":46},"root",[47,55,61,68,75,80,110,115,121,126,156,162,167,173,178,184],{"type":48,"tag":49,"props":50,"children":51},"element","h1",{"id":4},[52],{"type":53,"value":54},"text","Hypothesis Validation",{"type":48,"tag":56,"props":57,"children":58},"p",{},[59],{"type":53,"value":60},"Investigate the related context for a given hypothesis holistically. Record evidence and conclude whether the hypothesis is validated, invalidated, or inconclusive.",{"type":48,"tag":62,"props":63,"children":65},"h2",{"id":64},"procedure",[66],{"type":53,"value":67},"Procedure",{"type":48,"tag":69,"props":70,"children":72},"h3",{"id":71},"_1-context-hydration",[73],{"type":53,"value":74},"1: Context hydration",{"type":48,"tag":56,"props":76,"children":77},{},[78],{"type":53,"value":79},"Scan the conversation for:",{"type":48,"tag":81,"props":82,"children":83},"ul",{},[84,90,95,100,105],{"type":48,"tag":85,"props":86,"children":87},"li",{},[88],{"type":53,"value":89},"alert or incident metadata",{"type":48,"tag":85,"props":91,"children":92},{},[93],{"type":53,"value":94},"service names, environment names, region hints",{"type":48,"tag":85,"props":96,"children":97},{},[98],{"type":53,"value":99},"timestamps or time ranges",{"type":48,"tag":85,"props":101,"children":102},{},[103],{"type":53,"value":104},"symptoms (errors, latency, downtime)",{"type":48,"tag":85,"props":106,"children":107},{},[108],{"type":53,"value":109},"links to external pieces of context",{"type":48,"tag":56,"props":111,"children":112},{},[113],{"type":53,"value":114},"The goal here is getting a quick hydration of possibly relevant context for the hypothesis before doing a deeper dive.",{"type":48,"tag":69,"props":116,"children":118},{"id":117},"_2-dig-deep",[119],{"type":53,"value":120},"2: Dig deep",{"type":48,"tag":56,"props":122,"children":123},{},[124],{"type":53,"value":125},"After identifying possibly relevant context, dig deep into the most relevant pieces of context to gather enough evidence to validate, invalidate, or reach an inconclusive result for the hypothesis.",{"type":48,"tag":56,"props":127,"children":128},{},[129,131,138,140,146,148,154],{"type":53,"value":130},"Record findings as you dig. Follow the Evidence rules in the agent instructions. Call ",{"type":48,"tag":132,"props":133,"children":135},"code",{"className":134},[],[136],{"type":53,"value":137},"evidence_record",{"type":53,"value":139},", ",{"type":48,"tag":132,"props":141,"children":143},{"className":142},[],[144],{"type":53,"value":145},"evidence_remove",{"type":53,"value":147},", and ",{"type":48,"tag":132,"props":149,"children":151},{"className":150},[],[152],{"type":53,"value":153},"evidence_list",{"type":53,"value":155}," as those rules say.",{"type":48,"tag":69,"props":157,"children":159},{"id":158},"_3-draw-conclusions",[160],{"type":53,"value":161},"3: Draw conclusions",{"type":48,"tag":56,"props":163,"children":164},{},[165],{"type":53,"value":166},"After gathering enough evidence, draw a final conclusion about the hypothesis. The conclusion for the hypothesis should be \"validated\", \"invalidated\", or \"inconclusive\". Include a description that cites the most important pieces of evidence used to draw the conclusion.",{"type":48,"tag":62,"props":168,"children":170},{"id":169},"result",[171],{"type":53,"value":172},"Result",{"type":48,"tag":56,"props":174,"children":175},{},[176],{"type":53,"value":177},"A synthesized conclusion for the hypothesis.",{"type":48,"tag":62,"props":179,"children":181},{"id":180},"boundaries",[182],{"type":53,"value":183},"Boundaries",{"type":48,"tag":81,"props":185,"children":186},{},[187],{"type":48,"tag":85,"props":188,"children":189},{},[190],{"type":53,"value":191},"Do not use this skill to run a full investigation. Use the deep investigation skill.",{"items":193,"total":243},[194,208,216,233],{"slug":195,"name":195,"fn":196,"description":197,"org":198,"tags":199,"stars":28,"repoUrl":29,"updatedAt":207},"deep-investigation","investigate operational problems and recommend solutions","Investigate an operational problem to determine what happened, assess its impact, and recommend next steps using a hypothesis-backed approach.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[200,201,202,205,206],{"name":20,"slug":21,"type":15},{"name":23,"slug":24,"type":15},{"name":203,"slug":204,"type":15},"Incident Response","incident-response",{"name":17,"slug":18,"type":15},{"name":13,"slug":14,"type":15},"2026-08-27T13:32:49.407914",{"slug":4,"name":4,"fn":5,"description":6,"org":209,"tags":210,"stars":28,"repoUrl":29,"updatedAt":30},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[211,212,213,214,215],{"name":20,"slug":21,"type":15},{"name":23,"slug":24,"type":15},{"name":26,"slug":27,"type":15},{"name":17,"slug":18,"type":15},{"name":13,"slug":14,"type":15},{"slug":217,"name":217,"fn":218,"description":219,"org":220,"tags":221,"stars":28,"repoUrl":29,"updatedAt":232},"on-call-handoff","summarize on-call shift handoffs","Summarize a personal or team on-call shift from supplied context, Slack, Datadog, GitHub, and Vercel. Activate when asked for an on-call handoff, shift summary, rotation handoff, what to tell the next on-call, or leaving on-call.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[222,225,228,229],{"name":223,"slug":224,"type":15},"Communications","communications",{"name":226,"slug":227,"type":15},"Management","management",{"name":17,"slug":18,"type":15},{"name":230,"slug":231,"type":15},"Runbooks","runbooks","2026-08-27T13:33:04.26561",{"slug":234,"name":234,"fn":235,"description":236,"org":237,"tags":238,"stars":28,"repoUrl":29,"updatedAt":242},"suggest-follow-ups","suggest incident follow-up actions","Suggest high-leverage incident follow-up actions from established root cause and incident context. Activate when asked for follow-ups, action items, preventive measures, or \"what should we do so this doesn't happen again\" after an incident.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[239,240,241],{"name":203,"slug":204,"type":15},{"name":17,"slug":18,"type":15},{"name":13,"slug":14,"type":15},"2026-08-27T13:33:16.147912",4,{"items":245,"total":416},[246,264,276,288,303,320,332,350,363,374,385,397],{"slug":247,"name":247,"fn":248,"description":249,"org":250,"tags":251,"stars":261,"repoUrl":262,"updatedAt":263},"agent-browser","automate browser interactions for AI agents","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.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[252,255,258],{"name":253,"slug":254,"type":15},"Agents","agents",{"name":256,"slug":257,"type":15},"Automation","automation",{"name":259,"slug":260,"type":15},"Browser Automation","browser-automation",38346,"https:\u002F\u002Fgithub.com\u002Fvercel-labs\u002Fagent-browser","2026-08-24T03:36:10.45111",{"slug":265,"name":265,"fn":266,"description":267,"org":268,"tags":269,"stars":261,"repoUrl":262,"updatedAt":275},"agentcore","run browser automation on AWS Bedrock","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.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[270,271,274],{"name":256,"slug":257,"type":15},{"name":272,"slug":273,"type":15},"AWS","aws",{"name":259,"slug":260,"type":15},"2026-07-17T06:08:33.665276",{"slug":277,"name":277,"fn":278,"description":279,"org":280,"tags":281,"stars":261,"repoUrl":262,"updatedAt":287},"core","navigate and interact with web pages","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.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[282,283,284],{"name":253,"slug":254,"type":15},{"name":259,"slug":260,"type":15},{"name":285,"slug":286,"type":15},"Navigation","navigation","2026-08-27T13:05:09.446966",{"slug":289,"name":289,"fn":290,"description":291,"org":292,"tags":293,"stars":261,"repoUrl":262,"updatedAt":302},"derive-client","reverse engineer internal APIs from browser traffic","Reverse-engineer a website's internal API by recording browser traffic into a HAR file, then generate a standalone client or CLI that calls the endpoints directly, with no browser needed after the first recording. Use when asked to \"derive a client\", \"build a CLI for \u003Csite>\", \"reverse engineer this site's API\", \"record network requests\", \"turn this site into an API\", or when the same site will be automated repeatedly and direct HTTP calls would beat driving the browser every time.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[294,297,298,299],{"name":295,"slug":296,"type":15},"API Development","api-development",{"name":256,"slug":257,"type":15},{"name":259,"slug":260,"type":15},{"name":300,"slug":301,"type":15},"Web Scraping","web-scraping","2026-07-20T06:24:11.928835",{"slug":304,"name":304,"fn":305,"description":306,"org":307,"tags":308,"stars":261,"repoUrl":262,"updatedAt":319},"dogfood","perform exploratory testing on web applications","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\u002Fsite\u002Fplatform\", 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.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[309,310,313,316],{"name":259,"slug":260,"type":15},{"name":311,"slug":312,"type":15},"Debugging","debugging",{"name":314,"slug":315,"type":15},"QA","qa",{"name":317,"slug":318,"type":15},"Testing","testing","2026-07-17T06:07:41.421482",{"slug":321,"name":321,"fn":322,"description":323,"org":324,"tags":325,"stars":261,"repoUrl":262,"updatedAt":331},"electron","automate Electron desktop applications","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.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[326,327,328],{"name":253,"slug":254,"type":15},{"name":259,"slug":260,"type":15},{"name":329,"slug":330,"type":15},"Desktop","desktop","2026-07-17T06:08:28.007783",{"slug":333,"name":333,"fn":334,"description":335,"org":336,"tags":337,"stars":261,"repoUrl":262,"updatedAt":349},"protected-vercel-deployments","access protected Vercel deployments","Access and test Vercel deployments protected by Vercel Authentication, SSO, or Deployment Protection with agent-browser. Use when a preview or production URL redirects to a Vercel login page, returns a protection 401 or 403, or needs short-lived Trusted Sources OIDC authentication instead of a static bypass secret or public exception.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[338,341,344,347],{"name":339,"slug":340,"type":15},"Auth","auth",{"name":342,"slug":343,"type":15},"Deployment","deployment",{"name":345,"slug":346,"type":15},"Security","security",{"name":348,"slug":36,"type":15},"Vercel","2026-08-24T03:57:05.330407",{"slug":351,"name":351,"fn":352,"description":353,"org":354,"tags":355,"stars":261,"repoUrl":262,"updatedAt":362},"slack","interact with Slack workspaces","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.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[356,357,360],{"name":259,"slug":260,"type":15},{"name":358,"slug":359,"type":15},"Messaging","messaging",{"name":361,"slug":351,"type":15},"Slack","2026-07-17T06:08:27.679015",{"slug":364,"name":364,"fn":365,"description":366,"org":367,"tags":368,"stars":261,"repoUrl":262,"updatedAt":373},"vercel-sandbox","run browser automation in 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.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[369,370,371,372],{"name":256,"slug":257,"type":15},{"name":259,"slug":260,"type":15},{"name":317,"slug":318,"type":15},{"name":348,"slug":36,"type":15},"2026-07-17T06:08:28.349899",{"slug":375,"name":375,"fn":376,"description":377,"org":378,"tags":379,"stars":382,"repoUrl":383,"updatedAt":384},"deploy-to-vercel","deploy applications to Vercel","Deploy applications and websites to Vercel. Use when the user requests deployment actions like \"deploy my app\", \"deploy and give me the link\", \"push this live\", or \"create a preview deployment\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[380,381],{"name":342,"slug":343,"type":15},{"name":348,"slug":36,"type":15},28993,"https:\u002F\u002Fgithub.com\u002Fvercel-labs\u002Fagent-skills","2026-07-17T06:08:41.18374",{"slug":386,"name":386,"fn":387,"description":388,"org":389,"tags":390,"stars":382,"repoUrl":383,"updatedAt":396},"vercel-cli-with-tokens","manage Vercel projects via CLI","Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. \"deploy to vercel\", \"set up vercel\", \"add environment variables to vercel\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[391,394,395],{"name":392,"slug":393,"type":15},"CLI","cli",{"name":342,"slug":343,"type":15},{"name":348,"slug":36,"type":15},"2026-07-17T06:08:41.84179",{"slug":398,"name":398,"fn":399,"description":400,"org":401,"tags":402,"stars":382,"repoUrl":383,"updatedAt":415},"vercel-composition-patterns","implement scalable React composition patterns","React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[403,406,409,412],{"name":404,"slug":405,"type":15},"Best Practices","best-practices",{"name":407,"slug":408,"type":15},"Frontend","frontend",{"name":410,"slug":411,"type":15},"React","react",{"name":413,"slug":414,"type":15},"UI Components","ui-components","2026-07-17T06:05:40.576913",104]