[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-vercel-labs-suggest-follow-ups":3,"mdc-jmmuhp-key":36,"related-org-vercel-labs-suggest-follow-ups":251,"related-repo-vercel-labs-suggest-follow-ups":424},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":22,"repoUrl":23,"updatedAt":24,"license":25,"forks":26,"topics":27,"repo":31,"sourceUrl":34,"mdContent":35},"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},"vercel-labs","Vercel Labs","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fvercel-labs.png",[12,16,19],{"name":13,"slug":14,"type":15},"SRE","sre","tag",{"name":17,"slug":18,"type":15},"Operations","operations",{"name":20,"slug":21,"type":15},"Incident Response","incident-response",6,"https:\u002F\u002Fgithub.com\u002Fvercel-labs\u002Feve-sre-agent-template","2026-08-27T13:33:16.147912",null,1,[28,29,30],"agent","ai","vercel",{"repoUrl":23,"stars":22,"forks":26,"topics":32,"description":33},[28,29,30],"Meet sre, an eve incident response agent.","https:\u002F\u002Fgithub.com\u002Fvercel-labs\u002Feve-sre-agent-template\u002Ftree\u002FHEAD\u002Fagent\u002Fskills\u002Fsuggest-follow-ups","---\nname: suggest-follow-ups\ndescription: 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.\n---\n\n# Suggest Follow-ups\n\nTurn an incident's root cause, timeline, and blast radius into a short, ranked list of high-leverage follow-up actions. Suggest only; do not file follow-ups.\n\nPrefer an established root cause. If root cause is unknown, do not investigate to invent one. Suggest only what available context supports, state that prevention-level follow-ups are premature, and recommend `deep-investigation` first if deeper follow-ups are wanted.\n\n## Procedure\n\n### Step 1: Gather what went wrong\n\nFrom the incident channel and supporting evidence, identify:\n\n- Root cause — the underlying fragility, not just the trigger\n- Timeline — detection, diagnosis, and mitigation speed\n- Blast radius — services, endpoints, or users affected, and severity\n- Issues that made the timeline slow or blast radius large\n\nIf these facts are not already in the thread, read the incident thread with Slack tools. Do not run new Datadog or GitHub queries to expand the investigation.\n\n### Step 2: Load existing follow-ups\n\nScan the thread for follow-ups that people already named. Do not duplicate those items. If this is a repeat incident, raise priority and note that earlier mitigation did not hold.\n\n### Step 3: Map to categories\n\nWeight toward where this incident actually hurt:\n\n- **Prevent** — eliminate the cause or class of cause\n- **Detect faster (MTTD)** — close a genuine detection gap\n- **Mitigate faster (MTTR)** — rollback automation, kill switch, missing runbook, missing dashboard\n- **Limit blast radius** — rate limiting, load shedding, circuit breaker, isolation, graceful degradation\n\nIf detection was already fast but recovery was slow, prefer mitigation over more alerts.\n\n### Step 4: Apply a high bar\n\nA follow-up qualifies only if it is durable\u002Fsystemic, targets the failure class, is worth the cost, and is verifiable. Drop process-vigilance items (\"be careful\", \"add review\", \"remind\").\n\nA proposed alert must also be symptom-based, actionable, page-worthy only if urgent, threshold-tuned, and prefer fixing\u002Fconsolidating an existing monitor over adding a new one.\n\n### Step 5: Rank\n\nOrder survivors by leverage — cheap, high-impact, fast-to-land first. Typically one to three items. If nothing clears the bar, say so rather than inventing low-value items.\n\n## Result\n\nA short ranked list of suggested follow-ups, each with priority, action, and one sentence on why it matters tied to evidence.\n\n## Boundaries\n\n- Suggest only. Do not file follow-ups in an external system.\n- Do not investigate or run new observability\u002Fcode queries to manufacture a root cause.\n- Do not assign owners.\n",{"data":37,"body":38},{"name":4,"description":6},{"type":39,"children":40},"root",[41,49,55,69,76,83,88,113,118,124,129,135,140,184,189,195,200,205,211,216,222,227,233],{"type":42,"tag":43,"props":44,"children":45},"element","h1",{"id":4},[46],{"type":47,"value":48},"text","Suggest Follow-ups",{"type":42,"tag":50,"props":51,"children":52},"p",{},[53],{"type":47,"value":54},"Turn an incident's root cause, timeline, and blast radius into a short, ranked list of high-leverage follow-up actions. Suggest only; do not file follow-ups.",{"type":42,"tag":50,"props":56,"children":57},{},[58,60,67],{"type":47,"value":59},"Prefer an established root cause. If root cause is unknown, do not investigate to invent one. Suggest only what available context supports, state that prevention-level follow-ups are premature, and recommend ",{"type":42,"tag":61,"props":62,"children":64},"code",{"className":63},[],[65],{"type":47,"value":66},"deep-investigation",{"type":47,"value":68}," first if deeper follow-ups are wanted.",{"type":42,"tag":70,"props":71,"children":73},"h2",{"id":72},"procedure",[74],{"type":47,"value":75},"Procedure",{"type":42,"tag":77,"props":78,"children":80},"h3",{"id":79},"step-1-gather-what-went-wrong",[81],{"type":47,"value":82},"Step 1: Gather what went wrong",{"type":42,"tag":50,"props":84,"children":85},{},[86],{"type":47,"value":87},"From the incident channel and supporting evidence, identify:",{"type":42,"tag":89,"props":90,"children":91},"ul",{},[92,98,103,108],{"type":42,"tag":93,"props":94,"children":95},"li",{},[96],{"type":47,"value":97},"Root cause — the underlying fragility, not just the trigger",{"type":42,"tag":93,"props":99,"children":100},{},[101],{"type":47,"value":102},"Timeline — detection, diagnosis, and mitigation speed",{"type":42,"tag":93,"props":104,"children":105},{},[106],{"type":47,"value":107},"Blast radius — services, endpoints, or users affected, and severity",{"type":42,"tag":93,"props":109,"children":110},{},[111],{"type":47,"value":112},"Issues that made the timeline slow or blast radius large",{"type":42,"tag":50,"props":114,"children":115},{},[116],{"type":47,"value":117},"If these facts are not already in the thread, read the incident thread with Slack tools. Do not run new Datadog or GitHub queries to expand the investigation.",{"type":42,"tag":77,"props":119,"children":121},{"id":120},"step-2-load-existing-follow-ups",[122],{"type":47,"value":123},"Step 2: Load existing follow-ups",{"type":42,"tag":50,"props":125,"children":126},{},[127],{"type":47,"value":128},"Scan the thread for follow-ups that people already named. Do not duplicate those items. If this is a repeat incident, raise priority and note that earlier mitigation did not hold.",{"type":42,"tag":77,"props":130,"children":132},{"id":131},"step-3-map-to-categories",[133],{"type":47,"value":134},"Step 3: Map to categories",{"type":42,"tag":50,"props":136,"children":137},{},[138],{"type":47,"value":139},"Weight toward where this incident actually hurt:",{"type":42,"tag":89,"props":141,"children":142},{},[143,154,164,174],{"type":42,"tag":93,"props":144,"children":145},{},[146,152],{"type":42,"tag":147,"props":148,"children":149},"strong",{},[150],{"type":47,"value":151},"Prevent",{"type":47,"value":153}," — eliminate the cause or class of cause",{"type":42,"tag":93,"props":155,"children":156},{},[157,162],{"type":42,"tag":147,"props":158,"children":159},{},[160],{"type":47,"value":161},"Detect faster (MTTD)",{"type":47,"value":163}," — close a genuine detection gap",{"type":42,"tag":93,"props":165,"children":166},{},[167,172],{"type":42,"tag":147,"props":168,"children":169},{},[170],{"type":47,"value":171},"Mitigate faster (MTTR)",{"type":47,"value":173}," — rollback automation, kill switch, missing runbook, missing dashboard",{"type":42,"tag":93,"props":175,"children":176},{},[177,182],{"type":42,"tag":147,"props":178,"children":179},{},[180],{"type":47,"value":181},"Limit blast radius",{"type":47,"value":183}," — rate limiting, load shedding, circuit breaker, isolation, graceful degradation",{"type":42,"tag":50,"props":185,"children":186},{},[187],{"type":47,"value":188},"If detection was already fast but recovery was slow, prefer mitigation over more alerts.",{"type":42,"tag":77,"props":190,"children":192},{"id":191},"step-4-apply-a-high-bar",[193],{"type":47,"value":194},"Step 4: Apply a high bar",{"type":42,"tag":50,"props":196,"children":197},{},[198],{"type":47,"value":199},"A follow-up qualifies only if it is durable\u002Fsystemic, targets the failure class, is worth the cost, and is verifiable. Drop process-vigilance items (\"be careful\", \"add review\", \"remind\").",{"type":42,"tag":50,"props":201,"children":202},{},[203],{"type":47,"value":204},"A proposed alert must also be symptom-based, actionable, page-worthy only if urgent, threshold-tuned, and prefer fixing\u002Fconsolidating an existing monitor over adding a new one.",{"type":42,"tag":77,"props":206,"children":208},{"id":207},"step-5-rank",[209],{"type":47,"value":210},"Step 5: Rank",{"type":42,"tag":50,"props":212,"children":213},{},[214],{"type":47,"value":215},"Order survivors by leverage — cheap, high-impact, fast-to-land first. Typically one to three items. If nothing clears the bar, say so rather than inventing low-value items.",{"type":42,"tag":70,"props":217,"children":219},{"id":218},"result",[220],{"type":47,"value":221},"Result",{"type":42,"tag":50,"props":223,"children":224},{},[225],{"type":47,"value":226},"A short ranked list of suggested follow-ups, each with priority, action, and one sentence on why it matters tied to evidence.",{"type":42,"tag":70,"props":228,"children":230},{"id":229},"boundaries",[231],{"type":47,"value":232},"Boundaries",{"type":42,"tag":89,"props":234,"children":235},{},[236,241,246],{"type":42,"tag":93,"props":237,"children":238},{},[239],{"type":47,"value":240},"Suggest only. Do not file follow-ups in an external system.",{"type":42,"tag":93,"props":242,"children":243},{},[244],{"type":47,"value":245},"Do not investigate or run new observability\u002Fcode queries to manufacture a root cause.",{"type":42,"tag":93,"props":247,"children":248},{},[249],{"type":47,"value":250},"Do not assign owners.",{"items":252,"total":423},[253,271,283,295,310,327,339,357,370,381,392,404],{"slug":254,"name":254,"fn":255,"description":256,"org":257,"tags":258,"stars":268,"repoUrl":269,"updatedAt":270},"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},[259,262,265],{"name":260,"slug":261,"type":15},"Agents","agents",{"name":263,"slug":264,"type":15},"Automation","automation",{"name":266,"slug":267,"type":15},"Browser Automation","browser-automation",38346,"https:\u002F\u002Fgithub.com\u002Fvercel-labs\u002Fagent-browser","2026-08-24T03:36:10.45111",{"slug":272,"name":272,"fn":273,"description":274,"org":275,"tags":276,"stars":268,"repoUrl":269,"updatedAt":282},"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},[277,278,281],{"name":263,"slug":264,"type":15},{"name":279,"slug":280,"type":15},"AWS","aws",{"name":266,"slug":267,"type":15},"2026-07-17T06:08:33.665276",{"slug":284,"name":284,"fn":285,"description":286,"org":287,"tags":288,"stars":268,"repoUrl":269,"updatedAt":294},"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},[289,290,291],{"name":260,"slug":261,"type":15},{"name":266,"slug":267,"type":15},{"name":292,"slug":293,"type":15},"Navigation","navigation","2026-08-27T13:05:09.446966",{"slug":296,"name":296,"fn":297,"description":298,"org":299,"tags":300,"stars":268,"repoUrl":269,"updatedAt":309},"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},[301,304,305,306],{"name":302,"slug":303,"type":15},"API Development","api-development",{"name":263,"slug":264,"type":15},{"name":266,"slug":267,"type":15},{"name":307,"slug":308,"type":15},"Web Scraping","web-scraping","2026-07-20T06:24:11.928835",{"slug":311,"name":311,"fn":312,"description":313,"org":314,"tags":315,"stars":268,"repoUrl":269,"updatedAt":326},"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},[316,317,320,323],{"name":266,"slug":267,"type":15},{"name":318,"slug":319,"type":15},"Debugging","debugging",{"name":321,"slug":322,"type":15},"QA","qa",{"name":324,"slug":325,"type":15},"Testing","testing","2026-07-17T06:07:41.421482",{"slug":328,"name":328,"fn":329,"description":330,"org":331,"tags":332,"stars":268,"repoUrl":269,"updatedAt":338},"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},[333,334,335],{"name":260,"slug":261,"type":15},{"name":266,"slug":267,"type":15},{"name":336,"slug":337,"type":15},"Desktop","desktop","2026-07-17T06:08:28.007783",{"slug":340,"name":340,"fn":341,"description":342,"org":343,"tags":344,"stars":268,"repoUrl":269,"updatedAt":356},"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},[345,348,351,354],{"name":346,"slug":347,"type":15},"Auth","auth",{"name":349,"slug":350,"type":15},"Deployment","deployment",{"name":352,"slug":353,"type":15},"Security","security",{"name":355,"slug":30,"type":15},"Vercel","2026-08-24T03:57:05.330407",{"slug":358,"name":358,"fn":359,"description":360,"org":361,"tags":362,"stars":268,"repoUrl":269,"updatedAt":369},"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},[363,364,367],{"name":266,"slug":267,"type":15},{"name":365,"slug":366,"type":15},"Messaging","messaging",{"name":368,"slug":358,"type":15},"Slack","2026-07-17T06:08:27.679015",{"slug":371,"name":371,"fn":372,"description":373,"org":374,"tags":375,"stars":268,"repoUrl":269,"updatedAt":380},"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},[376,377,378,379],{"name":263,"slug":264,"type":15},{"name":266,"slug":267,"type":15},{"name":324,"slug":325,"type":15},{"name":355,"slug":30,"type":15},"2026-07-17T06:08:28.349899",{"slug":382,"name":382,"fn":383,"description":384,"org":385,"tags":386,"stars":389,"repoUrl":390,"updatedAt":391},"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},[387,388],{"name":349,"slug":350,"type":15},{"name":355,"slug":30,"type":15},28993,"https:\u002F\u002Fgithub.com\u002Fvercel-labs\u002Fagent-skills","2026-07-17T06:08:41.18374",{"slug":393,"name":393,"fn":394,"description":395,"org":396,"tags":397,"stars":389,"repoUrl":390,"updatedAt":403},"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},[398,401,402],{"name":399,"slug":400,"type":15},"CLI","cli",{"name":349,"slug":350,"type":15},{"name":355,"slug":30,"type":15},"2026-07-17T06:08:41.84179",{"slug":405,"name":405,"fn":406,"description":407,"org":408,"tags":409,"stars":389,"repoUrl":390,"updatedAt":422},"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},[410,413,416,419],{"name":411,"slug":412,"type":15},"Best Practices","best-practices",{"name":414,"slug":415,"type":15},"Frontend","frontend",{"name":417,"slug":418,"type":15},"React","react",{"name":420,"slug":421,"type":15},"UI Components","ui-components","2026-07-17T06:05:40.576913",104,{"items":425,"total":478},[426,441,455,472],{"slug":66,"name":66,"fn":427,"description":428,"org":429,"tags":430,"stars":22,"repoUrl":23,"updatedAt":440},"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},[431,434,437,438,439],{"name":432,"slug":433,"type":15},"Analysis","analysis",{"name":435,"slug":436,"type":15},"Diagnostics","diagnostics",{"name":20,"slug":21,"type":15},{"name":17,"slug":18,"type":15},{"name":13,"slug":14,"type":15},"2026-08-27T13:32:49.407914",{"slug":442,"name":442,"fn":443,"description":444,"org":445,"tags":446,"stars":22,"repoUrl":23,"updatedAt":454},"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},[447,448,449,452,453],{"name":432,"slug":433,"type":15},{"name":435,"slug":436,"type":15},{"name":450,"slug":451,"type":15},"Engineering","engineering",{"name":17,"slug":18,"type":15},{"name":13,"slug":14,"type":15},"2026-08-27T13:33:16.558074",{"slug":456,"name":456,"fn":457,"description":458,"org":459,"tags":460,"stars":22,"repoUrl":23,"updatedAt":471},"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},[461,464,467,468],{"name":462,"slug":463,"type":15},"Communications","communications",{"name":465,"slug":466,"type":15},"Management","management",{"name":17,"slug":18,"type":15},{"name":469,"slug":470,"type":15},"Runbooks","runbooks","2026-08-27T13:33:04.26561",{"slug":4,"name":4,"fn":5,"description":6,"org":473,"tags":474,"stars":22,"repoUrl":23,"updatedAt":24},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[475,476,477],{"name":20,"slug":21,"type":15},{"name":17,"slug":18,"type":15},{"name":13,"slug":14,"type":15},4]