[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-slack":3,"mdc--mg70po-key":35,"related-org-openai-slack":503,"related-repo-openai-slack":708},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":24,"repoUrl":25,"updatedAt":26,"license":27,"forks":28,"topics":29,"repo":30,"sourceUrl":33,"mdContent":34},"slack","manage Slack conversations and workflows","Read Slack context, route to the right Slack workflow, and prepare or perform Slack writes that match the user's intent.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"openai","OpenAI","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fopenai.png",[12,16,19,21],{"name":13,"slug":14,"type":15},"Productivity","productivity","tag",{"name":17,"slug":18,"type":15},"Messaging","messaging",{"name":20,"slug":4,"type":15},"Slack",{"name":22,"slug":23,"type":15},"Communications","communications",3992,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-04-06T18:42:05.410092",null,465,[],{"repoUrl":25,"stars":24,"forks":28,"topics":31,"description":32},[],"OpenAI Plugins","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fslack\u002Fskills\u002Fslack","---\nname: slack\ndescription: Read Slack context, route to the right Slack workflow, and prepare or perform Slack writes that match the user's intent.\n---\n\n# Slack\n\n## Overview\n\nUse this skill as the router for Slack work. Read the relevant Slack context first, then hand off to the most specific Slack workflow.\nIf the task will produce outgoing Slack text or perform a Slack write, switch to [..\u002Fslack-outgoing-message\u002FSKILL.md](..\u002Fslack-outgoing-message\u002FSKILL.md) before finalizing and reread that file's `## Formatting Rules` section immediately before any send, draft, schedule, or canvas creation.\n\n## Related Skills\n\n| Workflow | Skill |\n| --- | --- |\n| Message composition, rewrites, drafts, and canvas-writing workflows | [..\u002Fslack-outgoing-message\u002FSKILL.md](..\u002Fslack-outgoing-message\u002FSKILL.md) |\n| Bounded channel recaps and thematic Slack summaries | [..\u002Fslack-channel-summarization\u002FSKILL.md](..\u002Fslack-channel-summarization\u002FSKILL.md) |\n| Daily digests across selected channels or topics | [..\u002Fslack-daily-digest\u002FSKILL.md](..\u002Fslack-daily-digest\u002FSKILL.md) |\n| Find messages that likely need a response and prepare reply drafts | [..\u002Fslack-reply-drafting\u002FSKILL.md](..\u002Fslack-reply-drafting\u002FSKILL.md) |\n| Triage for what the user needs to read, reply to, or do next | [..\u002Fslack-notification-triage\u002FSKILL.md](..\u002Fslack-notification-triage\u002FSKILL.md) |\n\n## Reference Notes\n\n| Task | Reference |\n| --- | --- |\n| Slack Markdown formatting rules and examples | [references\u002Fmarkdown.md](.\u002Freferences\u002Fmarkdown.md) |\n\n## Support Checks\n\n- Confirm the requested action is supported before asking the user for more input. If Slack does not support the action, say so immediately and offer the closest supported path instead of collecting unnecessary details.\n- For broad Slack analysis requests, fail fast if the connector cannot establish the needed coverage or signals reliably. Do not invent channel names, imply the user is in a channel, or present workspace-wide conclusions as authoritative. Ask for a candidate list, a narrower scope, or a question that can be answered from specific channels, threads, profiles, or search results.\n- The current Slack app surface here supports reading\u002Fsearching channels, users, threads, and canvases plus writing messages, drafts, scheduled messages, and canvases. Do not claim support for creating channels, editing messages, deleting messages, or other unsupported Slack admin actions.\n\n## Intent Routing\n\n- If the user explicitly asks to send, post, reply, share, or create something in Slack, follow that write intent directly. Do not downgrade the request into a draft unless the user asked for a draft or review-first flow.\n- If the user explicitly asks for a draft, rewrite, or review-first workflow, use a draft.\n- If the user asks for Slack analysis only, return the result in chat unless they also asked for Slack delivery.\n- If the user asks for an unsupported Slack write action, say so and offer the closest supported path instead of forcing a draft.\n\n## Tool Rate Limits\n\n- Slack tools have per-minute RPM quotas by bucket, not by individual tool. Treat `slack_search_*` tools as the search bucket, `slack_read_*`, `slack_list_*`, and lookup-style tools as the read bucket, and message, draft, schedule, or canvas creation tools as the send\u002Fwrite bucket.\n- If a Slack tool returns a 429, do not retry immediately and do not switch to an equivalent tool in the same bucket. If the response includes `Retry-After` or another explicit wait hint, follow it. Otherwise wait about 30 seconds before calling that bucket again.\n- If the same bucket returns another 429 during the task, wait about 1 minute before the next retry, then about 2 minutes after the next 429, continuing with exponential backoff as needed.\n- A 429 in one bucket does not imply the other buckets are exhausted. While waiting on one bucket, continue making useful progress with other buckets when that can advance the task safely.\n- If the task cannot be completed without the exhausted bucket after reasonable backoff, explain the rate limit to the user and return the best partial result or next step.\n\n## DM Routing\n\n- When the same message is meant for multiple specific people, first look for an existing group DM with the right people and prefer that over duplicate one-to-one DMs.\n- If there is no suitable group DM, do not silently fan out separate DMs. Ask whether the user wants individual DMs instead, or ask them to create the group DM if that is the better path and the connector cannot create it.\n\n## Write Safety\n\n- Preserve exact channel names, thread context, links, code snippets, and owners from the source conversation unless the user asks for changes.\n- Before acting on a relative message target such as \"last message\", \"latest reply\", \"above\", or \"that message\", re-read the destination channel or thread and resolve the target from fresh results. Do not reuse earlier reads for reactions, replies, edits, or other writes.\n- Treat @channel, @here, mass mentions, and customer-facing channels as high-impact. Call them out before posting.\n- Keep post-ready drafts short enough to scan quickly unless the user asks for a long-form announcement.\n- If there are multiple channels or threads with similar topics, identify the intended destination before drafting or posting.\n\n## Output Conventions\n\n- Prefer a short opener, a few tight bullets, and a clear ask or next step.\n- Use Markdown formatting rules from `references\u002Fmarkdown.md` for emphasis, lists, links, quotes, mentions, and code.\n- For any outgoing Slack text, use the `slack-outgoing-message` skill.\n- Distinguish clearly between a private summary for the user and a post-ready message for Slack.\n- When summarizing a thread, lead with the latest status and then list blockers, decisions, and owners.\n- When drafting a reply, match the tone of the channel and avoid over-formatting.\n\n## Example Requests\n\n- \"Summarize the incident thread in #ops and draft a calm update for leadership.\"\n- \"Turn these meeting notes into a short Slack post for the team channel.\"\n- \"Read the product launch thread and draft a reply that confirms the timeline.\"\n- \"Rewrite this long update so it lands well in Slack and still keeps the important links.\"\n\n## Light Fallback\n\nIf Slack messages are missing, say that Slack access may be unavailable, the workspace may be disconnected, or the wrong channel or thread may be in scope, then ask the user to reconnect or clarify the destination.\n",{"data":36,"body":37},{"name":4,"description":6},{"type":38,"children":39},"root",[40,47,54,77,83,190,196,235,241,261,267,290,296,356,362,375,381,409,415,463,469,492,498],{"type":41,"tag":42,"props":43,"children":44},"element","h1",{"id":4},[45],{"type":46,"value":20},"text",{"type":41,"tag":48,"props":49,"children":51},"h2",{"id":50},"overview",[52],{"type":46,"value":53},"Overview",{"type":41,"tag":55,"props":56,"children":57},"p",{},[58,60,66,68,75],{"type":46,"value":59},"Use this skill as the router for Slack work. Read the relevant Slack context first, then hand off to the most specific Slack workflow.\nIf the task will produce outgoing Slack text or perform a Slack write, switch to ",{"type":41,"tag":61,"props":62,"children":64},"a",{"href":63},"..\u002Fslack-outgoing-message\u002FSKILL.md",[65],{"type":46,"value":63},{"type":46,"value":67}," before finalizing and reread that file's ",{"type":41,"tag":69,"props":70,"children":72},"code",{"className":71},[],[73],{"type":46,"value":74},"## Formatting Rules",{"type":46,"value":76}," section immediately before any send, draft, schedule, or canvas creation.",{"type":41,"tag":48,"props":78,"children":80},{"id":79},"related-skills",[81],{"type":46,"value":82},"Related Skills",{"type":41,"tag":84,"props":85,"children":86},"table",{},[87,106],{"type":41,"tag":88,"props":89,"children":90},"thead",{},[91],{"type":41,"tag":92,"props":93,"children":94},"tr",{},[95,101],{"type":41,"tag":96,"props":97,"children":98},"th",{},[99],{"type":46,"value":100},"Workflow",{"type":41,"tag":96,"props":102,"children":103},{},[104],{"type":46,"value":105},"Skill",{"type":41,"tag":107,"props":108,"children":109},"tbody",{},[110,126,142,158,174],{"type":41,"tag":92,"props":111,"children":112},{},[113,119],{"type":41,"tag":114,"props":115,"children":116},"td",{},[117],{"type":46,"value":118},"Message composition, rewrites, drafts, and canvas-writing workflows",{"type":41,"tag":114,"props":120,"children":121},{},[122],{"type":41,"tag":61,"props":123,"children":124},{"href":63},[125],{"type":46,"value":63},{"type":41,"tag":92,"props":127,"children":128},{},[129,134],{"type":41,"tag":114,"props":130,"children":131},{},[132],{"type":46,"value":133},"Bounded channel recaps and thematic Slack summaries",{"type":41,"tag":114,"props":135,"children":136},{},[137],{"type":41,"tag":61,"props":138,"children":140},{"href":139},"..\u002Fslack-channel-summarization\u002FSKILL.md",[141],{"type":46,"value":139},{"type":41,"tag":92,"props":143,"children":144},{},[145,150],{"type":41,"tag":114,"props":146,"children":147},{},[148],{"type":46,"value":149},"Daily digests across selected channels or topics",{"type":41,"tag":114,"props":151,"children":152},{},[153],{"type":41,"tag":61,"props":154,"children":156},{"href":155},"..\u002Fslack-daily-digest\u002FSKILL.md",[157],{"type":46,"value":155},{"type":41,"tag":92,"props":159,"children":160},{},[161,166],{"type":41,"tag":114,"props":162,"children":163},{},[164],{"type":46,"value":165},"Find messages that likely need a response and prepare reply drafts",{"type":41,"tag":114,"props":167,"children":168},{},[169],{"type":41,"tag":61,"props":170,"children":172},{"href":171},"..\u002Fslack-reply-drafting\u002FSKILL.md",[173],{"type":46,"value":171},{"type":41,"tag":92,"props":175,"children":176},{},[177,182],{"type":41,"tag":114,"props":178,"children":179},{},[180],{"type":46,"value":181},"Triage for what the user needs to read, reply to, or do next",{"type":41,"tag":114,"props":183,"children":184},{},[185],{"type":41,"tag":61,"props":186,"children":188},{"href":187},"..\u002Fslack-notification-triage\u002FSKILL.md",[189],{"type":46,"value":187},{"type":41,"tag":48,"props":191,"children":193},{"id":192},"reference-notes",[194],{"type":46,"value":195},"Reference Notes",{"type":41,"tag":84,"props":197,"children":198},{},[199,215],{"type":41,"tag":88,"props":200,"children":201},{},[202],{"type":41,"tag":92,"props":203,"children":204},{},[205,210],{"type":41,"tag":96,"props":206,"children":207},{},[208],{"type":46,"value":209},"Task",{"type":41,"tag":96,"props":211,"children":212},{},[213],{"type":46,"value":214},"Reference",{"type":41,"tag":107,"props":216,"children":217},{},[218],{"type":41,"tag":92,"props":219,"children":220},{},[221,226],{"type":41,"tag":114,"props":222,"children":223},{},[224],{"type":46,"value":225},"Slack Markdown formatting rules and examples",{"type":41,"tag":114,"props":227,"children":228},{},[229],{"type":41,"tag":61,"props":230,"children":232},{"href":231},".\u002Freferences\u002Fmarkdown.md",[233],{"type":46,"value":234},"references\u002Fmarkdown.md",{"type":41,"tag":48,"props":236,"children":238},{"id":237},"support-checks",[239],{"type":46,"value":240},"Support Checks",{"type":41,"tag":242,"props":243,"children":244},"ul",{},[245,251,256],{"type":41,"tag":246,"props":247,"children":248},"li",{},[249],{"type":46,"value":250},"Confirm the requested action is supported before asking the user for more input. If Slack does not support the action, say so immediately and offer the closest supported path instead of collecting unnecessary details.",{"type":41,"tag":246,"props":252,"children":253},{},[254],{"type":46,"value":255},"For broad Slack analysis requests, fail fast if the connector cannot establish the needed coverage or signals reliably. Do not invent channel names, imply the user is in a channel, or present workspace-wide conclusions as authoritative. Ask for a candidate list, a narrower scope, or a question that can be answered from specific channels, threads, profiles, or search results.",{"type":41,"tag":246,"props":257,"children":258},{},[259],{"type":46,"value":260},"The current Slack app surface here supports reading\u002Fsearching channels, users, threads, and canvases plus writing messages, drafts, scheduled messages, and canvases. Do not claim support for creating channels, editing messages, deleting messages, or other unsupported Slack admin actions.",{"type":41,"tag":48,"props":262,"children":264},{"id":263},"intent-routing",[265],{"type":46,"value":266},"Intent Routing",{"type":41,"tag":242,"props":268,"children":269},{},[270,275,280,285],{"type":41,"tag":246,"props":271,"children":272},{},[273],{"type":46,"value":274},"If the user explicitly asks to send, post, reply, share, or create something in Slack, follow that write intent directly. Do not downgrade the request into a draft unless the user asked for a draft or review-first flow.",{"type":41,"tag":246,"props":276,"children":277},{},[278],{"type":46,"value":279},"If the user explicitly asks for a draft, rewrite, or review-first workflow, use a draft.",{"type":41,"tag":246,"props":281,"children":282},{},[283],{"type":46,"value":284},"If the user asks for Slack analysis only, return the result in chat unless they also asked for Slack delivery.",{"type":41,"tag":246,"props":286,"children":287},{},[288],{"type":46,"value":289},"If the user asks for an unsupported Slack write action, say so and offer the closest supported path instead of forcing a draft.",{"type":41,"tag":48,"props":291,"children":293},{"id":292},"tool-rate-limits",[294],{"type":46,"value":295},"Tool Rate Limits",{"type":41,"tag":242,"props":297,"children":298},{},[299,328,341,346,351],{"type":41,"tag":246,"props":300,"children":301},{},[302,304,310,312,318,320,326],{"type":46,"value":303},"Slack tools have per-minute RPM quotas by bucket, not by individual tool. Treat ",{"type":41,"tag":69,"props":305,"children":307},{"className":306},[],[308],{"type":46,"value":309},"slack_search_*",{"type":46,"value":311}," tools as the search bucket, ",{"type":41,"tag":69,"props":313,"children":315},{"className":314},[],[316],{"type":46,"value":317},"slack_read_*",{"type":46,"value":319},", ",{"type":41,"tag":69,"props":321,"children":323},{"className":322},[],[324],{"type":46,"value":325},"slack_list_*",{"type":46,"value":327},", and lookup-style tools as the read bucket, and message, draft, schedule, or canvas creation tools as the send\u002Fwrite bucket.",{"type":41,"tag":246,"props":329,"children":330},{},[331,333,339],{"type":46,"value":332},"If a Slack tool returns a 429, do not retry immediately and do not switch to an equivalent tool in the same bucket. If the response includes ",{"type":41,"tag":69,"props":334,"children":336},{"className":335},[],[337],{"type":46,"value":338},"Retry-After",{"type":46,"value":340}," or another explicit wait hint, follow it. Otherwise wait about 30 seconds before calling that bucket again.",{"type":41,"tag":246,"props":342,"children":343},{},[344],{"type":46,"value":345},"If the same bucket returns another 429 during the task, wait about 1 minute before the next retry, then about 2 minutes after the next 429, continuing with exponential backoff as needed.",{"type":41,"tag":246,"props":347,"children":348},{},[349],{"type":46,"value":350},"A 429 in one bucket does not imply the other buckets are exhausted. While waiting on one bucket, continue making useful progress with other buckets when that can advance the task safely.",{"type":41,"tag":246,"props":352,"children":353},{},[354],{"type":46,"value":355},"If the task cannot be completed without the exhausted bucket after reasonable backoff, explain the rate limit to the user and return the best partial result or next step.",{"type":41,"tag":48,"props":357,"children":359},{"id":358},"dm-routing",[360],{"type":46,"value":361},"DM Routing",{"type":41,"tag":242,"props":363,"children":364},{},[365,370],{"type":41,"tag":246,"props":366,"children":367},{},[368],{"type":46,"value":369},"When the same message is meant for multiple specific people, first look for an existing group DM with the right people and prefer that over duplicate one-to-one DMs.",{"type":41,"tag":246,"props":371,"children":372},{},[373],{"type":46,"value":374},"If there is no suitable group DM, do not silently fan out separate DMs. Ask whether the user wants individual DMs instead, or ask them to create the group DM if that is the better path and the connector cannot create it.",{"type":41,"tag":48,"props":376,"children":378},{"id":377},"write-safety",[379],{"type":46,"value":380},"Write Safety",{"type":41,"tag":242,"props":382,"children":383},{},[384,389,394,399,404],{"type":41,"tag":246,"props":385,"children":386},{},[387],{"type":46,"value":388},"Preserve exact channel names, thread context, links, code snippets, and owners from the source conversation unless the user asks for changes.",{"type":41,"tag":246,"props":390,"children":391},{},[392],{"type":46,"value":393},"Before acting on a relative message target such as \"last message\", \"latest reply\", \"above\", or \"that message\", re-read the destination channel or thread and resolve the target from fresh results. Do not reuse earlier reads for reactions, replies, edits, or other writes.",{"type":41,"tag":246,"props":395,"children":396},{},[397],{"type":46,"value":398},"Treat @channel, @here, mass mentions, and customer-facing channels as high-impact. Call them out before posting.",{"type":41,"tag":246,"props":400,"children":401},{},[402],{"type":46,"value":403},"Keep post-ready drafts short enough to scan quickly unless the user asks for a long-form announcement.",{"type":41,"tag":246,"props":405,"children":406},{},[407],{"type":46,"value":408},"If there are multiple channels or threads with similar topics, identify the intended destination before drafting or posting.",{"type":41,"tag":48,"props":410,"children":412},{"id":411},"output-conventions",[413],{"type":46,"value":414},"Output Conventions",{"type":41,"tag":242,"props":416,"children":417},{},[418,423,435,448,453,458],{"type":41,"tag":246,"props":419,"children":420},{},[421],{"type":46,"value":422},"Prefer a short opener, a few tight bullets, and a clear ask or next step.",{"type":41,"tag":246,"props":424,"children":425},{},[426,428,433],{"type":46,"value":427},"Use Markdown formatting rules from ",{"type":41,"tag":69,"props":429,"children":431},{"className":430},[],[432],{"type":46,"value":234},{"type":46,"value":434}," for emphasis, lists, links, quotes, mentions, and code.",{"type":41,"tag":246,"props":436,"children":437},{},[438,440,446],{"type":46,"value":439},"For any outgoing Slack text, use the ",{"type":41,"tag":69,"props":441,"children":443},{"className":442},[],[444],{"type":46,"value":445},"slack-outgoing-message",{"type":46,"value":447}," skill.",{"type":41,"tag":246,"props":449,"children":450},{},[451],{"type":46,"value":452},"Distinguish clearly between a private summary for the user and a post-ready message for Slack.",{"type":41,"tag":246,"props":454,"children":455},{},[456],{"type":46,"value":457},"When summarizing a thread, lead with the latest status and then list blockers, decisions, and owners.",{"type":41,"tag":246,"props":459,"children":460},{},[461],{"type":46,"value":462},"When drafting a reply, match the tone of the channel and avoid over-formatting.",{"type":41,"tag":48,"props":464,"children":466},{"id":465},"example-requests",[467],{"type":46,"value":468},"Example Requests",{"type":41,"tag":242,"props":470,"children":471},{},[472,477,482,487],{"type":41,"tag":246,"props":473,"children":474},{},[475],{"type":46,"value":476},"\"Summarize the incident thread in #ops and draft a calm update for leadership.\"",{"type":41,"tag":246,"props":478,"children":479},{},[480],{"type":46,"value":481},"\"Turn these meeting notes into a short Slack post for the team channel.\"",{"type":41,"tag":246,"props":483,"children":484},{},[485],{"type":46,"value":486},"\"Read the product launch thread and draft a reply that confirms the timeline.\"",{"type":41,"tag":246,"props":488,"children":489},{},[490],{"type":46,"value":491},"\"Rewrite this long update so it lands well in Slack and still keeps the important links.\"",{"type":41,"tag":48,"props":493,"children":495},{"id":494},"light-fallback",[496],{"type":46,"value":497},"Light Fallback",{"type":41,"tag":55,"props":499,"children":500},{},[501],{"type":46,"value":502},"If Slack messages are missing, say that Slack access may be unavailable, the workspace may be disconnected, or the wrong channel or thread may be in scope, then ask the user to reconnect or clarify the destination.",{"items":504,"total":707},[505,526,549,566,582,601,618,634,650,664,676,691],{"slug":506,"name":506,"fn":507,"description":508,"org":509,"tags":510,"stars":523,"repoUrl":524,"updatedAt":525},"prior-auth-packet-builder","build healthcare prior authorization packets","Build a concise prior authorization packet from local case files and payer policy docs.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[511,514,517,520],{"name":512,"slug":513,"type":15},"Documents","documents",{"name":515,"slug":516,"type":15},"Healthcare","healthcare",{"name":518,"slug":519,"type":15},"Insurance","insurance",{"name":521,"slug":522,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":527,"name":527,"fn":528,"description":529,"org":530,"tags":531,"stars":546,"repoUrl":547,"updatedAt":548},"aspnet-core","build ASP.NET Core web applications","Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web Apps, Razor Pages, MVC, Minimal APIs, controller-based Web APIs, SignalR, gRPC, middleware, dependency injection, configuration, authentication, authorization, testing, performance, deployment, or ASP.NET Core upgrades.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[532,535,537,540,543],{"name":533,"slug":534,"type":15},".NET","dotnet",{"name":536,"slug":527,"type":15},"ASP.NET Core",{"name":538,"slug":539,"type":15},"Blazor","blazor",{"name":541,"slug":542,"type":15},"C#","csharp",{"name":544,"slug":545,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":550,"name":550,"fn":551,"description":552,"org":553,"tags":554,"stars":546,"repoUrl":547,"updatedAt":565},"chatgpt-apps","build ChatGPT Apps SDK applications","Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[555,558,561,564],{"name":556,"slug":557,"type":15},"Apps SDK","apps-sdk",{"name":559,"slug":560,"type":15},"ChatGPT","chatgpt",{"name":562,"slug":563,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":567,"name":567,"fn":568,"description":569,"org":570,"tags":571,"stars":546,"repoUrl":547,"updatedAt":581},"cli-creator","build CLIs from API docs","Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read\u002Fwrite commands, return stable JSON, manage auth, and pair with a companion skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[572,575,578],{"name":573,"slug":574,"type":15},"API Development","api-development",{"name":576,"slug":577,"type":15},"CLI","cli",{"name":579,"slug":580,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":583,"name":583,"fn":584,"description":585,"org":586,"tags":587,"stars":546,"repoUrl":547,"updatedAt":600},"cloudflare-deploy","deploy projects to Cloudflare","Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[588,591,594,597],{"name":589,"slug":590,"type":15},"Cloudflare","cloudflare",{"name":592,"slug":593,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":595,"slug":596,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":598,"slug":599,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":602,"name":602,"fn":603,"description":604,"org":605,"tags":606,"stars":546,"repoUrl":547,"updatedAt":617},"define-goal","define and set measurable project goals","Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy intention into a quantitative outcome. Use this skill for goal creation and goal refinement only; it does not manage durable snapshots, decision logs, or long-running execution artifacts.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[607,608,611,614],{"name":13,"slug":14,"type":15},{"name":609,"slug":610,"type":15},"Project Management","project-management",{"name":612,"slug":613,"type":15},"Strategy","strategy",{"name":615,"slug":616,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":619,"name":619,"fn":620,"description":621,"org":622,"tags":623,"stars":546,"repoUrl":547,"updatedAt":633},"figma","translate Figma designs into code","Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[624,627,629,632],{"name":625,"slug":626,"type":15},"Design","design",{"name":628,"slug":619,"type":15},"Figma",{"name":630,"slug":631,"type":15},"Frontend","frontend",{"name":562,"slug":563,"type":15},"2026-04-12T05:06:47.939943",{"slug":635,"name":635,"fn":636,"description":637,"org":638,"tags":639,"stars":546,"repoUrl":547,"updatedAt":649},"figma-code-connect-components","connect Figma designs to code components","Connects Figma design components to code components using Code Connect mapping tools. Use when user says \"code connect\", \"connect this component to code\", \"map this component\", \"link component to code\", \"create code connect mapping\", or wants to establish mappings between Figma designs and code implementations. For canvas writes via `use_figma`, use `figma-use`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[640,641,644,645,646],{"name":625,"slug":626,"type":15},{"name":642,"slug":643,"type":15},"Design System","design-system",{"name":628,"slug":619,"type":15},{"name":630,"slug":631,"type":15},{"name":647,"slug":648,"type":15},"UI Components","ui-components","2026-05-10T05:59:52.971881",{"slug":651,"name":651,"fn":652,"description":653,"org":654,"tags":655,"stars":546,"repoUrl":547,"updatedAt":663},"figma-create-design-system-rules","generate design system rules from Figma","Generates custom design system rules for the user's codebase. Use when user says \"create design system rules\", \"generate rules for my project\", \"set up design rules\", \"customize design system guidelines\", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server connection.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[656,657,658,661,662],{"name":625,"slug":626,"type":15},{"name":642,"slug":643,"type":15},{"name":659,"slug":660,"type":15},"Documentation","documentation",{"name":628,"slug":619,"type":15},{"name":630,"slug":631,"type":15},"2026-05-16T06:07:47.821474",{"slug":665,"name":665,"fn":666,"description":667,"org":668,"tags":669,"stars":546,"repoUrl":547,"updatedAt":675},"figma-implement-design","translate Figma designs into application code","Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions \"implement design\", \"generate code\", \"implement component\", provides Figma URLs, or asks to build components matching Figma specs. For Figma canvas writes via `use_figma`, use `figma-use`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[670,671,672,673,674],{"name":625,"slug":626,"type":15},{"name":628,"slug":619,"type":15},{"name":630,"slug":631,"type":15},{"name":647,"slug":648,"type":15},{"name":544,"slug":545,"type":15},"2026-05-16T06:07:40.583615",{"slug":677,"name":677,"fn":678,"description":679,"org":680,"tags":681,"stars":546,"repoUrl":547,"updatedAt":690},"hatch-pet","create animated pets for Codex","Create, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references. Use when a user wants a lightweight-worker Codex pet workflow, a non-pixel custom pet style, a prospect or company mascot pet, or a full 8x9 animated pet atlas with transparent unused cells, QA contact sheets, and pet.json packaging. This skill composes the installed $imagegen system skill for visual generation and uses bundled scripts for deterministic spritesheet assembly.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[682,685,686,689],{"name":683,"slug":684,"type":15},"Animation","animation",{"name":579,"slug":580,"type":15},{"name":687,"slug":688,"type":15},"Creative","creative",{"name":625,"slug":626,"type":15},"2026-05-02T05:31:48.48485",{"slug":692,"name":692,"fn":693,"description":694,"org":695,"tags":696,"stars":546,"repoUrl":547,"updatedAt":706},"imagegen","generate and edit raster images","Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG\u002Fvector\u002Fcode-native assets, extending an established icon or logo system, or building the visual directly in HTML\u002FCSS\u002Fcanvas.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[697,698,699,702,705],{"name":687,"slug":688,"type":15},{"name":625,"slug":626,"type":15},{"name":700,"slug":701,"type":15},"Image Generation","image-generation",{"name":703,"slug":704,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675,{"items":709,"total":823},[710,727,743,755,773,791,811],{"slug":711,"name":711,"fn":712,"description":713,"org":714,"tags":715,"stars":24,"repoUrl":25,"updatedAt":726},"accessibility-and-inclusive-visualization","make data visualizations accessible","Make data visualizations accessible and inclusive. Use when the user needs chart or diagram accessibility guidance, text alternatives for complex visuals, color and contrast review, keyboard support, reduced-motion behavior for animation or parallax, or an accessibility QA workflow for exported figures, UML-like diagrams, and dashboards.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[716,719,722,725],{"name":717,"slug":718,"type":15},"Accessibility","accessibility",{"name":720,"slug":721,"type":15},"Charts","charts",{"name":723,"slug":724,"type":15},"Data Visualization","data-visualization",{"name":625,"slug":626,"type":15},"2026-06-30T19:00:57.102",{"slug":728,"name":728,"fn":729,"description":730,"org":731,"tags":732,"stars":24,"repoUrl":25,"updatedAt":742},"agent-browser","automate browser interactions for agents","Browser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data, or automate any browser task. Also triggers when a dev server starts so you can verify it visually.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[733,736,739],{"name":734,"slug":735,"type":15},"Agents","agents",{"name":737,"slug":738,"type":15},"Browser Automation","browser-automation",{"name":740,"slug":741,"type":15},"Testing","testing","2026-04-06T18:41:03.44016",{"slug":744,"name":744,"fn":745,"description":746,"org":747,"tags":748,"stars":24,"repoUrl":25,"updatedAt":754},"agent-browser-verify","verify dev server output with automated browser","Automated browser verification for dev servers. Triggers when a dev server starts to run a visual gut-check with agent-browser — verifies the page loads, checks for console errors, validates key UI elements, and reports pass\u002Ffail before continuing.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[749,750,753],{"name":737,"slug":738,"type":15},{"name":751,"slug":752,"type":15},"Local Development","local-development",{"name":740,"slug":741,"type":15},"2026-04-06T18:41:17.526867",{"slug":756,"name":756,"fn":757,"description":758,"org":759,"tags":760,"stars":24,"repoUrl":25,"updatedAt":772},"agents-sdk","build AI agents on Cloudflare Workers","Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[761,762,763,766,769],{"name":734,"slug":735,"type":15},{"name":595,"slug":596,"type":15},{"name":764,"slug":765,"type":15},"SDK","sdk",{"name":767,"slug":768,"type":15},"Serverless","serverless",{"name":770,"slug":771,"type":15},"WebSockets","websockets","2026-04-06T18:39:51.717063",{"slug":774,"name":774,"fn":775,"description":776,"org":777,"tags":778,"stars":24,"repoUrl":25,"updatedAt":790},"ai-elements","build chat UIs with AI Elements","AI Elements component library guidance — pre-built React components for AI interfaces built on shadcn\u002Fui. Use when building chat UIs, message displays, tool call rendering, streaming responses, reasoning panels, or any AI-native interface with the AI SDK.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[779,780,783,786,787],{"name":630,"slug":631,"type":15},{"name":781,"slug":782,"type":15},"React","react",{"name":784,"slug":785,"type":15},"shadcn\u002Fui","shadcn-ui",{"name":647,"slug":648,"type":15},{"name":788,"slug":789,"type":15},"Vercel","vercel","2026-04-06T18:40:59.619419",{"slug":792,"name":792,"fn":793,"description":794,"org":795,"tags":796,"stars":24,"repoUrl":25,"updatedAt":810},"ai-gateway","configure Vercel AI Gateway","Vercel AI Gateway expert guidance. Use when configuring model routing, provider failover, cost tracking, or managing multiple AI providers through a unified API.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[797,800,803,806,809],{"name":798,"slug":799,"type":15},"AI Infrastructure","ai-infrastructure",{"name":801,"slug":802,"type":15},"Cost Optimization","cost-optimization",{"name":804,"slug":805,"type":15},"LLM","llm",{"name":807,"slug":808,"type":15},"Performance","performance",{"name":788,"slug":789,"type":15},"2026-04-06T18:40:44.377464",{"slug":812,"name":812,"fn":813,"description":814,"org":815,"tags":816,"stars":24,"repoUrl":25,"updatedAt":822},"ai-generation-persistence","implement persistence patterns for AI generations","AI generation persistence patterns — unique IDs, addressable URLs, database storage, and cost tracking for every LLM generation",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[817,818,821],{"name":801,"slug":802,"type":15},{"name":819,"slug":820,"type":15},"Database","database",{"name":804,"slug":805,"type":15},"2026-04-06T18:41:08.513425",600]