[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-threat-model":3,"mdc--74lkl4-key":33,"related-org-openai-threat-model":413,"related-repo-openai-threat-model":618},{"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":28,"sourceUrl":31,"mdContent":32},"threat-model","create and update repository threat models","Use when Codex is already in the threat-modeling phase of a security scan, the user explicitly invokes $threat-model, or the user explicitly asks to create, update, or persist a repository threat model. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.",{"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],{"name":13,"slug":14,"type":15},"Security","security","tag",{"name":17,"slug":18,"type":15},"Codex","codex",{"name":20,"slug":21,"type":15},"Threat Modeling","threat-modeling",3992,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-05-01T06:02:29.461649",null,465,[],{"repoUrl":23,"stars":22,"forks":26,"topics":29,"description":30},[],"OpenAI Plugins","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fcodex-security\u002Fskills\u002Fthreat-model","---\nname: threat-model\ndescription: Use when Codex is already in the threat-modeling phase of a security scan, the user explicitly invokes $threat-model, or the user explicitly asks to create, update, or persist a repository threat model. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.\n---\n\n# Security Threat Model\n\n## Objective\n\nEstablish the repository-scoped threat model at the path defined in `..\u002F..\u002Freferences\u002Fscan-artifacts.md`. Reuse a cached model only when its final `Repository` and `Version` lines match the current target.\n\n`AGENTS.md` or resolved `SECURITY.md` guidance can be that authoritative source when it is sufficiently specific about the repository's product surfaces, trust boundaries, attacker-controlled inputs, assumptions, or security scan guidance to serve as the threat model.\n\nIf no threat model is provided, generate a repository-scoped threat model to be used in future bug discovery. The threat model should holistically cover the entire repository and should make it obvious:\n\n- what assets or privileges matter\n- what trust boundaries exist\n- what inputs are attacker-controlled\n- what invariants the code must preserve\n- what repository-wide failure modes would matter most\n\n## Artifact Resolution\n\nThe path references in this skill are the default locations for this phase.\nIf the user explicitly provides a different path for a required input or output, use the user-provided path instead of the corresponding default path referenced in this skill.\nIf a required input is still missing, stop and ask the user for it before continuing.\nUse the shared scan artifact path conventions in `..\u002F..\u002Freferences\u002Fscan-artifacts.md`.\n\n## Workflow\n\n1. Resolve `target_id`, the current version (revision for an immutable Git tree, snapshot digest otherwise), and the repository-scoped threat model path using `..\u002F..\u002Freferences\u002Fscan-artifacts.md`.\n2. If the repository-scoped threat model exists, reuse it only when its final `Repository` and `Version` lines match those current values. Otherwise regenerate it.\n3. Before inspecting repository source or generating a threat model, read `..\u002F..\u002Freferences\u002Fsecurity-guidance.md` and the policy resolved for the scan target. Resolve it first if the coordinator did not supply it.\n4. If a threat model or authoritative security scan guidance is provided or referenced:\n   - preserve it unchanged as the threat model body\n   - treat that body as the only threat model source of truth\n   - do not expand, summarize, or reinterpret the body\n   - `AGENTS.md` is acceptable here when it is clearly being used as the security scan guidance or threat model source for this scan and is sufficiently repository-specific to stand in for a threat model\n5. Otherwise, generate a repository-scoped threat model using the checklist below.\n6. Before finalizing this phase, sanity-check that:\n   - the threat model is repository-scoped rather than being centered around any specific scan target\n   - it describes repository-wide primary product or runtime surfaces and trust boundaries before covering any narrower examples\n   - any vulnerability-class discussion is about repository-context classes, not findings about any current diff\n7. Append the exact `Repository` and `Version` lines from `..\u002F..\u002Freferences\u002Fscan-artifacts.md`, then write the threat model to the repository-scoped path.\n\n## Threat Model Generation Guidance\n\nGenerate and structure the threat model using `references\u002Fthreat-model-guidance.md`.\n\n## Hard Rules\n\n- A provided threat model or authoritative security scan guidance is authoritative. Keep its body unchanged and append only the required cache footer.\n- Threat model generation must stay at repository scope unless the user explicitly asks for narrower scope.\n- Do not turn this phase into findings about any current diff.\n- Do not let the current scan target, touched subsystem, or changed directories become the center of gravity for this phase unless the user explicitly asks for that narrower scope.\n- In large monorepos, avoid centering `personal\u002F`, `test\u002F`, `tests\u002F`, `docs\u002F`, `examples\u002F`, or one-off developer tooling unless repository evidence shows those are real deployed or privileged workflow surfaces.\n- Call out trust boundaries and assumptions explicitly.\n- Keep references to vulnerability types at the level of repository-context classes, rather than any diff findings.\n- Persist the threat model output to the repository-scoped threat model path from `..\u002F..\u002Freferences\u002Fscan-artifacts.md`.\n",{"data":34,"body":35},{"name":4,"description":6},{"type":36,"children":37},"root",[38,47,54,85,104,109,139,145,157,163,303,309,321,327],{"type":39,"tag":40,"props":41,"children":43},"element","h1",{"id":42},"security-threat-model",[44],{"type":45,"value":46},"text","Security Threat Model",{"type":39,"tag":48,"props":49,"children":51},"h2",{"id":50},"objective",[52],{"type":45,"value":53},"Objective",{"type":39,"tag":55,"props":56,"children":57},"p",{},[58,60,67,69,75,77,83],{"type":45,"value":59},"Establish the repository-scoped threat model at the path defined in ",{"type":39,"tag":61,"props":62,"children":64},"code",{"className":63},[],[65],{"type":45,"value":66},"..\u002F..\u002Freferences\u002Fscan-artifacts.md",{"type":45,"value":68},". Reuse a cached model only when its final ",{"type":39,"tag":61,"props":70,"children":72},{"className":71},[],[73],{"type":45,"value":74},"Repository",{"type":45,"value":76}," and ",{"type":39,"tag":61,"props":78,"children":80},{"className":79},[],[81],{"type":45,"value":82},"Version",{"type":45,"value":84}," lines match the current target.",{"type":39,"tag":55,"props":86,"children":87},{},[88,94,96,102],{"type":39,"tag":61,"props":89,"children":91},{"className":90},[],[92],{"type":45,"value":93},"AGENTS.md",{"type":45,"value":95}," or resolved ",{"type":39,"tag":61,"props":97,"children":99},{"className":98},[],[100],{"type":45,"value":101},"SECURITY.md",{"type":45,"value":103}," guidance can be that authoritative source when it is sufficiently specific about the repository's product surfaces, trust boundaries, attacker-controlled inputs, assumptions, or security scan guidance to serve as the threat model.",{"type":39,"tag":55,"props":105,"children":106},{},[107],{"type":45,"value":108},"If no threat model is provided, generate a repository-scoped threat model to be used in future bug discovery. The threat model should holistically cover the entire repository and should make it obvious:",{"type":39,"tag":110,"props":111,"children":112},"ul",{},[113,119,124,129,134],{"type":39,"tag":114,"props":115,"children":116},"li",{},[117],{"type":45,"value":118},"what assets or privileges matter",{"type":39,"tag":114,"props":120,"children":121},{},[122],{"type":45,"value":123},"what trust boundaries exist",{"type":39,"tag":114,"props":125,"children":126},{},[127],{"type":45,"value":128},"what inputs are attacker-controlled",{"type":39,"tag":114,"props":130,"children":131},{},[132],{"type":45,"value":133},"what invariants the code must preserve",{"type":39,"tag":114,"props":135,"children":136},{},[137],{"type":45,"value":138},"what repository-wide failure modes would matter most",{"type":39,"tag":48,"props":140,"children":142},{"id":141},"artifact-resolution",[143],{"type":45,"value":144},"Artifact Resolution",{"type":39,"tag":55,"props":146,"children":147},{},[148,150,155],{"type":45,"value":149},"The path references in this skill are the default locations for this phase.\nIf the user explicitly provides a different path for a required input or output, use the user-provided path instead of the corresponding default path referenced in this skill.\nIf a required input is still missing, stop and ask the user for it before continuing.\nUse the shared scan artifact path conventions in ",{"type":39,"tag":61,"props":151,"children":153},{"className":152},[],[154],{"type":45,"value":66},{"type":45,"value":156},".",{"type":39,"tag":48,"props":158,"children":160},{"id":159},"workflow",[161],{"type":45,"value":162},"Workflow",{"type":39,"tag":164,"props":165,"children":166},"ol",{},[167,186,204,217,250,255,278],{"type":39,"tag":114,"props":168,"children":169},{},[170,172,178,180,185],{"type":45,"value":171},"Resolve ",{"type":39,"tag":61,"props":173,"children":175},{"className":174},[],[176],{"type":45,"value":177},"target_id",{"type":45,"value":179},", the current version (revision for an immutable Git tree, snapshot digest otherwise), and the repository-scoped threat model path using ",{"type":39,"tag":61,"props":181,"children":183},{"className":182},[],[184],{"type":45,"value":66},{"type":45,"value":156},{"type":39,"tag":114,"props":187,"children":188},{},[189,191,196,197,202],{"type":45,"value":190},"If the repository-scoped threat model exists, reuse it only when its final ",{"type":39,"tag":61,"props":192,"children":194},{"className":193},[],[195],{"type":45,"value":74},{"type":45,"value":76},{"type":39,"tag":61,"props":198,"children":200},{"className":199},[],[201],{"type":45,"value":82},{"type":45,"value":203}," lines match those current values. Otherwise regenerate it.",{"type":39,"tag":114,"props":205,"children":206},{},[207,209,215],{"type":45,"value":208},"Before inspecting repository source or generating a threat model, read ",{"type":39,"tag":61,"props":210,"children":212},{"className":211},[],[213],{"type":45,"value":214},"..\u002F..\u002Freferences\u002Fsecurity-guidance.md",{"type":45,"value":216}," and the policy resolved for the scan target. Resolve it first if the coordinator did not supply it.",{"type":39,"tag":114,"props":218,"children":219},{},[220,222],{"type":45,"value":221},"If a threat model or authoritative security scan guidance is provided or referenced:\n",{"type":39,"tag":110,"props":223,"children":224},{},[225,230,235,240],{"type":39,"tag":114,"props":226,"children":227},{},[228],{"type":45,"value":229},"preserve it unchanged as the threat model body",{"type":39,"tag":114,"props":231,"children":232},{},[233],{"type":45,"value":234},"treat that body as the only threat model source of truth",{"type":39,"tag":114,"props":236,"children":237},{},[238],{"type":45,"value":239},"do not expand, summarize, or reinterpret the body",{"type":39,"tag":114,"props":241,"children":242},{},[243,248],{"type":39,"tag":61,"props":244,"children":246},{"className":245},[],[247],{"type":45,"value":93},{"type":45,"value":249}," is acceptable here when it is clearly being used as the security scan guidance or threat model source for this scan and is sufficiently repository-specific to stand in for a threat model",{"type":39,"tag":114,"props":251,"children":252},{},[253],{"type":45,"value":254},"Otherwise, generate a repository-scoped threat model using the checklist below.",{"type":39,"tag":114,"props":256,"children":257},{},[258,260],{"type":45,"value":259},"Before finalizing this phase, sanity-check that:\n",{"type":39,"tag":110,"props":261,"children":262},{},[263,268,273],{"type":39,"tag":114,"props":264,"children":265},{},[266],{"type":45,"value":267},"the threat model is repository-scoped rather than being centered around any specific scan target",{"type":39,"tag":114,"props":269,"children":270},{},[271],{"type":45,"value":272},"it describes repository-wide primary product or runtime surfaces and trust boundaries before covering any narrower examples",{"type":39,"tag":114,"props":274,"children":275},{},[276],{"type":45,"value":277},"any vulnerability-class discussion is about repository-context classes, not findings about any current diff",{"type":39,"tag":114,"props":279,"children":280},{},[281,283,288,289,294,296,301],{"type":45,"value":282},"Append the exact ",{"type":39,"tag":61,"props":284,"children":286},{"className":285},[],[287],{"type":45,"value":74},{"type":45,"value":76},{"type":39,"tag":61,"props":290,"children":292},{"className":291},[],[293],{"type":45,"value":82},{"type":45,"value":295}," lines from ",{"type":39,"tag":61,"props":297,"children":299},{"className":298},[],[300],{"type":45,"value":66},{"type":45,"value":302},", then write the threat model to the repository-scoped path.",{"type":39,"tag":48,"props":304,"children":306},{"id":305},"threat-model-generation-guidance",[307],{"type":45,"value":308},"Threat Model Generation Guidance",{"type":39,"tag":55,"props":310,"children":311},{},[312,314,320],{"type":45,"value":313},"Generate and structure the threat model using ",{"type":39,"tag":61,"props":315,"children":317},{"className":316},[],[318],{"type":45,"value":319},"references\u002Fthreat-model-guidance.md",{"type":45,"value":156},{"type":39,"tag":48,"props":322,"children":324},{"id":323},"hard-rules",[325],{"type":45,"value":326},"Hard Rules",{"type":39,"tag":110,"props":328,"children":329},{},[330,335,340,345,350,392,397,402],{"type":39,"tag":114,"props":331,"children":332},{},[333],{"type":45,"value":334},"A provided threat model or authoritative security scan guidance is authoritative. Keep its body unchanged and append only the required cache footer.",{"type":39,"tag":114,"props":336,"children":337},{},[338],{"type":45,"value":339},"Threat model generation must stay at repository scope unless the user explicitly asks for narrower scope.",{"type":39,"tag":114,"props":341,"children":342},{},[343],{"type":45,"value":344},"Do not turn this phase into findings about any current diff.",{"type":39,"tag":114,"props":346,"children":347},{},[348],{"type":45,"value":349},"Do not let the current scan target, touched subsystem, or changed directories become the center of gravity for this phase unless the user explicitly asks for that narrower scope.",{"type":39,"tag":114,"props":351,"children":352},{},[353,355,361,363,369,370,376,377,383,384,390],{"type":45,"value":354},"In large monorepos, avoid centering ",{"type":39,"tag":61,"props":356,"children":358},{"className":357},[],[359],{"type":45,"value":360},"personal\u002F",{"type":45,"value":362},", ",{"type":39,"tag":61,"props":364,"children":366},{"className":365},[],[367],{"type":45,"value":368},"test\u002F",{"type":45,"value":362},{"type":39,"tag":61,"props":371,"children":373},{"className":372},[],[374],{"type":45,"value":375},"tests\u002F",{"type":45,"value":362},{"type":39,"tag":61,"props":378,"children":380},{"className":379},[],[381],{"type":45,"value":382},"docs\u002F",{"type":45,"value":362},{"type":39,"tag":61,"props":385,"children":387},{"className":386},[],[388],{"type":45,"value":389},"examples\u002F",{"type":45,"value":391},", or one-off developer tooling unless repository evidence shows those are real deployed or privileged workflow surfaces.",{"type":39,"tag":114,"props":393,"children":394},{},[395],{"type":45,"value":396},"Call out trust boundaries and assumptions explicitly.",{"type":39,"tag":114,"props":398,"children":399},{},[400],{"type":45,"value":401},"Keep references to vulnerability types at the level of repository-context classes, rather than any diff findings.",{"type":39,"tag":114,"props":403,"children":404},{},[405,407,412],{"type":45,"value":406},"Persist the threat model output to the repository-scoped threat model path from ",{"type":39,"tag":61,"props":408,"children":410},{"className":409},[],[411],{"type":45,"value":66},{"type":45,"value":156},{"items":414,"total":617},[415,436,459,476,490,509,528,544,560,574,586,601],{"slug":416,"name":416,"fn":417,"description":418,"org":419,"tags":420,"stars":433,"repoUrl":434,"updatedAt":435},"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},[421,424,427,430],{"name":422,"slug":423,"type":15},"Documents","documents",{"name":425,"slug":426,"type":15},"Healthcare","healthcare",{"name":428,"slug":429,"type":15},"Insurance","insurance",{"name":431,"slug":432,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":437,"name":437,"fn":438,"description":439,"org":440,"tags":441,"stars":456,"repoUrl":457,"updatedAt":458},"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},[442,445,447,450,453],{"name":443,"slug":444,"type":15},".NET","dotnet",{"name":446,"slug":437,"type":15},"ASP.NET Core",{"name":448,"slug":449,"type":15},"Blazor","blazor",{"name":451,"slug":452,"type":15},"C#","csharp",{"name":454,"slug":455,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":460,"name":460,"fn":461,"description":462,"org":463,"tags":464,"stars":456,"repoUrl":457,"updatedAt":475},"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},[465,468,471,474],{"name":466,"slug":467,"type":15},"Apps SDK","apps-sdk",{"name":469,"slug":470,"type":15},"ChatGPT","chatgpt",{"name":472,"slug":473,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":477,"name":477,"fn":478,"description":479,"org":480,"tags":481,"stars":456,"repoUrl":457,"updatedAt":489},"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},[482,485,488],{"name":483,"slug":484,"type":15},"API Development","api-development",{"name":486,"slug":487,"type":15},"CLI","cli",{"name":17,"slug":18,"type":15},"2026-04-12T05:07:04.132762",{"slug":491,"name":491,"fn":492,"description":493,"org":494,"tags":495,"stars":456,"repoUrl":457,"updatedAt":508},"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},[496,499,502,505],{"name":497,"slug":498,"type":15},"Cloudflare","cloudflare",{"name":500,"slug":501,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":503,"slug":504,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":506,"slug":507,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":510,"name":510,"fn":511,"description":512,"org":513,"tags":514,"stars":456,"repoUrl":457,"updatedAt":527},"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},[515,518,521,524],{"name":516,"slug":517,"type":15},"Productivity","productivity",{"name":519,"slug":520,"type":15},"Project Management","project-management",{"name":522,"slug":523,"type":15},"Strategy","strategy",{"name":525,"slug":526,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":529,"name":529,"fn":530,"description":531,"org":532,"tags":533,"stars":456,"repoUrl":457,"updatedAt":543},"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},[534,537,539,542],{"name":535,"slug":536,"type":15},"Design","design",{"name":538,"slug":529,"type":15},"Figma",{"name":540,"slug":541,"type":15},"Frontend","frontend",{"name":472,"slug":473,"type":15},"2026-04-12T05:06:47.939943",{"slug":545,"name":545,"fn":546,"description":547,"org":548,"tags":549,"stars":456,"repoUrl":457,"updatedAt":559},"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},[550,551,554,555,556],{"name":535,"slug":536,"type":15},{"name":552,"slug":553,"type":15},"Design System","design-system",{"name":538,"slug":529,"type":15},{"name":540,"slug":541,"type":15},{"name":557,"slug":558,"type":15},"UI Components","ui-components","2026-05-10T05:59:52.971881",{"slug":561,"name":561,"fn":562,"description":563,"org":564,"tags":565,"stars":456,"repoUrl":457,"updatedAt":573},"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},[566,567,568,571,572],{"name":535,"slug":536,"type":15},{"name":552,"slug":553,"type":15},{"name":569,"slug":570,"type":15},"Documentation","documentation",{"name":538,"slug":529,"type":15},{"name":540,"slug":541,"type":15},"2026-05-16T06:07:47.821474",{"slug":575,"name":575,"fn":576,"description":577,"org":578,"tags":579,"stars":456,"repoUrl":457,"updatedAt":585},"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},[580,581,582,583,584],{"name":535,"slug":536,"type":15},{"name":538,"slug":529,"type":15},{"name":540,"slug":541,"type":15},{"name":557,"slug":558,"type":15},{"name":454,"slug":455,"type":15},"2026-05-16T06:07:40.583615",{"slug":587,"name":587,"fn":588,"description":589,"org":590,"tags":591,"stars":456,"repoUrl":457,"updatedAt":600},"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},[592,595,596,599],{"name":593,"slug":594,"type":15},"Animation","animation",{"name":17,"slug":18,"type":15},{"name":597,"slug":598,"type":15},"Creative","creative",{"name":535,"slug":536,"type":15},"2026-05-02T05:31:48.48485",{"slug":602,"name":602,"fn":603,"description":604,"org":605,"tags":606,"stars":456,"repoUrl":457,"updatedAt":616},"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},[607,608,609,612,615],{"name":597,"slug":598,"type":15},{"name":535,"slug":536,"type":15},{"name":610,"slug":611,"type":15},"Image Generation","image-generation",{"name":613,"slug":614,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675,{"items":619,"total":733},[620,637,653,665,683,701,721],{"slug":621,"name":621,"fn":622,"description":623,"org":624,"tags":625,"stars":22,"repoUrl":23,"updatedAt":636},"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},[626,629,632,635],{"name":627,"slug":628,"type":15},"Accessibility","accessibility",{"name":630,"slug":631,"type":15},"Charts","charts",{"name":633,"slug":634,"type":15},"Data Visualization","data-visualization",{"name":535,"slug":536,"type":15},"2026-06-30T19:00:57.102",{"slug":638,"name":638,"fn":639,"description":640,"org":641,"tags":642,"stars":22,"repoUrl":23,"updatedAt":652},"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},[643,646,649],{"name":644,"slug":645,"type":15},"Agents","agents",{"name":647,"slug":648,"type":15},"Browser Automation","browser-automation",{"name":650,"slug":651,"type":15},"Testing","testing","2026-04-06T18:41:03.44016",{"slug":654,"name":654,"fn":655,"description":656,"org":657,"tags":658,"stars":22,"repoUrl":23,"updatedAt":664},"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},[659,660,663],{"name":647,"slug":648,"type":15},{"name":661,"slug":662,"type":15},"Local Development","local-development",{"name":650,"slug":651,"type":15},"2026-04-06T18:41:17.526867",{"slug":666,"name":666,"fn":667,"description":668,"org":669,"tags":670,"stars":22,"repoUrl":23,"updatedAt":682},"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},[671,672,673,676,679],{"name":644,"slug":645,"type":15},{"name":503,"slug":504,"type":15},{"name":674,"slug":675,"type":15},"SDK","sdk",{"name":677,"slug":678,"type":15},"Serverless","serverless",{"name":680,"slug":681,"type":15},"WebSockets","websockets","2026-04-06T18:39:51.717063",{"slug":684,"name":684,"fn":685,"description":686,"org":687,"tags":688,"stars":22,"repoUrl":23,"updatedAt":700},"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},[689,690,693,696,697],{"name":540,"slug":541,"type":15},{"name":691,"slug":692,"type":15},"React","react",{"name":694,"slug":695,"type":15},"shadcn\u002Fui","shadcn-ui",{"name":557,"slug":558,"type":15},{"name":698,"slug":699,"type":15},"Vercel","vercel","2026-04-06T18:40:59.619419",{"slug":702,"name":702,"fn":703,"description":704,"org":705,"tags":706,"stars":22,"repoUrl":23,"updatedAt":720},"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},[707,710,713,716,719],{"name":708,"slug":709,"type":15},"AI Infrastructure","ai-infrastructure",{"name":711,"slug":712,"type":15},"Cost Optimization","cost-optimization",{"name":714,"slug":715,"type":15},"LLM","llm",{"name":717,"slug":718,"type":15},"Performance","performance",{"name":698,"slug":699,"type":15},"2026-04-06T18:40:44.377464",{"slug":722,"name":722,"fn":723,"description":724,"org":725,"tags":726,"stars":22,"repoUrl":23,"updatedAt":732},"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},[727,728,731],{"name":711,"slug":712,"type":15},{"name":729,"slug":730,"type":15},"Database","database",{"name":714,"slug":715,"type":15},"2026-04-06T18:41:08.513425",600]