[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-plugin-eval":3,"mdc-3s2gdj-key":36,"related-repo-openai-plugin-eval":916,"related-org-openai-plugin-eval":1036},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":25,"repoUrl":26,"updatedAt":27,"license":28,"forks":29,"topics":30,"repo":31,"sourceUrl":34,"mdContent":35},"plugin-eval","evaluate and benchmark agent skills","Help engineers evaluate a local skill or plugin, explain why it scored that way, show what to fix first, measure real token usage, benchmark starter scenarios, or decide what to run next. Use when the user says things like \"evaluate this skill\", \"give me an analysis of the game dev skill\", \"why did this score that way\", \"what should I fix first\", \"measure the real token usage of this skill\", or \"what should I run next?\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"openai","OpenAI","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fopenai.png",[12,16,19,22],{"name":13,"slug":14,"type":15},"Performance","performance","tag",{"name":17,"slug":18,"type":15},"Evals","evals",{"name":20,"slug":21,"type":15},"Agents","agents",{"name":23,"slug":24,"type":15},"Engineering","engineering",3992,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-04-17T05:07:31.113837",null,465,[],{"repoUrl":26,"stars":25,"forks":29,"topics":32,"description":33},[],"OpenAI Plugins","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fplugin-eval\u002Fskills\u002Fplugin-eval","---\nname: plugin-eval\ndescription: Help engineers evaluate a local skill or plugin, explain why it scored that way, show what to fix first, measure real token usage, benchmark starter scenarios, or decide what to run next. Use when the user says things like \"evaluate this skill\", \"give me an analysis of the game dev skill\", \"why did this score that way\", \"what should I fix first\", \"measure the real token usage of this skill\", or \"what should I run next?\".\n---\n\n# Plugin Eval\n\nUse this as the beginner-friendly umbrella entrypoint for local Codex skill and plugin evaluation.\n\n## Start Here\n\n1. Resolve whether the target path is a skill, a plugin, or another local folder.\n2. Prefer the chat-first router when the user speaks naturally or is not sure which command they need:\n\n```bash\nplugin-eval start \u003Cpath> --request \"\u003Cuser request>\" --format markdown\n```\n\n3. Route natural chat requests to the matching workflow:\n   - \"Give me an analysis of the game dev skill.\" -> resolve the named skill path, run `plugin-eval analyze \u003Cpath> --format markdown`, then initialize a benchmark and show the setup questions needed to tailor `benchmark.json`\n   - \"Evaluate this skill.\" -> `plugin-eval analyze \u003Cpath> --format markdown`\n   - \"Why did this score that way?\" -> `plugin-eval analyze \u003Cpath> --format markdown`\n   - \"What should I fix first?\" -> `plugin-eval analyze \u003Cpath> --format markdown`\n   - \"Explain the token budget for this skill.\" -> `plugin-eval explain-budget \u003Cpath> --format markdown`\n   - \"Measure the real token usage of this skill.\" -> benchmark flow, then `plugin-eval measurement-plan`\n   - \"Help me benchmark this plugin.\" -> starter benchmark flow\n   - \"What should I run next?\" -> `plugin-eval start \u003Cpath> --request \"What should I run next?\" --format markdown`\n4. If the user wants rewrite help after evaluation, route to `..\u002Fimprove-skill\u002FSKILL.md`.\n5. If the user wants a custom rubric, route to `..\u002Fmetric-pack-designer\u002FSKILL.md`.\n6. If the user names a skill instead of giving a path, resolve it locally before running commands:\n   - check `~\u002F.codex\u002Fskills\u002F\u003Cskill-name>` first\n   - then check any repo-local `skills\u002F\u003Cskill-name>` directory\n   - if the name is still ambiguous, ask one short clarifying question before continuing\n7. When the request sounds like \"analysis\" rather than just \"evaluate\", do the fuller path:\n   - run the report\n   - initialize `.plugin-eval\u002Fbenchmark.json`\n   - surface the setup questions that will refine the starter scenarios\n   - preview the dry-run command the user can execute next\n\n## Chat Requests To Recognize\n\n- `Give me an analysis of the game dev skill.`\n- `Evaluate this skill.`\n- `Evaluate this plugin.`\n- `Why did this score that way?`\n- `What should I fix first?`\n- `Explain the token budget for this skill.`\n- `Measure the real token usage of this skill.`\n- `Help me benchmark this plugin.`\n- `What should I run next?`\n\n## Matching Commands\n\n```bash\nplugin-eval start \u003Cpath> --request \"Evaluate this skill.\" --format markdown\nplugin-eval start \u003Cpath> --request \"Give me a full analysis of this skill, including benchmark setup.\" --format markdown\nplugin-eval analyze \u003Cpath> --format markdown\nplugin-eval explain-budget \u003Cpath> --format markdown\nplugin-eval measurement-plan \u003Cpath> --format markdown\nplugin-eval init-benchmark \u003Cpath>\nplugin-eval benchmark \u003Cpath> --dry-run\nplugin-eval benchmark \u003Cpath>\n```\n\n## Output Expectations\n\n- Prefer the JSON result as the source of truth.\n- Lead with `At a Glance`, `Why It Matters`, `Fix First`, and `Recommended Next Step`.\n- Keep the `why` content terse and easy to skim.\n- Call out whether budget numbers are static estimates or measured harness results.\n- Show the user the exact chat phrase they can reuse next, the `plugin-eval start` command that routes it, and the first local workflow command behind it.\n- When the user asks for an analysis of a named skill, do not stop at the report if benchmark setup is still missing.\n- When the user is asking about a skill specifically, hand off to `..\u002Fevaluate-skill\u002FSKILL.md`.\n- When the user is asking about a plugin bundle, hand off to `..\u002Fevaluate-plugin\u002FSKILL.md`.\n\n## References\n\n- `..\u002F..\u002Freferences\u002Fchat-first-workflows.md`\n- `..\u002F..\u002Freferences\u002Ftechnical-design.md`\n- `..\u002F..\u002Freferences\u002Fevaluation-result-schema.md`\n",{"data":37,"body":38},{"name":4,"description":6},{"type":39,"children":40},"root",[41,49,55,62,77,158,356,362,446,452,765,771,874,880,910],{"type":42,"tag":43,"props":44,"children":45},"element","h1",{"id":4},[46],{"type":47,"value":48},"text","Plugin Eval",{"type":42,"tag":50,"props":51,"children":52},"p",{},[53],{"type":47,"value":54},"Use this as the beginner-friendly umbrella entrypoint for local Codex skill and plugin evaluation.",{"type":42,"tag":56,"props":57,"children":59},"h2",{"id":58},"start-here",[60],{"type":47,"value":61},"Start Here",{"type":42,"tag":63,"props":64,"children":65},"ol",{},[66,72],{"type":42,"tag":67,"props":68,"children":69},"li",{},[70],{"type":47,"value":71},"Resolve whether the target path is a skill, a plugin, or another local folder.",{"type":42,"tag":67,"props":73,"children":74},{},[75],{"type":47,"value":76},"Prefer the chat-first router when the user speaks naturally or is not sure which command they need:",{"type":42,"tag":78,"props":79,"children":84},"pre",{"className":80,"code":81,"language":82,"meta":83,"style":83},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","plugin-eval start \u003Cpath> --request \"\u003Cuser request>\" --format markdown\n","bash","",[85],{"type":42,"tag":86,"props":87,"children":88},"code",{"__ignoreMap":83},[89],{"type":42,"tag":90,"props":91,"children":94},"span",{"class":92,"line":93},"line",1,[95,100,106,112,117,123,128,133,138,143,148,153],{"type":42,"tag":90,"props":96,"children":98},{"style":97},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[99],{"type":47,"value":4},{"type":42,"tag":90,"props":101,"children":103},{"style":102},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[104],{"type":47,"value":105}," start",{"type":42,"tag":90,"props":107,"children":109},{"style":108},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[110],{"type":47,"value":111}," \u003C",{"type":42,"tag":90,"props":113,"children":114},{"style":102},[115],{"type":47,"value":116},"pat",{"type":42,"tag":90,"props":118,"children":120},{"style":119},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[121],{"type":47,"value":122},"h",{"type":42,"tag":90,"props":124,"children":125},{"style":108},[126],{"type":47,"value":127},">",{"type":42,"tag":90,"props":129,"children":130},{"style":102},[131],{"type":47,"value":132}," --request",{"type":42,"tag":90,"props":134,"children":135},{"style":108},[136],{"type":47,"value":137}," \"",{"type":42,"tag":90,"props":139,"children":140},{"style":102},[141],{"type":47,"value":142},"\u003Cuser request>",{"type":42,"tag":90,"props":144,"children":145},{"style":108},[146],{"type":47,"value":147},"\"",{"type":42,"tag":90,"props":149,"children":150},{"style":102},[151],{"type":47,"value":152}," --format",{"type":42,"tag":90,"props":154,"children":155},{"style":102},[156],{"type":47,"value":157}," markdown\n",{"type":42,"tag":63,"props":159,"children":161},{"start":160},3,[162,258,271,283,322],{"type":42,"tag":67,"props":163,"children":164},{},[165,167],{"type":47,"value":166},"Route natural chat requests to the matching workflow:\n",{"type":42,"tag":168,"props":169,"children":170},"ul",{},[171,190,200,210,220,231,242,247],{"type":42,"tag":67,"props":172,"children":173},{},[174,176,182,184],{"type":47,"value":175},"\"Give me an analysis of the game dev skill.\" -> resolve the named skill path, run ",{"type":42,"tag":86,"props":177,"children":179},{"className":178},[],[180],{"type":47,"value":181},"plugin-eval analyze \u003Cpath> --format markdown",{"type":47,"value":183},", then initialize a benchmark and show the setup questions needed to tailor ",{"type":42,"tag":86,"props":185,"children":187},{"className":186},[],[188],{"type":47,"value":189},"benchmark.json",{"type":42,"tag":67,"props":191,"children":192},{},[193,195],{"type":47,"value":194},"\"Evaluate this skill.\" -> ",{"type":42,"tag":86,"props":196,"children":198},{"className":197},[],[199],{"type":47,"value":181},{"type":42,"tag":67,"props":201,"children":202},{},[203,205],{"type":47,"value":204},"\"Why did this score that way?\" -> ",{"type":42,"tag":86,"props":206,"children":208},{"className":207},[],[209],{"type":47,"value":181},{"type":42,"tag":67,"props":211,"children":212},{},[213,215],{"type":47,"value":214},"\"What should I fix first?\" -> ",{"type":42,"tag":86,"props":216,"children":218},{"className":217},[],[219],{"type":47,"value":181},{"type":42,"tag":67,"props":221,"children":222},{},[223,225],{"type":47,"value":224},"\"Explain the token budget for this skill.\" -> ",{"type":42,"tag":86,"props":226,"children":228},{"className":227},[],[229],{"type":47,"value":230},"plugin-eval explain-budget \u003Cpath> --format markdown",{"type":42,"tag":67,"props":232,"children":233},{},[234,236],{"type":47,"value":235},"\"Measure the real token usage of this skill.\" -> benchmark flow, then ",{"type":42,"tag":86,"props":237,"children":239},{"className":238},[],[240],{"type":47,"value":241},"plugin-eval measurement-plan",{"type":42,"tag":67,"props":243,"children":244},{},[245],{"type":47,"value":246},"\"Help me benchmark this plugin.\" -> starter benchmark flow",{"type":42,"tag":67,"props":248,"children":249},{},[250,252],{"type":47,"value":251},"\"What should I run next?\" -> ",{"type":42,"tag":86,"props":253,"children":255},{"className":254},[],[256],{"type":47,"value":257},"plugin-eval start \u003Cpath> --request \"What should I run next?\" --format markdown",{"type":42,"tag":67,"props":259,"children":260},{},[261,263,269],{"type":47,"value":262},"If the user wants rewrite help after evaluation, route to ",{"type":42,"tag":86,"props":264,"children":266},{"className":265},[],[267],{"type":47,"value":268},"..\u002Fimprove-skill\u002FSKILL.md",{"type":47,"value":270},".",{"type":42,"tag":67,"props":272,"children":273},{},[274,276,282],{"type":47,"value":275},"If the user wants a custom rubric, route to ",{"type":42,"tag":86,"props":277,"children":279},{"className":278},[],[280],{"type":47,"value":281},"..\u002Fmetric-pack-designer\u002FSKILL.md",{"type":47,"value":270},{"type":42,"tag":67,"props":284,"children":285},{},[286,288],{"type":47,"value":287},"If the user names a skill instead of giving a path, resolve it locally before running commands:\n",{"type":42,"tag":168,"props":289,"children":290},{},[291,304,317],{"type":42,"tag":67,"props":292,"children":293},{},[294,296,302],{"type":47,"value":295},"check ",{"type":42,"tag":86,"props":297,"children":299},{"className":298},[],[300],{"type":47,"value":301},"~\u002F.codex\u002Fskills\u002F\u003Cskill-name>",{"type":47,"value":303}," first",{"type":42,"tag":67,"props":305,"children":306},{},[307,309,315],{"type":47,"value":308},"then check any repo-local ",{"type":42,"tag":86,"props":310,"children":312},{"className":311},[],[313],{"type":47,"value":314},"skills\u002F\u003Cskill-name>",{"type":47,"value":316}," directory",{"type":42,"tag":67,"props":318,"children":319},{},[320],{"type":47,"value":321},"if the name is still ambiguous, ask one short clarifying question before continuing",{"type":42,"tag":67,"props":323,"children":324},{},[325,327],{"type":47,"value":326},"When the request sounds like \"analysis\" rather than just \"evaluate\", do the fuller path:\n",{"type":42,"tag":168,"props":328,"children":329},{},[330,335,346,351],{"type":42,"tag":67,"props":331,"children":332},{},[333],{"type":47,"value":334},"run the report",{"type":42,"tag":67,"props":336,"children":337},{},[338,340],{"type":47,"value":339},"initialize ",{"type":42,"tag":86,"props":341,"children":343},{"className":342},[],[344],{"type":47,"value":345},".plugin-eval\u002Fbenchmark.json",{"type":42,"tag":67,"props":347,"children":348},{},[349],{"type":47,"value":350},"surface the setup questions that will refine the starter scenarios",{"type":42,"tag":67,"props":352,"children":353},{},[354],{"type":47,"value":355},"preview the dry-run command the user can execute next",{"type":42,"tag":56,"props":357,"children":359},{"id":358},"chat-requests-to-recognize",[360],{"type":47,"value":361},"Chat Requests To Recognize",{"type":42,"tag":168,"props":363,"children":364},{},[365,374,383,392,401,410,419,428,437],{"type":42,"tag":67,"props":366,"children":367},{},[368],{"type":42,"tag":86,"props":369,"children":371},{"className":370},[],[372],{"type":47,"value":373},"Give me an analysis of the game dev skill.",{"type":42,"tag":67,"props":375,"children":376},{},[377],{"type":42,"tag":86,"props":378,"children":380},{"className":379},[],[381],{"type":47,"value":382},"Evaluate this skill.",{"type":42,"tag":67,"props":384,"children":385},{},[386],{"type":42,"tag":86,"props":387,"children":389},{"className":388},[],[390],{"type":47,"value":391},"Evaluate this plugin.",{"type":42,"tag":67,"props":393,"children":394},{},[395],{"type":42,"tag":86,"props":396,"children":398},{"className":397},[],[399],{"type":47,"value":400},"Why did this score that way?",{"type":42,"tag":67,"props":402,"children":403},{},[404],{"type":42,"tag":86,"props":405,"children":407},{"className":406},[],[408],{"type":47,"value":409},"What should I fix first?",{"type":42,"tag":67,"props":411,"children":412},{},[413],{"type":42,"tag":86,"props":414,"children":416},{"className":415},[],[417],{"type":47,"value":418},"Explain the token budget for this skill.",{"type":42,"tag":67,"props":420,"children":421},{},[422],{"type":42,"tag":86,"props":423,"children":425},{"className":424},[],[426],{"type":47,"value":427},"Measure the real token usage of this skill.",{"type":42,"tag":67,"props":429,"children":430},{},[431],{"type":42,"tag":86,"props":432,"children":434},{"className":433},[],[435],{"type":47,"value":436},"Help me benchmark this plugin.",{"type":42,"tag":67,"props":438,"children":439},{},[440],{"type":42,"tag":86,"props":441,"children":443},{"className":442},[],[444],{"type":47,"value":445},"What should I run next?",{"type":42,"tag":56,"props":447,"children":449},{"id":448},"matching-commands",[450],{"type":47,"value":451},"Matching Commands",{"type":42,"tag":78,"props":453,"children":455},{"className":80,"code":454,"language":82,"meta":83,"style":83},"plugin-eval start \u003Cpath> --request \"Evaluate this skill.\" --format markdown\nplugin-eval start \u003Cpath> --request \"Give me a full analysis of this skill, including benchmark setup.\" --format markdown\nplugin-eval analyze \u003Cpath> --format markdown\nplugin-eval explain-budget \u003Cpath> --format markdown\nplugin-eval measurement-plan \u003Cpath> --format markdown\nplugin-eval init-benchmark \u003Cpath>\nplugin-eval benchmark \u003Cpath> --dry-run\nplugin-eval benchmark \u003Cpath>\n",[456],{"type":42,"tag":86,"props":457,"children":458},{"__ignoreMap":83},[459,510,563,599,636,673,703,737],{"type":42,"tag":90,"props":460,"children":461},{"class":92,"line":93},[462,466,470,474,478,482,486,490,494,498,502,506],{"type":42,"tag":90,"props":463,"children":464},{"style":97},[465],{"type":47,"value":4},{"type":42,"tag":90,"props":467,"children":468},{"style":102},[469],{"type":47,"value":105},{"type":42,"tag":90,"props":471,"children":472},{"style":108},[473],{"type":47,"value":111},{"type":42,"tag":90,"props":475,"children":476},{"style":102},[477],{"type":47,"value":116},{"type":42,"tag":90,"props":479,"children":480},{"style":119},[481],{"type":47,"value":122},{"type":42,"tag":90,"props":483,"children":484},{"style":108},[485],{"type":47,"value":127},{"type":42,"tag":90,"props":487,"children":488},{"style":102},[489],{"type":47,"value":132},{"type":42,"tag":90,"props":491,"children":492},{"style":108},[493],{"type":47,"value":137},{"type":42,"tag":90,"props":495,"children":496},{"style":102},[497],{"type":47,"value":382},{"type":42,"tag":90,"props":499,"children":500},{"style":108},[501],{"type":47,"value":147},{"type":42,"tag":90,"props":503,"children":504},{"style":102},[505],{"type":47,"value":152},{"type":42,"tag":90,"props":507,"children":508},{"style":102},[509],{"type":47,"value":157},{"type":42,"tag":90,"props":511,"children":513},{"class":92,"line":512},2,[514,518,522,526,530,534,538,542,546,551,555,559],{"type":42,"tag":90,"props":515,"children":516},{"style":97},[517],{"type":47,"value":4},{"type":42,"tag":90,"props":519,"children":520},{"style":102},[521],{"type":47,"value":105},{"type":42,"tag":90,"props":523,"children":524},{"style":108},[525],{"type":47,"value":111},{"type":42,"tag":90,"props":527,"children":528},{"style":102},[529],{"type":47,"value":116},{"type":42,"tag":90,"props":531,"children":532},{"style":119},[533],{"type":47,"value":122},{"type":42,"tag":90,"props":535,"children":536},{"style":108},[537],{"type":47,"value":127},{"type":42,"tag":90,"props":539,"children":540},{"style":102},[541],{"type":47,"value":132},{"type":42,"tag":90,"props":543,"children":544},{"style":108},[545],{"type":47,"value":137},{"type":42,"tag":90,"props":547,"children":548},{"style":102},[549],{"type":47,"value":550},"Give me a full analysis of this skill, including benchmark setup.",{"type":42,"tag":90,"props":552,"children":553},{"style":108},[554],{"type":47,"value":147},{"type":42,"tag":90,"props":556,"children":557},{"style":102},[558],{"type":47,"value":152},{"type":42,"tag":90,"props":560,"children":561},{"style":102},[562],{"type":47,"value":157},{"type":42,"tag":90,"props":564,"children":565},{"class":92,"line":160},[566,570,575,579,583,587,591,595],{"type":42,"tag":90,"props":567,"children":568},{"style":97},[569],{"type":47,"value":4},{"type":42,"tag":90,"props":571,"children":572},{"style":102},[573],{"type":47,"value":574}," analyze",{"type":42,"tag":90,"props":576,"children":577},{"style":108},[578],{"type":47,"value":111},{"type":42,"tag":90,"props":580,"children":581},{"style":102},[582],{"type":47,"value":116},{"type":42,"tag":90,"props":584,"children":585},{"style":119},[586],{"type":47,"value":122},{"type":42,"tag":90,"props":588,"children":589},{"style":108},[590],{"type":47,"value":127},{"type":42,"tag":90,"props":592,"children":593},{"style":102},[594],{"type":47,"value":152},{"type":42,"tag":90,"props":596,"children":597},{"style":102},[598],{"type":47,"value":157},{"type":42,"tag":90,"props":600,"children":602},{"class":92,"line":601},4,[603,607,612,616,620,624,628,632],{"type":42,"tag":90,"props":604,"children":605},{"style":97},[606],{"type":47,"value":4},{"type":42,"tag":90,"props":608,"children":609},{"style":102},[610],{"type":47,"value":611}," explain-budget",{"type":42,"tag":90,"props":613,"children":614},{"style":108},[615],{"type":47,"value":111},{"type":42,"tag":90,"props":617,"children":618},{"style":102},[619],{"type":47,"value":116},{"type":42,"tag":90,"props":621,"children":622},{"style":119},[623],{"type":47,"value":122},{"type":42,"tag":90,"props":625,"children":626},{"style":108},[627],{"type":47,"value":127},{"type":42,"tag":90,"props":629,"children":630},{"style":102},[631],{"type":47,"value":152},{"type":42,"tag":90,"props":633,"children":634},{"style":102},[635],{"type":47,"value":157},{"type":42,"tag":90,"props":637,"children":639},{"class":92,"line":638},5,[640,644,649,653,657,661,665,669],{"type":42,"tag":90,"props":641,"children":642},{"style":97},[643],{"type":47,"value":4},{"type":42,"tag":90,"props":645,"children":646},{"style":102},[647],{"type":47,"value":648}," measurement-plan",{"type":42,"tag":90,"props":650,"children":651},{"style":108},[652],{"type":47,"value":111},{"type":42,"tag":90,"props":654,"children":655},{"style":102},[656],{"type":47,"value":116},{"type":42,"tag":90,"props":658,"children":659},{"style":119},[660],{"type":47,"value":122},{"type":42,"tag":90,"props":662,"children":663},{"style":108},[664],{"type":47,"value":127},{"type":42,"tag":90,"props":666,"children":667},{"style":102},[668],{"type":47,"value":152},{"type":42,"tag":90,"props":670,"children":671},{"style":102},[672],{"type":47,"value":157},{"type":42,"tag":90,"props":674,"children":676},{"class":92,"line":675},6,[677,681,686,690,694,698],{"type":42,"tag":90,"props":678,"children":679},{"style":97},[680],{"type":47,"value":4},{"type":42,"tag":90,"props":682,"children":683},{"style":102},[684],{"type":47,"value":685}," init-benchmark",{"type":42,"tag":90,"props":687,"children":688},{"style":108},[689],{"type":47,"value":111},{"type":42,"tag":90,"props":691,"children":692},{"style":102},[693],{"type":47,"value":116},{"type":42,"tag":90,"props":695,"children":696},{"style":119},[697],{"type":47,"value":122},{"type":42,"tag":90,"props":699,"children":700},{"style":108},[701],{"type":47,"value":702},">\n",{"type":42,"tag":90,"props":704,"children":706},{"class":92,"line":705},7,[707,711,716,720,724,728,732],{"type":42,"tag":90,"props":708,"children":709},{"style":97},[710],{"type":47,"value":4},{"type":42,"tag":90,"props":712,"children":713},{"style":102},[714],{"type":47,"value":715}," benchmark",{"type":42,"tag":90,"props":717,"children":718},{"style":108},[719],{"type":47,"value":111},{"type":42,"tag":90,"props":721,"children":722},{"style":102},[723],{"type":47,"value":116},{"type":42,"tag":90,"props":725,"children":726},{"style":119},[727],{"type":47,"value":122},{"type":42,"tag":90,"props":729,"children":730},{"style":108},[731],{"type":47,"value":127},{"type":42,"tag":90,"props":733,"children":734},{"style":102},[735],{"type":47,"value":736}," --dry-run\n",{"type":42,"tag":90,"props":738,"children":740},{"class":92,"line":739},8,[741,745,749,753,757,761],{"type":42,"tag":90,"props":742,"children":743},{"style":97},[744],{"type":47,"value":4},{"type":42,"tag":90,"props":746,"children":747},{"style":102},[748],{"type":47,"value":715},{"type":42,"tag":90,"props":750,"children":751},{"style":108},[752],{"type":47,"value":111},{"type":42,"tag":90,"props":754,"children":755},{"style":102},[756],{"type":47,"value":116},{"type":42,"tag":90,"props":758,"children":759},{"style":119},[760],{"type":47,"value":122},{"type":42,"tag":90,"props":762,"children":763},{"style":108},[764],{"type":47,"value":702},{"type":42,"tag":56,"props":766,"children":768},{"id":767},"output-expectations",[769],{"type":47,"value":770},"Output Expectations",{"type":42,"tag":168,"props":772,"children":773},{},[774,779,814,827,832,845,850,862],{"type":42,"tag":67,"props":775,"children":776},{},[777],{"type":47,"value":778},"Prefer the JSON result as the source of truth.",{"type":42,"tag":67,"props":780,"children":781},{},[782,784,790,792,798,799,805,807,813],{"type":47,"value":783},"Lead with ",{"type":42,"tag":86,"props":785,"children":787},{"className":786},[],[788],{"type":47,"value":789},"At a Glance",{"type":47,"value":791},", ",{"type":42,"tag":86,"props":793,"children":795},{"className":794},[],[796],{"type":47,"value":797},"Why It Matters",{"type":47,"value":791},{"type":42,"tag":86,"props":800,"children":802},{"className":801},[],[803],{"type":47,"value":804},"Fix First",{"type":47,"value":806},", and ",{"type":42,"tag":86,"props":808,"children":810},{"className":809},[],[811],{"type":47,"value":812},"Recommended Next Step",{"type":47,"value":270},{"type":42,"tag":67,"props":815,"children":816},{},[817,819,825],{"type":47,"value":818},"Keep the ",{"type":42,"tag":86,"props":820,"children":822},{"className":821},[],[823],{"type":47,"value":824},"why",{"type":47,"value":826}," content terse and easy to skim.",{"type":42,"tag":67,"props":828,"children":829},{},[830],{"type":47,"value":831},"Call out whether budget numbers are static estimates or measured harness results.",{"type":42,"tag":67,"props":833,"children":834},{},[835,837,843],{"type":47,"value":836},"Show the user the exact chat phrase they can reuse next, the ",{"type":42,"tag":86,"props":838,"children":840},{"className":839},[],[841],{"type":47,"value":842},"plugin-eval start",{"type":47,"value":844}," command that routes it, and the first local workflow command behind it.",{"type":42,"tag":67,"props":846,"children":847},{},[848],{"type":47,"value":849},"When the user asks for an analysis of a named skill, do not stop at the report if benchmark setup is still missing.",{"type":42,"tag":67,"props":851,"children":852},{},[853,855,861],{"type":47,"value":854},"When the user is asking about a skill specifically, hand off to ",{"type":42,"tag":86,"props":856,"children":858},{"className":857},[],[859],{"type":47,"value":860},"..\u002Fevaluate-skill\u002FSKILL.md",{"type":47,"value":270},{"type":42,"tag":67,"props":863,"children":864},{},[865,867,873],{"type":47,"value":866},"When the user is asking about a plugin bundle, hand off to ",{"type":42,"tag":86,"props":868,"children":870},{"className":869},[],[871],{"type":47,"value":872},"..\u002Fevaluate-plugin\u002FSKILL.md",{"type":47,"value":270},{"type":42,"tag":56,"props":875,"children":877},{"id":876},"references",[878],{"type":47,"value":879},"References",{"type":42,"tag":168,"props":881,"children":882},{},[883,892,901],{"type":42,"tag":67,"props":884,"children":885},{},[886],{"type":42,"tag":86,"props":887,"children":889},{"className":888},[],[890],{"type":47,"value":891},"..\u002F..\u002Freferences\u002Fchat-first-workflows.md",{"type":42,"tag":67,"props":893,"children":894},{},[895],{"type":42,"tag":86,"props":896,"children":898},{"className":897},[],[899],{"type":47,"value":900},"..\u002F..\u002Freferences\u002Ftechnical-design.md",{"type":42,"tag":67,"props":902,"children":903},{},[904],{"type":42,"tag":86,"props":905,"children":907},{"className":906},[],[908],{"type":47,"value":909},"..\u002F..\u002Freferences\u002Fevaluation-result-schema.md",{"type":42,"tag":911,"props":912,"children":913},"style",{},[914],{"type":47,"value":915},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":917,"total":1035},[918,937,951,963,983,1005,1023],{"slug":919,"name":919,"fn":920,"description":921,"org":922,"tags":923,"stars":25,"repoUrl":26,"updatedAt":936},"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},[924,927,930,933],{"name":925,"slug":926,"type":15},"Accessibility","accessibility",{"name":928,"slug":929,"type":15},"Charts","charts",{"name":931,"slug":932,"type":15},"Data Visualization","data-visualization",{"name":934,"slug":935,"type":15},"Design","design","2026-06-30T19:00:57.102",{"slug":938,"name":938,"fn":939,"description":940,"org":941,"tags":942,"stars":25,"repoUrl":26,"updatedAt":950},"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},[943,944,947],{"name":20,"slug":21,"type":15},{"name":945,"slug":946,"type":15},"Browser Automation","browser-automation",{"name":948,"slug":949,"type":15},"Testing","testing","2026-04-06T18:41:03.44016",{"slug":952,"name":952,"fn":953,"description":954,"org":955,"tags":956,"stars":25,"repoUrl":26,"updatedAt":962},"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},[957,958,961],{"name":945,"slug":946,"type":15},{"name":959,"slug":960,"type":15},"Local Development","local-development",{"name":948,"slug":949,"type":15},"2026-04-06T18:41:17.526867",{"slug":964,"name":964,"fn":965,"description":966,"org":967,"tags":968,"stars":25,"repoUrl":26,"updatedAt":982},"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},[969,970,973,976,979],{"name":20,"slug":21,"type":15},{"name":971,"slug":972,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":974,"slug":975,"type":15},"SDK","sdk",{"name":977,"slug":978,"type":15},"Serverless","serverless",{"name":980,"slug":981,"type":15},"WebSockets","websockets","2026-04-06T18:39:51.717063",{"slug":984,"name":984,"fn":985,"description":986,"org":987,"tags":988,"stars":25,"repoUrl":26,"updatedAt":1004},"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},[989,992,995,998,1001],{"name":990,"slug":991,"type":15},"Frontend","frontend",{"name":993,"slug":994,"type":15},"React","react",{"name":996,"slug":997,"type":15},"shadcn\u002Fui","shadcn-ui",{"name":999,"slug":1000,"type":15},"UI Components","ui-components",{"name":1002,"slug":1003,"type":15},"Vercel","vercel","2026-04-06T18:40:59.619419",{"slug":1006,"name":1006,"fn":1007,"description":1008,"org":1009,"tags":1010,"stars":25,"repoUrl":26,"updatedAt":1022},"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},[1011,1014,1017,1020,1021],{"name":1012,"slug":1013,"type":15},"AI Infrastructure","ai-infrastructure",{"name":1015,"slug":1016,"type":15},"Cost Optimization","cost-optimization",{"name":1018,"slug":1019,"type":15},"LLM","llm",{"name":13,"slug":14,"type":15},{"name":1002,"slug":1003,"type":15},"2026-04-06T18:40:44.377464",{"slug":1024,"name":1024,"fn":1025,"description":1026,"org":1027,"tags":1028,"stars":25,"repoUrl":26,"updatedAt":1034},"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},[1029,1030,1033],{"name":1015,"slug":1016,"type":15},{"name":1031,"slug":1032,"type":15},"Database","database",{"name":1018,"slug":1019,"type":15},"2026-04-06T18:41:08.513425",600,{"items":1037,"total":1234},[1038,1059,1082,1099,1115,1132,1151,1163,1177,1191,1203,1218],{"slug":1039,"name":1039,"fn":1040,"description":1041,"org":1042,"tags":1043,"stars":1056,"repoUrl":1057,"updatedAt":1058},"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},[1044,1047,1050,1053],{"name":1045,"slug":1046,"type":15},"Documents","documents",{"name":1048,"slug":1049,"type":15},"Healthcare","healthcare",{"name":1051,"slug":1052,"type":15},"Insurance","insurance",{"name":1054,"slug":1055,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":1060,"name":1060,"fn":1061,"description":1062,"org":1063,"tags":1064,"stars":1079,"repoUrl":1080,"updatedAt":1081},"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},[1065,1068,1070,1073,1076],{"name":1066,"slug":1067,"type":15},".NET","dotnet",{"name":1069,"slug":1060,"type":15},"ASP.NET Core",{"name":1071,"slug":1072,"type":15},"Blazor","blazor",{"name":1074,"slug":1075,"type":15},"C#","csharp",{"name":1077,"slug":1078,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":1083,"name":1083,"fn":1084,"description":1085,"org":1086,"tags":1087,"stars":1079,"repoUrl":1080,"updatedAt":1098},"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},[1088,1091,1094,1097],{"name":1089,"slug":1090,"type":15},"Apps SDK","apps-sdk",{"name":1092,"slug":1093,"type":15},"ChatGPT","chatgpt",{"name":1095,"slug":1096,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":1100,"name":1100,"fn":1101,"description":1102,"org":1103,"tags":1104,"stars":1079,"repoUrl":1080,"updatedAt":1114},"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},[1105,1108,1111],{"name":1106,"slug":1107,"type":15},"API Development","api-development",{"name":1109,"slug":1110,"type":15},"CLI","cli",{"name":1112,"slug":1113,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":1116,"name":1116,"fn":1117,"description":1118,"org":1119,"tags":1120,"stars":1079,"repoUrl":1080,"updatedAt":1131},"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},[1121,1124,1127,1128],{"name":1122,"slug":1123,"type":15},"Cloudflare","cloudflare",{"name":1125,"slug":1126,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":971,"slug":972,"type":15},{"name":1129,"slug":1130,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":1133,"name":1133,"fn":1134,"description":1135,"org":1136,"tags":1137,"stars":1079,"repoUrl":1080,"updatedAt":1150},"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},[1138,1141,1144,1147],{"name":1139,"slug":1140,"type":15},"Productivity","productivity",{"name":1142,"slug":1143,"type":15},"Project Management","project-management",{"name":1145,"slug":1146,"type":15},"Strategy","strategy",{"name":1148,"slug":1149,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":1152,"name":1152,"fn":1153,"description":1154,"org":1155,"tags":1156,"stars":1079,"repoUrl":1080,"updatedAt":1162},"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},[1157,1158,1160,1161],{"name":934,"slug":935,"type":15},{"name":1159,"slug":1152,"type":15},"Figma",{"name":990,"slug":991,"type":15},{"name":1095,"slug":1096,"type":15},"2026-04-12T05:06:47.939943",{"slug":1164,"name":1164,"fn":1165,"description":1166,"org":1167,"tags":1168,"stars":1079,"repoUrl":1080,"updatedAt":1176},"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},[1169,1170,1173,1174,1175],{"name":934,"slug":935,"type":15},{"name":1171,"slug":1172,"type":15},"Design System","design-system",{"name":1159,"slug":1152,"type":15},{"name":990,"slug":991,"type":15},{"name":999,"slug":1000,"type":15},"2026-05-10T05:59:52.971881",{"slug":1178,"name":1178,"fn":1179,"description":1180,"org":1181,"tags":1182,"stars":1079,"repoUrl":1080,"updatedAt":1190},"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},[1183,1184,1185,1188,1189],{"name":934,"slug":935,"type":15},{"name":1171,"slug":1172,"type":15},{"name":1186,"slug":1187,"type":15},"Documentation","documentation",{"name":1159,"slug":1152,"type":15},{"name":990,"slug":991,"type":15},"2026-05-16T06:07:47.821474",{"slug":1192,"name":1192,"fn":1193,"description":1194,"org":1195,"tags":1196,"stars":1079,"repoUrl":1080,"updatedAt":1202},"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},[1197,1198,1199,1200,1201],{"name":934,"slug":935,"type":15},{"name":1159,"slug":1152,"type":15},{"name":990,"slug":991,"type":15},{"name":999,"slug":1000,"type":15},{"name":1077,"slug":1078,"type":15},"2026-05-16T06:07:40.583615",{"slug":1204,"name":1204,"fn":1205,"description":1206,"org":1207,"tags":1208,"stars":1079,"repoUrl":1080,"updatedAt":1217},"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},[1209,1212,1213,1216],{"name":1210,"slug":1211,"type":15},"Animation","animation",{"name":1112,"slug":1113,"type":15},{"name":1214,"slug":1215,"type":15},"Creative","creative",{"name":934,"slug":935,"type":15},"2026-05-02T05:31:48.48485",{"slug":1219,"name":1219,"fn":1220,"description":1221,"org":1222,"tags":1223,"stars":1079,"repoUrl":1080,"updatedAt":1233},"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},[1224,1225,1226,1229,1232],{"name":1214,"slug":1215,"type":15},{"name":934,"slug":935,"type":15},{"name":1227,"slug":1228,"type":15},"Image Generation","image-generation",{"name":1230,"slug":1231,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675]