[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-verification":3,"mdc--8unn6g-key":33,"related-org-openai-verification":826,"related-repo-openai-verification":1033},{"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},"verification","verify complete application flows end-to-end","Full-story verification — infers what the user is building, then verifies the complete flow end-to-end: browser → API → data → response. Triggers on dev server start and 'why isn't this working' signals.",{"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},"Observability","observability","tag",{"name":17,"slug":18,"type":15},"E2E Testing","e2e-testing",{"name":20,"slug":21,"type":15},"QA","qa",3992,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-04-06T18:41:11.065395",null,465,[],{"repoUrl":23,"stars":22,"forks":26,"topics":29,"description":30},[],"OpenAI Plugins","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fvercel\u002Fskills\u002Fverification","---\nname: verification\ndescription: \"Full-story verification — infers what the user is building, then verifies the complete flow end-to-end: browser → API → data → response. Triggers on dev server start and 'why isn't this working' signals.\"\nmetadata:\n  priority: 7\n  docs:\n    - \"https:\u002F\u002Fvercel.com\u002Fdocs\u002Fprojects\u002Fproject-configuration\"\n  sitemap: \"https:\u002F\u002Fvercel.com\u002Fsitemap\u002Fdocs.xml\"\n  pathPatterns: []\n  bashPatterns:\n    - '\\bnext\\s+dev\\b'\n    - '\\bnpm\\s+run\\s+dev\\b'\n    - '\\bpnpm\\s+dev\\b'\n    - '\\bbun\\s+run\\s+dev\\b'\n    - '\\byarn\\s+dev\\b'\n    - '\\bvite\\s*(dev)?\\b'\n    - '\\bvercel\\s+dev\\b'\n    - '\\bastro\\s+dev\\b'\n  importPatterns: []\n  promptSignals:\n    phrases:\n      - \"verify the flow\"\n      - \"verify everything works\"\n      - \"test the whole thing\"\n      - \"does it actually work\"\n      - \"check end to end\"\n      - \"end to end test\"\n      - \"why isn't it working right\"\n      - \"why doesn't it work\"\n      - \"it's not working correctly\"\n      - \"something's off\"\n      - \"not quite right\"\n      - \"almost works but\"\n      - \"works locally but\"\n      - \"verify the feature\"\n      - \"make sure it works\"\n      - \"full verification\"\n    allOf:\n      - [verify, flow]\n      - [verify, works]\n      - [check, everything]\n      - [test, end, end]\n      - [not, working, right]\n      - [something, off]\n      - [almost, works]\n      - [make, sure, works]\n    anyOf:\n      - \"verify\"\n      - \"verification\"\n      - \"end-to-end\"\n      - \"full flow\"\n      - \"works\"\n      - \"working\"\n    noneOf:\n      - \"unit test\"\n      - \"jest\"\n      - \"vitest\"\n      - \"playwright test\"\n      - \"cypress test\"\n    minScore: 6\n---\n\n# Full-Story Verification\n\nYou are a verification orchestrator. Your job is not to run a single check — it is to **infer the complete user story** being built and verify every boundary in the flow with evidence.\n\nThis skill coordinates with `agent-browser-verify` (browser-side visual checks), `investigation-mode` (reactive debugging), and `observability` (logging\u002Fmonitoring) — but your focus is the **end-to-end story**, not any single layer.\n\n## When This Triggers\n\n- A dev server just started and the user wants to know if things work\n- The user says something \"isn't quite right\" or \"almost works\"\n- The user asks you to verify a feature or check the full flow\n\n## Step 1 — Infer the User Story\n\nBefore checking anything, determine **what is being built**:\n\n1. Read recently edited files (check git diff or recent Write\u002FEdit tool calls)\n2. Identify the feature boundary: which routes, components, API endpoints, and data sources are involved\n3. Scan `package.json` scripts, route structure (`app\u002F` or `pages\u002F`), and environment files (`.env*`)\n4. State the story in one sentence: _\"The user is building [X] which flows from [UI entry point] → [API route] → [data source] → [response rendering]\"_\n\n**Do not skip this step.** Every subsequent check must be anchored to the inferred story.\n\n## Step 2 — Establish Evidence Baseline\n\nGather the current state across all layers:\n\n| Layer | How to check | What to capture |\n|-------|-------------|-----------------|\n| **Browser** | Use `agent-browser` — open the relevant page, screenshot, check console | Visual state, console errors, network failures |\n| **Server terminal** | Read the terminal output from the dev server process | Startup errors, request logs, compilation warnings |\n| **Runtime logs** | Run `vercel logs` (if deployed) or check server stdout | API response codes, error traces, timing |\n| **Environment** | Check `.env.local`, `vercel env ls`, compare expected vs actual | Missing vars, wrong values, production vs development mismatch |\n\nReport what you find at each layer before proceeding. Use the investigation-mode reporting contract:\n\n> **Checking**: [what you're looking at]\n> **Evidence**: [what you found — quote actual output]\n> **Next**: [what this means for the next step]\n\n## Step 3 — Walk the Data Flow\n\nTrace the feature's data path from trigger to completion:\n\n1. **UI trigger** — What user action initiates the flow? (button click, page load, form submit)\n2. **Client → Server** — What request is made? Check the fetch\u002Faction call, verify the URL, method, and payload match the API route\n3. **API route handler** — Read the route file. Does it handle the method? Does it validate input? Does it call the right service\u002Fdatabase?\n4. **External dependencies** — If the route calls a database, third-party API, or Vercel service (KV, Blob, Postgres, AI SDK): verify the client is initialized, credentials are present, and the call shape matches the SDK docs\n5. **Response → UI** — Does the response format match what the client expects? Is error handling present on both sides?\n\nAt each boundary, check for these common breaks:\n- **Missing `await`** on async operations\n- **Wrong HTTP method** (GET handler but POST fetch)\n- **Env var absent** in runtime but present in `.env.local`\n- **Import mismatch** (server module imported in client component or vice versa)\n- **Type mismatch** between API response and client expectation\n- **Missing error boundary** — unhandled rejection crashes the page silently\n\n## Step 4 — Report With Evidence\n\nSummarize findings in a structured report:\n\n```\n## Verification Report: [Feature Name]\n\n**Story**: [one-sentence description of the user story]\n\n### Flow Status\n| Boundary | Status | Evidence |\n|----------|--------|----------|\n| UI renders | ✅\u002F❌ | [screenshot or console output] |\n| Client → API | ✅\u002F❌ | [request\u002Fresponse or error] |\n| API → Data | ✅\u002F❌ | [log output or error trace] |\n| Data → Response | ✅\u002F❌ | [response shape or error] |\n| Response → UI | ✅\u002F❌ | [rendered output or error] |\n\n### Issues Found\n1. [Issue]: [evidence] → [fix]\n\n### Verified Working\n- [What was confirmed working with evidence]\n```\n\n## Stop Conditions\n\n**Stop verifying when**:\n- All boundaries in the flow are confirmed working with evidence — report success\n- You find the **first broken boundary** — report it with evidence and a specific fix, do not continue past the break\n- Two consecutive layers return no useful signal (e.g., no logs, no errors, no output) — flag the observability gap and recommend adding logging before continuing\n\n**Do not**:\n- Run the same check more than twice\n- Continue past a confirmed broken boundary\n- Verify unrelated features — stay on the inferred story\n- Spend time on cosmetic issues (styling, spacing) unless the user specifically asked\n\n## Suggest Verification After Implementation\n\nWhen you finish building or implementing a feature (wrote code, created routes, set up a project), briefly let the user know they can ask you to verify everything works — e.g. browser verification or end-to-end flow check. One sentence is enough. Don't force it if only a small fix or question was involved.\n\n## Coordination With Other Skills\n\n- **`agent-browser-verify`** — Handles browser screenshots and console checks. Defer to it for visual verification. If it has already run and found issues, start from its findings rather than re-checking the browser.\n- **`investigation-mode`** — Handles reactive debugging when things are stuck\u002Fhung. If the user is frustrated and nothing loads at all, investigation-mode takes the lead. Verification takes over when things _partially_ work.\n- **`observability`** — Handles logging\u002Fmonitoring setup. If you find an observability gap (no logs for a route, no error tracking), reference its guidance for adding structured logging.\n",{"data":34,"body":103},{"name":4,"description":6,"metadata":35},{"priority":36,"docs":37,"sitemap":39,"pathPatterns":40,"bashPatterns":41,"importPatterns":50,"promptSignals":51},7,[38],"https:\u002F\u002Fvercel.com\u002Fdocs\u002Fprojects\u002Fproject-configuration","https:\u002F\u002Fvercel.com\u002Fsitemap\u002Fdocs.xml",[],[42,43,44,45,46,47,48,49],"\\bnext\\s+dev\\b","\\bnpm\\s+run\\s+dev\\b","\\bpnpm\\s+dev\\b","\\bbun\\s+run\\s+dev\\b","\\byarn\\s+dev\\b","\\bvite\\s*(dev)?\\b","\\bvercel\\s+dev\\b","\\bastro\\s+dev\\b",[],{"phrases":52,"allOf":69,"anyOf":93,"noneOf":96,"minScore":102},[53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68],"verify the flow","verify everything works","test the whole thing","does it actually work","check end to end","end to end test","why isn't it working right","why doesn't it work","it's not working correctly","something's off","not quite right","almost works but","works locally but","verify the feature","make sure it works","full verification",[70,73,75,78,81,85,88,90],[71,72],"verify","flow",[71,74],"works",[76,77],"check","everything",[79,80,80],"test","end",[82,83,84],"not","working","right",[86,87],"something","off",[89,74],"almost",[91,92,74],"make","sure",[71,4,94,95,74,83],"end-to-end","full flow",[97,98,99,100,101],"unit test","jest","vitest","playwright test","cypress test",6,{"type":104,"children":105},"root",[106,115,129,165,172,192,198,210,306,316,322,327,476,481,522,528,533,586,591,665,671,676,688,694,703,728,737,760,766,771,777],{"type":107,"tag":108,"props":109,"children":111},"element","h1",{"id":110},"full-story-verification",[112],{"type":113,"value":114},"text","Full-Story Verification",{"type":107,"tag":116,"props":117,"children":118},"p",{},[119,121,127],{"type":113,"value":120},"You are a verification orchestrator. Your job is not to run a single check — it is to ",{"type":107,"tag":122,"props":123,"children":124},"strong",{},[125],{"type":113,"value":126},"infer the complete user story",{"type":113,"value":128}," being built and verify every boundary in the flow with evidence.",{"type":107,"tag":116,"props":130,"children":131},{},[132,134,141,143,149,151,156,158,163],{"type":113,"value":133},"This skill coordinates with ",{"type":107,"tag":135,"props":136,"children":138},"code",{"className":137},[],[139],{"type":113,"value":140},"agent-browser-verify",{"type":113,"value":142}," (browser-side visual checks), ",{"type":107,"tag":135,"props":144,"children":146},{"className":145},[],[147],{"type":113,"value":148},"investigation-mode",{"type":113,"value":150}," (reactive debugging), and ",{"type":107,"tag":135,"props":152,"children":154},{"className":153},[],[155],{"type":113,"value":14},{"type":113,"value":157}," (logging\u002Fmonitoring) — but your focus is the ",{"type":107,"tag":122,"props":159,"children":160},{},[161],{"type":113,"value":162},"end-to-end story",{"type":113,"value":164},", not any single layer.",{"type":107,"tag":166,"props":167,"children":169},"h2",{"id":168},"when-this-triggers",[170],{"type":113,"value":171},"When This Triggers",{"type":107,"tag":173,"props":174,"children":175},"ul",{},[176,182,187],{"type":107,"tag":177,"props":178,"children":179},"li",{},[180],{"type":113,"value":181},"A dev server just started and the user wants to know if things work",{"type":107,"tag":177,"props":183,"children":184},{},[185],{"type":113,"value":186},"The user says something \"isn't quite right\" or \"almost works\"",{"type":107,"tag":177,"props":188,"children":189},{},[190],{"type":113,"value":191},"The user asks you to verify a feature or check the full flow",{"type":107,"tag":166,"props":193,"children":195},{"id":194},"step-1-infer-the-user-story",[196],{"type":113,"value":197},"Step 1 — Infer the User Story",{"type":107,"tag":116,"props":199,"children":200},{},[201,203,208],{"type":113,"value":202},"Before checking anything, determine ",{"type":107,"tag":122,"props":204,"children":205},{},[206],{"type":113,"value":207},"what is being built",{"type":113,"value":209},":",{"type":107,"tag":211,"props":212,"children":213},"ol",{},[214,219,224,261],{"type":107,"tag":177,"props":215,"children":216},{},[217],{"type":113,"value":218},"Read recently edited files (check git diff or recent Write\u002FEdit tool calls)",{"type":107,"tag":177,"props":220,"children":221},{},[222],{"type":113,"value":223},"Identify the feature boundary: which routes, components, API endpoints, and data sources are involved",{"type":107,"tag":177,"props":225,"children":226},{},[227,229,235,237,243,245,251,253,259],{"type":113,"value":228},"Scan ",{"type":107,"tag":135,"props":230,"children":232},{"className":231},[],[233],{"type":113,"value":234},"package.json",{"type":113,"value":236}," scripts, route structure (",{"type":107,"tag":135,"props":238,"children":240},{"className":239},[],[241],{"type":113,"value":242},"app\u002F",{"type":113,"value":244}," or ",{"type":107,"tag":135,"props":246,"children":248},{"className":247},[],[249],{"type":113,"value":250},"pages\u002F",{"type":113,"value":252},"), and environment files (",{"type":107,"tag":135,"props":254,"children":256},{"className":255},[],[257],{"type":113,"value":258},".env*",{"type":113,"value":260},")",{"type":107,"tag":177,"props":262,"children":263},{},[264,266],{"type":113,"value":265},"State the story in one sentence: ",{"type":107,"tag":267,"props":268,"children":269},"em",{},[270,272,278,280,285,287,292,293,298,299,304],{"type":113,"value":271},"\"The user is building ",{"type":107,"tag":273,"props":274,"children":275},"span",{},[276],{"type":113,"value":277},"X",{"type":113,"value":279}," which flows from ",{"type":107,"tag":273,"props":281,"children":282},{},[283],{"type":113,"value":284},"UI entry point",{"type":113,"value":286}," → ",{"type":107,"tag":273,"props":288,"children":289},{},[290],{"type":113,"value":291},"API route",{"type":113,"value":286},{"type":107,"tag":273,"props":294,"children":295},{},[296],{"type":113,"value":297},"data source",{"type":113,"value":286},{"type":107,"tag":273,"props":300,"children":301},{},[302],{"type":113,"value":303},"response rendering",{"type":113,"value":305},"\"",{"type":107,"tag":116,"props":307,"children":308},{},[309,314],{"type":107,"tag":122,"props":310,"children":311},{},[312],{"type":113,"value":313},"Do not skip this step.",{"type":113,"value":315}," Every subsequent check must be anchored to the inferred story.",{"type":107,"tag":166,"props":317,"children":319},{"id":318},"step-2-establish-evidence-baseline",[320],{"type":113,"value":321},"Step 2 — Establish Evidence Baseline",{"type":107,"tag":116,"props":323,"children":324},{},[325],{"type":113,"value":326},"Gather the current state across all layers:",{"type":107,"tag":328,"props":329,"children":330},"table",{},[331,355],{"type":107,"tag":332,"props":333,"children":334},"thead",{},[335],{"type":107,"tag":336,"props":337,"children":338},"tr",{},[339,345,350],{"type":107,"tag":340,"props":341,"children":342},"th",{},[343],{"type":113,"value":344},"Layer",{"type":107,"tag":340,"props":346,"children":347},{},[348],{"type":113,"value":349},"How to check",{"type":107,"tag":340,"props":351,"children":352},{},[353],{"type":113,"value":354},"What to capture",{"type":107,"tag":356,"props":357,"children":358},"tbody",{},[359,389,410,439],{"type":107,"tag":336,"props":360,"children":361},{},[362,371,384],{"type":107,"tag":363,"props":364,"children":365},"td",{},[366],{"type":107,"tag":122,"props":367,"children":368},{},[369],{"type":113,"value":370},"Browser",{"type":107,"tag":363,"props":372,"children":373},{},[374,376,382],{"type":113,"value":375},"Use ",{"type":107,"tag":135,"props":377,"children":379},{"className":378},[],[380],{"type":113,"value":381},"agent-browser",{"type":113,"value":383}," — open the relevant page, screenshot, check console",{"type":107,"tag":363,"props":385,"children":386},{},[387],{"type":113,"value":388},"Visual state, console errors, network failures",{"type":107,"tag":336,"props":390,"children":391},{},[392,400,405],{"type":107,"tag":363,"props":393,"children":394},{},[395],{"type":107,"tag":122,"props":396,"children":397},{},[398],{"type":113,"value":399},"Server terminal",{"type":107,"tag":363,"props":401,"children":402},{},[403],{"type":113,"value":404},"Read the terminal output from the dev server process",{"type":107,"tag":363,"props":406,"children":407},{},[408],{"type":113,"value":409},"Startup errors, request logs, compilation warnings",{"type":107,"tag":336,"props":411,"children":412},{},[413,421,434],{"type":107,"tag":363,"props":414,"children":415},{},[416],{"type":107,"tag":122,"props":417,"children":418},{},[419],{"type":113,"value":420},"Runtime logs",{"type":107,"tag":363,"props":422,"children":423},{},[424,426,432],{"type":113,"value":425},"Run ",{"type":107,"tag":135,"props":427,"children":429},{"className":428},[],[430],{"type":113,"value":431},"vercel logs",{"type":113,"value":433}," (if deployed) or check server stdout",{"type":107,"tag":363,"props":435,"children":436},{},[437],{"type":113,"value":438},"API response codes, error traces, timing",{"type":107,"tag":336,"props":440,"children":441},{},[442,450,471],{"type":107,"tag":363,"props":443,"children":444},{},[445],{"type":107,"tag":122,"props":446,"children":447},{},[448],{"type":113,"value":449},"Environment",{"type":107,"tag":363,"props":451,"children":452},{},[453,455,461,463,469],{"type":113,"value":454},"Check ",{"type":107,"tag":135,"props":456,"children":458},{"className":457},[],[459],{"type":113,"value":460},".env.local",{"type":113,"value":462},", ",{"type":107,"tag":135,"props":464,"children":466},{"className":465},[],[467],{"type":113,"value":468},"vercel env ls",{"type":113,"value":470},", compare expected vs actual",{"type":107,"tag":363,"props":472,"children":473},{},[474],{"type":113,"value":475},"Missing vars, wrong values, production vs development mismatch",{"type":107,"tag":116,"props":477,"children":478},{},[479],{"type":113,"value":480},"Report what you find at each layer before proceeding. Use the investigation-mode reporting contract:",{"type":107,"tag":482,"props":483,"children":484},"blockquote",{},[485],{"type":107,"tag":116,"props":486,"children":487},{},[488,493,495,500,505,506,511,516,517],{"type":107,"tag":122,"props":489,"children":490},{},[491],{"type":113,"value":492},"Checking",{"type":113,"value":494},": ",{"type":107,"tag":273,"props":496,"children":497},{},[498],{"type":113,"value":499},"what you're looking at",{"type":107,"tag":122,"props":501,"children":502},{},[503],{"type":113,"value":504},"Evidence",{"type":113,"value":494},{"type":107,"tag":273,"props":507,"children":508},{},[509],{"type":113,"value":510},"what you found — quote actual output",{"type":107,"tag":122,"props":512,"children":513},{},[514],{"type":113,"value":515},"Next",{"type":113,"value":494},{"type":107,"tag":273,"props":518,"children":519},{},[520],{"type":113,"value":521},"what this means for the next step",{"type":107,"tag":166,"props":523,"children":525},{"id":524},"step-3-walk-the-data-flow",[526],{"type":113,"value":527},"Step 3 — Walk the Data Flow",{"type":107,"tag":116,"props":529,"children":530},{},[531],{"type":113,"value":532},"Trace the feature's data path from trigger to completion:",{"type":107,"tag":211,"props":534,"children":535},{},[536,546,556,566,576],{"type":107,"tag":177,"props":537,"children":538},{},[539,544],{"type":107,"tag":122,"props":540,"children":541},{},[542],{"type":113,"value":543},"UI trigger",{"type":113,"value":545}," — What user action initiates the flow? (button click, page load, form submit)",{"type":107,"tag":177,"props":547,"children":548},{},[549,554],{"type":107,"tag":122,"props":550,"children":551},{},[552],{"type":113,"value":553},"Client → Server",{"type":113,"value":555}," — What request is made? Check the fetch\u002Faction call, verify the URL, method, and payload match the API route",{"type":107,"tag":177,"props":557,"children":558},{},[559,564],{"type":107,"tag":122,"props":560,"children":561},{},[562],{"type":113,"value":563},"API route handler",{"type":113,"value":565}," — Read the route file. Does it handle the method? Does it validate input? Does it call the right service\u002Fdatabase?",{"type":107,"tag":177,"props":567,"children":568},{},[569,574],{"type":107,"tag":122,"props":570,"children":571},{},[572],{"type":113,"value":573},"External dependencies",{"type":113,"value":575}," — If the route calls a database, third-party API, or Vercel service (KV, Blob, Postgres, AI SDK): verify the client is initialized, credentials are present, and the call shape matches the SDK docs",{"type":107,"tag":177,"props":577,"children":578},{},[579,584],{"type":107,"tag":122,"props":580,"children":581},{},[582],{"type":113,"value":583},"Response → UI",{"type":113,"value":585}," — Does the response format match what the client expects? Is error handling present on both sides?",{"type":107,"tag":116,"props":587,"children":588},{},[589],{"type":113,"value":590},"At each boundary, check for these common breaks:",{"type":107,"tag":173,"props":592,"children":593},{},[594,610,620,635,645,655],{"type":107,"tag":177,"props":595,"children":596},{},[597,608],{"type":107,"tag":122,"props":598,"children":599},{},[600,602],{"type":113,"value":601},"Missing ",{"type":107,"tag":135,"props":603,"children":605},{"className":604},[],[606],{"type":113,"value":607},"await",{"type":113,"value":609}," on async operations",{"type":107,"tag":177,"props":611,"children":612},{},[613,618],{"type":107,"tag":122,"props":614,"children":615},{},[616],{"type":113,"value":617},"Wrong HTTP method",{"type":113,"value":619}," (GET handler but POST fetch)",{"type":107,"tag":177,"props":621,"children":622},{},[623,628,630],{"type":107,"tag":122,"props":624,"children":625},{},[626],{"type":113,"value":627},"Env var absent",{"type":113,"value":629}," in runtime but present in ",{"type":107,"tag":135,"props":631,"children":633},{"className":632},[],[634],{"type":113,"value":460},{"type":107,"tag":177,"props":636,"children":637},{},[638,643],{"type":107,"tag":122,"props":639,"children":640},{},[641],{"type":113,"value":642},"Import mismatch",{"type":113,"value":644}," (server module imported in client component or vice versa)",{"type":107,"tag":177,"props":646,"children":647},{},[648,653],{"type":107,"tag":122,"props":649,"children":650},{},[651],{"type":113,"value":652},"Type mismatch",{"type":113,"value":654}," between API response and client expectation",{"type":107,"tag":177,"props":656,"children":657},{},[658,663],{"type":107,"tag":122,"props":659,"children":660},{},[661],{"type":113,"value":662},"Missing error boundary",{"type":113,"value":664}," — unhandled rejection crashes the page silently",{"type":107,"tag":166,"props":666,"children":668},{"id":667},"step-4-report-with-evidence",[669],{"type":113,"value":670},"Step 4 — Report With Evidence",{"type":107,"tag":116,"props":672,"children":673},{},[674],{"type":113,"value":675},"Summarize findings in a structured report:",{"type":107,"tag":677,"props":678,"children":682},"pre",{"className":679,"code":681,"language":113},[680],"language-text","## Verification Report: [Feature Name]\n\n**Story**: [one-sentence description of the user story]\n\n### Flow Status\n| Boundary | Status | Evidence |\n|----------|--------|----------|\n| UI renders | ✅\u002F❌ | [screenshot or console output] |\n| Client → API | ✅\u002F❌ | [request\u002Fresponse or error] |\n| API → Data | ✅\u002F❌ | [log output or error trace] |\n| Data → Response | ✅\u002F❌ | [response shape or error] |\n| Response → UI | ✅\u002F❌ | [rendered output or error] |\n\n### Issues Found\n1. [Issue]: [evidence] → [fix]\n\n### Verified Working\n- [What was confirmed working with evidence]\n",[683],{"type":107,"tag":135,"props":684,"children":686},{"__ignoreMap":685},"",[687],{"type":113,"value":681},{"type":107,"tag":166,"props":689,"children":691},{"id":690},"stop-conditions",[692],{"type":113,"value":693},"Stop Conditions",{"type":107,"tag":116,"props":695,"children":696},{},[697,702],{"type":107,"tag":122,"props":698,"children":699},{},[700],{"type":113,"value":701},"Stop verifying when",{"type":113,"value":209},{"type":107,"tag":173,"props":704,"children":705},{},[706,711,723],{"type":107,"tag":177,"props":707,"children":708},{},[709],{"type":113,"value":710},"All boundaries in the flow are confirmed working with evidence — report success",{"type":107,"tag":177,"props":712,"children":713},{},[714,716,721],{"type":113,"value":715},"You find the ",{"type":107,"tag":122,"props":717,"children":718},{},[719],{"type":113,"value":720},"first broken boundary",{"type":113,"value":722}," — report it with evidence and a specific fix, do not continue past the break",{"type":107,"tag":177,"props":724,"children":725},{},[726],{"type":113,"value":727},"Two consecutive layers return no useful signal (e.g., no logs, no errors, no output) — flag the observability gap and recommend adding logging before continuing",{"type":107,"tag":116,"props":729,"children":730},{},[731,736],{"type":107,"tag":122,"props":732,"children":733},{},[734],{"type":113,"value":735},"Do not",{"type":113,"value":209},{"type":107,"tag":173,"props":738,"children":739},{},[740,745,750,755],{"type":107,"tag":177,"props":741,"children":742},{},[743],{"type":113,"value":744},"Run the same check more than twice",{"type":107,"tag":177,"props":746,"children":747},{},[748],{"type":113,"value":749},"Continue past a confirmed broken boundary",{"type":107,"tag":177,"props":751,"children":752},{},[753],{"type":113,"value":754},"Verify unrelated features — stay on the inferred story",{"type":107,"tag":177,"props":756,"children":757},{},[758],{"type":113,"value":759},"Spend time on cosmetic issues (styling, spacing) unless the user specifically asked",{"type":107,"tag":166,"props":761,"children":763},{"id":762},"suggest-verification-after-implementation",[764],{"type":113,"value":765},"Suggest Verification After Implementation",{"type":107,"tag":116,"props":767,"children":768},{},[769],{"type":113,"value":770},"When you finish building or implementing a feature (wrote code, created routes, set up a project), briefly let the user know they can ask you to verify everything works — e.g. browser verification or end-to-end flow check. One sentence is enough. Don't force it if only a small fix or question was involved.",{"type":107,"tag":166,"props":772,"children":774},{"id":773},"coordination-with-other-skills",[775],{"type":113,"value":776},"Coordination With Other Skills",{"type":107,"tag":173,"props":778,"children":779},{},[780,793,813],{"type":107,"tag":177,"props":781,"children":782},{},[783,791],{"type":107,"tag":122,"props":784,"children":785},{},[786],{"type":107,"tag":135,"props":787,"children":789},{"className":788},[],[790],{"type":113,"value":140},{"type":113,"value":792}," — Handles browser screenshots and console checks. Defer to it for visual verification. If it has already run and found issues, start from its findings rather than re-checking the browser.",{"type":107,"tag":177,"props":794,"children":795},{},[796,804,806,811],{"type":107,"tag":122,"props":797,"children":798},{},[799],{"type":107,"tag":135,"props":800,"children":802},{"className":801},[],[803],{"type":113,"value":148},{"type":113,"value":805}," — Handles reactive debugging when things are stuck\u002Fhung. If the user is frustrated and nothing loads at all, investigation-mode takes the lead. Verification takes over when things ",{"type":107,"tag":267,"props":807,"children":808},{},[809],{"type":113,"value":810},"partially",{"type":113,"value":812}," work.",{"type":107,"tag":177,"props":814,"children":815},{},[816,824],{"type":107,"tag":122,"props":817,"children":818},{},[819],{"type":107,"tag":135,"props":820,"children":822},{"className":821},[],[823],{"type":113,"value":14},{"type":113,"value":825}," — Handles logging\u002Fmonitoring setup. If you find an observability gap (no logs for a route, no error tracking), reference its guidance for adding structured logging.",{"items":827,"total":1032},[828,849,872,889,905,924,943,959,975,989,1001,1016],{"slug":829,"name":829,"fn":830,"description":831,"org":832,"tags":833,"stars":846,"repoUrl":847,"updatedAt":848},"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},[834,837,840,843],{"name":835,"slug":836,"type":15},"Documents","documents",{"name":838,"slug":839,"type":15},"Healthcare","healthcare",{"name":841,"slug":842,"type":15},"Insurance","insurance",{"name":844,"slug":845,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":850,"name":850,"fn":851,"description":852,"org":853,"tags":854,"stars":869,"repoUrl":870,"updatedAt":871},"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},[855,858,860,863,866],{"name":856,"slug":857,"type":15},".NET","dotnet",{"name":859,"slug":850,"type":15},"ASP.NET Core",{"name":861,"slug":862,"type":15},"Blazor","blazor",{"name":864,"slug":865,"type":15},"C#","csharp",{"name":867,"slug":868,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":873,"name":873,"fn":874,"description":875,"org":876,"tags":877,"stars":869,"repoUrl":870,"updatedAt":888},"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},[878,881,884,887],{"name":879,"slug":880,"type":15},"Apps SDK","apps-sdk",{"name":882,"slug":883,"type":15},"ChatGPT","chatgpt",{"name":885,"slug":886,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":890,"name":890,"fn":891,"description":892,"org":893,"tags":894,"stars":869,"repoUrl":870,"updatedAt":904},"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},[895,898,901],{"name":896,"slug":897,"type":15},"API Development","api-development",{"name":899,"slug":900,"type":15},"CLI","cli",{"name":902,"slug":903,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":906,"name":906,"fn":907,"description":908,"org":909,"tags":910,"stars":869,"repoUrl":870,"updatedAt":923},"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},[911,914,917,920],{"name":912,"slug":913,"type":15},"Cloudflare","cloudflare",{"name":915,"slug":916,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":918,"slug":919,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":921,"slug":922,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":925,"name":925,"fn":926,"description":927,"org":928,"tags":929,"stars":869,"repoUrl":870,"updatedAt":942},"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},[930,933,936,939],{"name":931,"slug":932,"type":15},"Productivity","productivity",{"name":934,"slug":935,"type":15},"Project Management","project-management",{"name":937,"slug":938,"type":15},"Strategy","strategy",{"name":940,"slug":941,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":944,"name":944,"fn":945,"description":946,"org":947,"tags":948,"stars":869,"repoUrl":870,"updatedAt":958},"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},[949,952,954,957],{"name":950,"slug":951,"type":15},"Design","design",{"name":953,"slug":944,"type":15},"Figma",{"name":955,"slug":956,"type":15},"Frontend","frontend",{"name":885,"slug":886,"type":15},"2026-04-12T05:06:47.939943",{"slug":960,"name":960,"fn":961,"description":962,"org":963,"tags":964,"stars":869,"repoUrl":870,"updatedAt":974},"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},[965,966,969,970,971],{"name":950,"slug":951,"type":15},{"name":967,"slug":968,"type":15},"Design System","design-system",{"name":953,"slug":944,"type":15},{"name":955,"slug":956,"type":15},{"name":972,"slug":973,"type":15},"UI Components","ui-components","2026-05-10T05:59:52.971881",{"slug":976,"name":976,"fn":977,"description":978,"org":979,"tags":980,"stars":869,"repoUrl":870,"updatedAt":988},"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},[981,982,983,986,987],{"name":950,"slug":951,"type":15},{"name":967,"slug":968,"type":15},{"name":984,"slug":985,"type":15},"Documentation","documentation",{"name":953,"slug":944,"type":15},{"name":955,"slug":956,"type":15},"2026-05-16T06:07:47.821474",{"slug":990,"name":990,"fn":991,"description":992,"org":993,"tags":994,"stars":869,"repoUrl":870,"updatedAt":1000},"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},[995,996,997,998,999],{"name":950,"slug":951,"type":15},{"name":953,"slug":944,"type":15},{"name":955,"slug":956,"type":15},{"name":972,"slug":973,"type":15},{"name":867,"slug":868,"type":15},"2026-05-16T06:07:40.583615",{"slug":1002,"name":1002,"fn":1003,"description":1004,"org":1005,"tags":1006,"stars":869,"repoUrl":870,"updatedAt":1015},"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},[1007,1010,1011,1014],{"name":1008,"slug":1009,"type":15},"Animation","animation",{"name":902,"slug":903,"type":15},{"name":1012,"slug":1013,"type":15},"Creative","creative",{"name":950,"slug":951,"type":15},"2026-05-02T05:31:48.48485",{"slug":1017,"name":1017,"fn":1018,"description":1019,"org":1020,"tags":1021,"stars":869,"repoUrl":870,"updatedAt":1031},"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},[1022,1023,1024,1027,1030],{"name":1012,"slug":1013,"type":15},{"name":950,"slug":951,"type":15},{"name":1025,"slug":1026,"type":15},"Image Generation","image-generation",{"name":1028,"slug":1029,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675,{"items":1034,"total":1146},[1035,1052,1067,1078,1096,1114,1134],{"slug":1036,"name":1036,"fn":1037,"description":1038,"org":1039,"tags":1040,"stars":22,"repoUrl":23,"updatedAt":1051},"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},[1041,1044,1047,1050],{"name":1042,"slug":1043,"type":15},"Accessibility","accessibility",{"name":1045,"slug":1046,"type":15},"Charts","charts",{"name":1048,"slug":1049,"type":15},"Data Visualization","data-visualization",{"name":950,"slug":951,"type":15},"2026-06-30T19:00:57.102",{"slug":381,"name":381,"fn":1053,"description":1054,"org":1055,"tags":1056,"stars":22,"repoUrl":23,"updatedAt":1066},"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},[1057,1060,1063],{"name":1058,"slug":1059,"type":15},"Agents","agents",{"name":1061,"slug":1062,"type":15},"Browser Automation","browser-automation",{"name":1064,"slug":1065,"type":15},"Testing","testing","2026-04-06T18:41:03.44016",{"slug":140,"name":140,"fn":1068,"description":1069,"org":1070,"tags":1071,"stars":22,"repoUrl":23,"updatedAt":1077},"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},[1072,1073,1076],{"name":1061,"slug":1062,"type":15},{"name":1074,"slug":1075,"type":15},"Local Development","local-development",{"name":1064,"slug":1065,"type":15},"2026-04-06T18:41:17.526867",{"slug":1079,"name":1079,"fn":1080,"description":1081,"org":1082,"tags":1083,"stars":22,"repoUrl":23,"updatedAt":1095},"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},[1084,1085,1086,1089,1092],{"name":1058,"slug":1059,"type":15},{"name":918,"slug":919,"type":15},{"name":1087,"slug":1088,"type":15},"SDK","sdk",{"name":1090,"slug":1091,"type":15},"Serverless","serverless",{"name":1093,"slug":1094,"type":15},"WebSockets","websockets","2026-04-06T18:39:51.717063",{"slug":1097,"name":1097,"fn":1098,"description":1099,"org":1100,"tags":1101,"stars":22,"repoUrl":23,"updatedAt":1113},"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},[1102,1103,1106,1109,1110],{"name":955,"slug":956,"type":15},{"name":1104,"slug":1105,"type":15},"React","react",{"name":1107,"slug":1108,"type":15},"shadcn\u002Fui","shadcn-ui",{"name":972,"slug":973,"type":15},{"name":1111,"slug":1112,"type":15},"Vercel","vercel","2026-04-06T18:40:59.619419",{"slug":1115,"name":1115,"fn":1116,"description":1117,"org":1118,"tags":1119,"stars":22,"repoUrl":23,"updatedAt":1133},"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},[1120,1123,1126,1129,1132],{"name":1121,"slug":1122,"type":15},"AI Infrastructure","ai-infrastructure",{"name":1124,"slug":1125,"type":15},"Cost Optimization","cost-optimization",{"name":1127,"slug":1128,"type":15},"LLM","llm",{"name":1130,"slug":1131,"type":15},"Performance","performance",{"name":1111,"slug":1112,"type":15},"2026-04-06T18:40:44.377464",{"slug":1135,"name":1135,"fn":1136,"description":1137,"org":1138,"tags":1139,"stars":22,"repoUrl":23,"updatedAt":1145},"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},[1140,1141,1144],{"name":1124,"slug":1125,"type":15},{"name":1142,"slug":1143,"type":15},"Database","database",{"name":1127,"slug":1128,"type":15},"2026-04-06T18:41:08.513425",600]