[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-audit":3,"mdc-nn9gbp-key":35,"related-org-openai-audit":724,"related-repo-openai-audit":929},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":24,"repoUrl":25,"updatedAt":26,"license":27,"forks":28,"topics":29,"repo":30,"sourceUrl":33,"mdContent":34},"audit","audit product flows and user journeys","Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"openai","OpenAI","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fopenai.png",[12,15,18,21],{"name":13,"slug":4,"type":14},"Audit","tag",{"name":16,"slug":17,"type":14},"Product Management","product-management",{"name":19,"slug":20,"type":14},"UX Design","ux-design",{"name":22,"slug":23,"type":14},"Design","design",427,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Frole-specific-plugins","2026-07-01T07:54:30.613428",null,65,[],{"repoUrl":25,"stars":24,"forks":28,"topics":31,"description":32},[],"Role-specific Codex plugin templates","https:\u002F\u002Fgithub.com\u002Fopenai\u002Frole-specific-plugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fproduct-design\u002Fskills\u002Faudit","---\nname: audit\ndescription: \"Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.\"\n---\n\n# Audit\n\nUse this skill when the user wants to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product flow, journey, funnel, onboarding path, checkout path, settings path, screen, or other product experience.\n\nThe output is not a loose opinion. The output is:\n\n- Screenshots of the flow\n- Those screenshots rendered inline in the report\n- A numbered step list\n- UX and design findings tied to steps or screenshots\n- Accessibility risks tied to steps or screenshots\n- Clear limits on what could not be checked from screenshots alone\n\n## Critical Overrides\n\n- Refer to the Plugin router [$index](..\u002Findex\u002FSKILL.md) before proceeding.\n- Follow [$critical-overrides](..\u002F..\u002Freferences\u002Fcritical-overrides.md).\n\n## User Context\n\nBefore starting, load [$user-context](..\u002Fuser-context\u002FSKILL.md) and run its preflight script when local shell access is available.\n\nUse saved product URLs, Figma files, screenshots, reference images, codebase paths, Storybook, tokens, design systems, brand assets, component refs, browser preferences, and share targets as grounding material when relevant.\n\nDo not inspect every saved reference. Inspect only what the current task needs.\n\n## Route\n\nBefore auditing:\n\n1. Identify the product or surface.\n2. Identify the flow or task.\n3. Choose the capture tool.\n4. Capture the flow.\n5. Save and inspect each screenshot.\n6. Return the audit inline with the accepted screenshots.\n\nOutput rules:\n\n- Default to a concise inline report with screenshots rendered in the chat.\n- Saving screenshots and notes in the workspace is an internal implementation detail. Do not ask the user to choose a local folder.\n- If the user explicitly asks for Figma, create the Figma audit board in addition to the inline report.\n- After the inline report, ask once: `Want me to plot this out in Figma with the screenshots and notes?`\n\nCapture rules:\n\n- Follow the Browser Choice rule in [$index](..\u002Findex\u002FSKILL.md#browser-choice).\n- If none of those can capture valid screenshots or control the flow, stop and report the blocker.\n\nBrowser capture order:\n\n1. Load the Browser skill before browser work.\n2. Connect to the browser and use the current tab when it already shows the target.\n3. Do not reload or navigate away unless the audit needs a fresh start.\n4. Observe the visible state before acting.\n5. Before each click, type, or key press, use the latest DOM snapshot to target one clear control.\n6. After each action, take the cheapest fresh check that proves what changed: DOM for structure, screenshot for visual state.\n7. Save and inspect the accepted screenshot before using it as audit evidence.\n\nFigma rules:\n\n- If Figma is the destination, load the required Figma skills before creating or editing the file.\n- Keep a local copy of every screenshot even when Figma succeeds.\n- Do not upload a screenshot to Figma until the saved local file has been inspected and accepted.\n- Figma is not done until the screenshots are visibly placed in the Figma output.\n- After placing screenshots in Figma, render or inspect the board and confirm every flow step has the correct screenshot visible in the correct card.\n- If an image is missing, misplaced, blank, or only uploaded as an unused asset, fix it before handoff.\n- If Figma tools cannot create files or place images, return the inline audit and explain the missing Figma capability.\n\nEvidence rules:\n\n- Use only evidence captured in the current audit run.\n- Do not use memory, prior chats, old traces, cached screenshots, or prior generated artifacts as audit evidence unless the user explicitly provides them.\n- Do not audit until the product, flow, and capture tool are known.\n- Do not claim full accessibility compliance from screenshots alone.\n\n## Capture And Audit The Flow\n\nYou are an expert design, UX, and accessibility auditor. For each step in the flow, capture what the user sees, observe how the screen behaves, inspect the screenshot, and write audit notes before moving on.\n\nFollow [references\u002Fdesign-audit-framework.md](references\u002Fdesign-audit-framework.md) when deciding what to inspect and how to describe strengths, UX issues, accessibility risks, limits, and recommendations.\n\nScreenshot source rule:\n\n- Use the screenshot you actually saw.\n- Save that exact screenshot to the local audit folder.\n- Open or inspect the saved file before accepting it.\n- If the saved file shows the wrong window, wrong state, blank page, crop, or loading screen, reject it and capture again.\n- When Figma is the destination, upload that accepted local file.\n- After upload, verify the Figma board shows the same step.\n- Do not replace a Browser, Chrome, or Computer Use screenshot with an OS screenshot unless you first prove the saved file shows the same window and state.\n\nFor every step:\n\n1. Move to the next step in the requested flow.\n2. Wait until the screen is loaded and visually stable.\n3. Check for loading spinners, blank areas, login walls, error pages, blocked states, cookie dialogs, and half-rendered content.\n4. Capture the screenshot.\n5. Inspect the screenshot before accepting it.\n6. Reject the screenshot if it is blank, loading, cropped, blocked, or showing the wrong state.\n7. Observe behavior that matters for the audit, such as navigation, focus, loading, validation, error handling, empty states, motion, and whether the next action is clear.\n8. Write notes for that step.\n9. In the notes, report strengths, UX issues, accessibility risks, and any limits that made the step difficult to audit.\n10. Save accepted screenshots with numbered names, such as `01-start.png`, `02-form-filled.png`, and `03-confirmation.png`.\n11. Inspect the saved screenshot file before upload or handoff.\n12. Keep each accepted screenshot and its notes together for the final inline report.\n13. If the user explicitly requested Figma, add each accepted screenshot and its notes to the board immediately.\n\nDefault inline report:\n\n- Render accepted screenshots in flow order.\n- Keep the report pithy: overall verdict, numbered steps, highest-impact changes, and evidence limits.\n- Tie every finding to the screenshot or step that supports it.\n\nIf the user explicitly requested Figma:\n\n- Place screenshots in order, left to right on the same row, with 200px between each one. Go to a new row every 15 screenshots, and separate those rows by 600px.\n- Underneath the screenshot, add text with the Step number and its name, and notes.\n- Keep a local folder copy even when Figma succeeds.\n- When you are done, wrap all of the assets you added in a Section and title the section.\n\nAcceptance checks:\n\n- Every important step in the requested flow has a valid screenshot or a named blocker.\n- Screenshots are saved in order.\n- Screenshots are rendered inline in the final report.\n- When Figma was explicitly requested, screenshots and notes are placed in the board as they are captured.\n- Every note points to the screenshot or step it describes.\n- Notes explain strengths, UX issues, accessibility risks, and evidence limits when those apply.\n- Accessibility risks say what can be seen from screenshots and what still needs testing.\n- The final screenshot set and notes are enough to support the requested audit.\n\nBlockers:\n\n- The flow cannot be completed.\n- A required step cannot be screenshotted.\n- The source changes in a way that makes the flow unclear.\n- Screenshots cannot be saved or rendered inline.\n- Notes cannot be written.\n- The requested claim would require evidence that screenshots cannot provide.\n- Do not claim an audit if the actual flow could not be accessed and captured. Help Center pages, web searches, and other indirect evidence are research, not an audit.\n\n## Final Response\n\nAfter the flow is captured and notes are written, list every step in the final response.\n\nThe final step list MUST include:\n\n- step number\n- short description of the step\n- general health of that step\n\nAlso include where the full output was saved or placed.\n\nKeep the language direct. Do not use broad design jargon when a plain phrase works.\n",{"data":36,"body":37},{"name":4,"description":6},{"type":38,"children":39},"root",[40,47,53,58,93,100,130,136,149,154,159,165,170,204,209,239,244,263,268,306,311,349,354,377,383,388,399,404,442,447,538,543,561,566,589,594,637,642,680,686,691,696,714,719],{"type":41,"tag":42,"props":43,"children":44},"element","h1",{"id":4},[45],{"type":46,"value":13},"text",{"type":41,"tag":48,"props":49,"children":50},"p",{},[51],{"type":46,"value":52},"Use this skill when the user wants to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product flow, journey, funnel, onboarding path, checkout path, settings path, screen, or other product experience.",{"type":41,"tag":48,"props":54,"children":55},{},[56],{"type":46,"value":57},"The output is not a loose opinion. The output is:",{"type":41,"tag":59,"props":60,"children":61},"ul",{},[62,68,73,78,83,88],{"type":41,"tag":63,"props":64,"children":65},"li",{},[66],{"type":46,"value":67},"Screenshots of the flow",{"type":41,"tag":63,"props":69,"children":70},{},[71],{"type":46,"value":72},"Those screenshots rendered inline in the report",{"type":41,"tag":63,"props":74,"children":75},{},[76],{"type":46,"value":77},"A numbered step list",{"type":41,"tag":63,"props":79,"children":80},{},[81],{"type":46,"value":82},"UX and design findings tied to steps or screenshots",{"type":41,"tag":63,"props":84,"children":85},{},[86],{"type":46,"value":87},"Accessibility risks tied to steps or screenshots",{"type":41,"tag":63,"props":89,"children":90},{},[91],{"type":46,"value":92},"Clear limits on what could not be checked from screenshots alone",{"type":41,"tag":94,"props":95,"children":97},"h2",{"id":96},"critical-overrides",[98],{"type":46,"value":99},"Critical Overrides",{"type":41,"tag":59,"props":101,"children":102},{},[103,117],{"type":41,"tag":63,"props":104,"children":105},{},[106,108,115],{"type":46,"value":107},"Refer to the Plugin router ",{"type":41,"tag":109,"props":110,"children":112},"a",{"href":111},"..\u002Findex\u002FSKILL.md",[113],{"type":46,"value":114},"$index",{"type":46,"value":116}," before proceeding.",{"type":41,"tag":63,"props":118,"children":119},{},[120,122,128],{"type":46,"value":121},"Follow ",{"type":41,"tag":109,"props":123,"children":125},{"href":124},"..\u002F..\u002Freferences\u002Fcritical-overrides.md",[126],{"type":46,"value":127},"$critical-overrides",{"type":46,"value":129},".",{"type":41,"tag":94,"props":131,"children":133},{"id":132},"user-context",[134],{"type":46,"value":135},"User Context",{"type":41,"tag":48,"props":137,"children":138},{},[139,141,147],{"type":46,"value":140},"Before starting, load ",{"type":41,"tag":109,"props":142,"children":144},{"href":143},"..\u002Fuser-context\u002FSKILL.md",[145],{"type":46,"value":146},"$user-context",{"type":46,"value":148}," and run its preflight script when local shell access is available.",{"type":41,"tag":48,"props":150,"children":151},{},[152],{"type":46,"value":153},"Use saved product URLs, Figma files, screenshots, reference images, codebase paths, Storybook, tokens, design systems, brand assets, component refs, browser preferences, and share targets as grounding material when relevant.",{"type":41,"tag":48,"props":155,"children":156},{},[157],{"type":46,"value":158},"Do not inspect every saved reference. Inspect only what the current task needs.",{"type":41,"tag":94,"props":160,"children":162},{"id":161},"route",[163],{"type":46,"value":164},"Route",{"type":41,"tag":48,"props":166,"children":167},{},[168],{"type":46,"value":169},"Before auditing:",{"type":41,"tag":171,"props":172,"children":173},"ol",{},[174,179,184,189,194,199],{"type":41,"tag":63,"props":175,"children":176},{},[177],{"type":46,"value":178},"Identify the product or surface.",{"type":41,"tag":63,"props":180,"children":181},{},[182],{"type":46,"value":183},"Identify the flow or task.",{"type":41,"tag":63,"props":185,"children":186},{},[187],{"type":46,"value":188},"Choose the capture tool.",{"type":41,"tag":63,"props":190,"children":191},{},[192],{"type":46,"value":193},"Capture the flow.",{"type":41,"tag":63,"props":195,"children":196},{},[197],{"type":46,"value":198},"Save and inspect each screenshot.",{"type":41,"tag":63,"props":200,"children":201},{},[202],{"type":46,"value":203},"Return the audit inline with the accepted screenshots.",{"type":41,"tag":48,"props":205,"children":206},{},[207],{"type":46,"value":208},"Output rules:",{"type":41,"tag":59,"props":210,"children":211},{},[212,217,222,227],{"type":41,"tag":63,"props":213,"children":214},{},[215],{"type":46,"value":216},"Default to a concise inline report with screenshots rendered in the chat.",{"type":41,"tag":63,"props":218,"children":219},{},[220],{"type":46,"value":221},"Saving screenshots and notes in the workspace is an internal implementation detail. Do not ask the user to choose a local folder.",{"type":41,"tag":63,"props":223,"children":224},{},[225],{"type":46,"value":226},"If the user explicitly asks for Figma, create the Figma audit board in addition to the inline report.",{"type":41,"tag":63,"props":228,"children":229},{},[230,232],{"type":46,"value":231},"After the inline report, ask once: ",{"type":41,"tag":233,"props":234,"children":236},"code",{"className":235},[],[237],{"type":46,"value":238},"Want me to plot this out in Figma with the screenshots and notes?",{"type":41,"tag":48,"props":240,"children":241},{},[242],{"type":46,"value":243},"Capture rules:",{"type":41,"tag":59,"props":245,"children":246},{},[247,258],{"type":41,"tag":63,"props":248,"children":249},{},[250,252,257],{"type":46,"value":251},"Follow the Browser Choice rule in ",{"type":41,"tag":109,"props":253,"children":255},{"href":254},"..\u002Findex\u002FSKILL.md#browser-choice",[256],{"type":46,"value":114},{"type":46,"value":129},{"type":41,"tag":63,"props":259,"children":260},{},[261],{"type":46,"value":262},"If none of those can capture valid screenshots or control the flow, stop and report the blocker.",{"type":41,"tag":48,"props":264,"children":265},{},[266],{"type":46,"value":267},"Browser capture order:",{"type":41,"tag":171,"props":269,"children":270},{},[271,276,281,286,291,296,301],{"type":41,"tag":63,"props":272,"children":273},{},[274],{"type":46,"value":275},"Load the Browser skill before browser work.",{"type":41,"tag":63,"props":277,"children":278},{},[279],{"type":46,"value":280},"Connect to the browser and use the current tab when it already shows the target.",{"type":41,"tag":63,"props":282,"children":283},{},[284],{"type":46,"value":285},"Do not reload or navigate away unless the audit needs a fresh start.",{"type":41,"tag":63,"props":287,"children":288},{},[289],{"type":46,"value":290},"Observe the visible state before acting.",{"type":41,"tag":63,"props":292,"children":293},{},[294],{"type":46,"value":295},"Before each click, type, or key press, use the latest DOM snapshot to target one clear control.",{"type":41,"tag":63,"props":297,"children":298},{},[299],{"type":46,"value":300},"After each action, take the cheapest fresh check that proves what changed: DOM for structure, screenshot for visual state.",{"type":41,"tag":63,"props":302,"children":303},{},[304],{"type":46,"value":305},"Save and inspect the accepted screenshot before using it as audit evidence.",{"type":41,"tag":48,"props":307,"children":308},{},[309],{"type":46,"value":310},"Figma rules:",{"type":41,"tag":59,"props":312,"children":313},{},[314,319,324,329,334,339,344],{"type":41,"tag":63,"props":315,"children":316},{},[317],{"type":46,"value":318},"If Figma is the destination, load the required Figma skills before creating or editing the file.",{"type":41,"tag":63,"props":320,"children":321},{},[322],{"type":46,"value":323},"Keep a local copy of every screenshot even when Figma succeeds.",{"type":41,"tag":63,"props":325,"children":326},{},[327],{"type":46,"value":328},"Do not upload a screenshot to Figma until the saved local file has been inspected and accepted.",{"type":41,"tag":63,"props":330,"children":331},{},[332],{"type":46,"value":333},"Figma is not done until the screenshots are visibly placed in the Figma output.",{"type":41,"tag":63,"props":335,"children":336},{},[337],{"type":46,"value":338},"After placing screenshots in Figma, render or inspect the board and confirm every flow step has the correct screenshot visible in the correct card.",{"type":41,"tag":63,"props":340,"children":341},{},[342],{"type":46,"value":343},"If an image is missing, misplaced, blank, or only uploaded as an unused asset, fix it before handoff.",{"type":41,"tag":63,"props":345,"children":346},{},[347],{"type":46,"value":348},"If Figma tools cannot create files or place images, return the inline audit and explain the missing Figma capability.",{"type":41,"tag":48,"props":350,"children":351},{},[352],{"type":46,"value":353},"Evidence rules:",{"type":41,"tag":59,"props":355,"children":356},{},[357,362,367,372],{"type":41,"tag":63,"props":358,"children":359},{},[360],{"type":46,"value":361},"Use only evidence captured in the current audit run.",{"type":41,"tag":63,"props":363,"children":364},{},[365],{"type":46,"value":366},"Do not use memory, prior chats, old traces, cached screenshots, or prior generated artifacts as audit evidence unless the user explicitly provides them.",{"type":41,"tag":63,"props":368,"children":369},{},[370],{"type":46,"value":371},"Do not audit until the product, flow, and capture tool are known.",{"type":41,"tag":63,"props":373,"children":374},{},[375],{"type":46,"value":376},"Do not claim full accessibility compliance from screenshots alone.",{"type":41,"tag":94,"props":378,"children":380},{"id":379},"capture-and-audit-the-flow",[381],{"type":46,"value":382},"Capture And Audit The Flow",{"type":41,"tag":48,"props":384,"children":385},{},[386],{"type":46,"value":387},"You are an expert design, UX, and accessibility auditor. For each step in the flow, capture what the user sees, observe how the screen behaves, inspect the screenshot, and write audit notes before moving on.",{"type":41,"tag":48,"props":389,"children":390},{},[391,392,397],{"type":46,"value":121},{"type":41,"tag":109,"props":393,"children":395},{"href":394},"references\u002Fdesign-audit-framework.md",[396],{"type":46,"value":394},{"type":46,"value":398}," when deciding what to inspect and how to describe strengths, UX issues, accessibility risks, limits, and recommendations.",{"type":41,"tag":48,"props":400,"children":401},{},[402],{"type":46,"value":403},"Screenshot source rule:",{"type":41,"tag":59,"props":405,"children":406},{},[407,412,417,422,427,432,437],{"type":41,"tag":63,"props":408,"children":409},{},[410],{"type":46,"value":411},"Use the screenshot you actually saw.",{"type":41,"tag":63,"props":413,"children":414},{},[415],{"type":46,"value":416},"Save that exact screenshot to the local audit folder.",{"type":41,"tag":63,"props":418,"children":419},{},[420],{"type":46,"value":421},"Open or inspect the saved file before accepting it.",{"type":41,"tag":63,"props":423,"children":424},{},[425],{"type":46,"value":426},"If the saved file shows the wrong window, wrong state, blank page, crop, or loading screen, reject it and capture again.",{"type":41,"tag":63,"props":428,"children":429},{},[430],{"type":46,"value":431},"When Figma is the destination, upload that accepted local file.",{"type":41,"tag":63,"props":433,"children":434},{},[435],{"type":46,"value":436},"After upload, verify the Figma board shows the same step.",{"type":41,"tag":63,"props":438,"children":439},{},[440],{"type":46,"value":441},"Do not replace a Browser, Chrome, or Computer Use screenshot with an OS screenshot unless you first prove the saved file shows the same window and state.",{"type":41,"tag":48,"props":443,"children":444},{},[445],{"type":46,"value":446},"For every step:",{"type":41,"tag":171,"props":448,"children":449},{},[450,455,460,465,470,475,480,485,490,495,523,528,533],{"type":41,"tag":63,"props":451,"children":452},{},[453],{"type":46,"value":454},"Move to the next step in the requested flow.",{"type":41,"tag":63,"props":456,"children":457},{},[458],{"type":46,"value":459},"Wait until the screen is loaded and visually stable.",{"type":41,"tag":63,"props":461,"children":462},{},[463],{"type":46,"value":464},"Check for loading spinners, blank areas, login walls, error pages, blocked states, cookie dialogs, and half-rendered content.",{"type":41,"tag":63,"props":466,"children":467},{},[468],{"type":46,"value":469},"Capture the screenshot.",{"type":41,"tag":63,"props":471,"children":472},{},[473],{"type":46,"value":474},"Inspect the screenshot before accepting it.",{"type":41,"tag":63,"props":476,"children":477},{},[478],{"type":46,"value":479},"Reject the screenshot if it is blank, loading, cropped, blocked, or showing the wrong state.",{"type":41,"tag":63,"props":481,"children":482},{},[483],{"type":46,"value":484},"Observe behavior that matters for the audit, such as navigation, focus, loading, validation, error handling, empty states, motion, and whether the next action is clear.",{"type":41,"tag":63,"props":486,"children":487},{},[488],{"type":46,"value":489},"Write notes for that step.",{"type":41,"tag":63,"props":491,"children":492},{},[493],{"type":46,"value":494},"In the notes, report strengths, UX issues, accessibility risks, and any limits that made the step difficult to audit.",{"type":41,"tag":63,"props":496,"children":497},{},[498,500,506,508,514,516,522],{"type":46,"value":499},"Save accepted screenshots with numbered names, such as ",{"type":41,"tag":233,"props":501,"children":503},{"className":502},[],[504],{"type":46,"value":505},"01-start.png",{"type":46,"value":507},", ",{"type":41,"tag":233,"props":509,"children":511},{"className":510},[],[512],{"type":46,"value":513},"02-form-filled.png",{"type":46,"value":515},", and ",{"type":41,"tag":233,"props":517,"children":519},{"className":518},[],[520],{"type":46,"value":521},"03-confirmation.png",{"type":46,"value":129},{"type":41,"tag":63,"props":524,"children":525},{},[526],{"type":46,"value":527},"Inspect the saved screenshot file before upload or handoff.",{"type":41,"tag":63,"props":529,"children":530},{},[531],{"type":46,"value":532},"Keep each accepted screenshot and its notes together for the final inline report.",{"type":41,"tag":63,"props":534,"children":535},{},[536],{"type":46,"value":537},"If the user explicitly requested Figma, add each accepted screenshot and its notes to the board immediately.",{"type":41,"tag":48,"props":539,"children":540},{},[541],{"type":46,"value":542},"Default inline report:",{"type":41,"tag":59,"props":544,"children":545},{},[546,551,556],{"type":41,"tag":63,"props":547,"children":548},{},[549],{"type":46,"value":550},"Render accepted screenshots in flow order.",{"type":41,"tag":63,"props":552,"children":553},{},[554],{"type":46,"value":555},"Keep the report pithy: overall verdict, numbered steps, highest-impact changes, and evidence limits.",{"type":41,"tag":63,"props":557,"children":558},{},[559],{"type":46,"value":560},"Tie every finding to the screenshot or step that supports it.",{"type":41,"tag":48,"props":562,"children":563},{},[564],{"type":46,"value":565},"If the user explicitly requested Figma:",{"type":41,"tag":59,"props":567,"children":568},{},[569,574,579,584],{"type":41,"tag":63,"props":570,"children":571},{},[572],{"type":46,"value":573},"Place screenshots in order, left to right on the same row, with 200px between each one. Go to a new row every 15 screenshots, and separate those rows by 600px.",{"type":41,"tag":63,"props":575,"children":576},{},[577],{"type":46,"value":578},"Underneath the screenshot, add text with the Step number and its name, and notes.",{"type":41,"tag":63,"props":580,"children":581},{},[582],{"type":46,"value":583},"Keep a local folder copy even when Figma succeeds.",{"type":41,"tag":63,"props":585,"children":586},{},[587],{"type":46,"value":588},"When you are done, wrap all of the assets you added in a Section and title the section.",{"type":41,"tag":48,"props":590,"children":591},{},[592],{"type":46,"value":593},"Acceptance checks:",{"type":41,"tag":59,"props":595,"children":596},{},[597,602,607,612,617,622,627,632],{"type":41,"tag":63,"props":598,"children":599},{},[600],{"type":46,"value":601},"Every important step in the requested flow has a valid screenshot or a named blocker.",{"type":41,"tag":63,"props":603,"children":604},{},[605],{"type":46,"value":606},"Screenshots are saved in order.",{"type":41,"tag":63,"props":608,"children":609},{},[610],{"type":46,"value":611},"Screenshots are rendered inline in the final report.",{"type":41,"tag":63,"props":613,"children":614},{},[615],{"type":46,"value":616},"When Figma was explicitly requested, screenshots and notes are placed in the board as they are captured.",{"type":41,"tag":63,"props":618,"children":619},{},[620],{"type":46,"value":621},"Every note points to the screenshot or step it describes.",{"type":41,"tag":63,"props":623,"children":624},{},[625],{"type":46,"value":626},"Notes explain strengths, UX issues, accessibility risks, and evidence limits when those apply.",{"type":41,"tag":63,"props":628,"children":629},{},[630],{"type":46,"value":631},"Accessibility risks say what can be seen from screenshots and what still needs testing.",{"type":41,"tag":63,"props":633,"children":634},{},[635],{"type":46,"value":636},"The final screenshot set and notes are enough to support the requested audit.",{"type":41,"tag":48,"props":638,"children":639},{},[640],{"type":46,"value":641},"Blockers:",{"type":41,"tag":59,"props":643,"children":644},{},[645,650,655,660,665,670,675],{"type":41,"tag":63,"props":646,"children":647},{},[648],{"type":46,"value":649},"The flow cannot be completed.",{"type":41,"tag":63,"props":651,"children":652},{},[653],{"type":46,"value":654},"A required step cannot be screenshotted.",{"type":41,"tag":63,"props":656,"children":657},{},[658],{"type":46,"value":659},"The source changes in a way that makes the flow unclear.",{"type":41,"tag":63,"props":661,"children":662},{},[663],{"type":46,"value":664},"Screenshots cannot be saved or rendered inline.",{"type":41,"tag":63,"props":666,"children":667},{},[668],{"type":46,"value":669},"Notes cannot be written.",{"type":41,"tag":63,"props":671,"children":672},{},[673],{"type":46,"value":674},"The requested claim would require evidence that screenshots cannot provide.",{"type":41,"tag":63,"props":676,"children":677},{},[678],{"type":46,"value":679},"Do not claim an audit if the actual flow could not be accessed and captured. Help Center pages, web searches, and other indirect evidence are research, not an audit.",{"type":41,"tag":94,"props":681,"children":683},{"id":682},"final-response",[684],{"type":46,"value":685},"Final Response",{"type":41,"tag":48,"props":687,"children":688},{},[689],{"type":46,"value":690},"After the flow is captured and notes are written, list every step in the final response.",{"type":41,"tag":48,"props":692,"children":693},{},[694],{"type":46,"value":695},"The final step list MUST include:",{"type":41,"tag":59,"props":697,"children":698},{},[699,704,709],{"type":41,"tag":63,"props":700,"children":701},{},[702],{"type":46,"value":703},"step number",{"type":41,"tag":63,"props":705,"children":706},{},[707],{"type":46,"value":708},"short description of the step",{"type":41,"tag":63,"props":710,"children":711},{},[712],{"type":46,"value":713},"general health of that step",{"type":41,"tag":48,"props":715,"children":716},{},[717],{"type":46,"value":718},"Also include where the full output was saved or placed.",{"type":41,"tag":48,"props":720,"children":721},{},[722],{"type":46,"value":723},"Keep the language direct. Do not use broad design jargon when a plain phrase works.",{"items":725,"total":928},[726,747,770,787,803,822,841,855,871,885,897,912],{"slug":727,"name":727,"fn":728,"description":729,"org":730,"tags":731,"stars":744,"repoUrl":745,"updatedAt":746},"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},[732,735,738,741],{"name":733,"slug":734,"type":14},"Documents","documents",{"name":736,"slug":737,"type":14},"Healthcare","healthcare",{"name":739,"slug":740,"type":14},"Insurance","insurance",{"name":742,"slug":743,"type":14},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":748,"name":748,"fn":749,"description":750,"org":751,"tags":752,"stars":767,"repoUrl":768,"updatedAt":769},"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},[753,756,758,761,764],{"name":754,"slug":755,"type":14},".NET","dotnet",{"name":757,"slug":748,"type":14},"ASP.NET Core",{"name":759,"slug":760,"type":14},"Blazor","blazor",{"name":762,"slug":763,"type":14},"C#","csharp",{"name":765,"slug":766,"type":14},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":771,"name":771,"fn":772,"description":773,"org":774,"tags":775,"stars":767,"repoUrl":768,"updatedAt":786},"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},[776,779,782,785],{"name":777,"slug":778,"type":14},"Apps SDK","apps-sdk",{"name":780,"slug":781,"type":14},"ChatGPT","chatgpt",{"name":783,"slug":784,"type":14},"MCP","mcp",{"name":9,"slug":8,"type":14},"2026-04-12T05:07:05.468097",{"slug":788,"name":788,"fn":789,"description":790,"org":791,"tags":792,"stars":767,"repoUrl":768,"updatedAt":802},"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},[793,796,799],{"name":794,"slug":795,"type":14},"API Development","api-development",{"name":797,"slug":798,"type":14},"CLI","cli",{"name":800,"slug":801,"type":14},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":804,"name":804,"fn":805,"description":806,"org":807,"tags":808,"stars":767,"repoUrl":768,"updatedAt":821},"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},[809,812,815,818],{"name":810,"slug":811,"type":14},"Cloudflare","cloudflare",{"name":813,"slug":814,"type":14},"Cloudflare Pages","cloudflare-pages",{"name":816,"slug":817,"type":14},"Cloudflare Workers","cloudflare-workers",{"name":819,"slug":820,"type":14},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":823,"name":823,"fn":824,"description":825,"org":826,"tags":827,"stars":767,"repoUrl":768,"updatedAt":840},"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},[828,831,834,837],{"name":829,"slug":830,"type":14},"Productivity","productivity",{"name":832,"slug":833,"type":14},"Project Management","project-management",{"name":835,"slug":836,"type":14},"Strategy","strategy",{"name":838,"slug":839,"type":14},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":842,"name":842,"fn":843,"description":844,"org":845,"tags":846,"stars":767,"repoUrl":768,"updatedAt":854},"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},[847,848,850,853],{"name":22,"slug":23,"type":14},{"name":849,"slug":842,"type":14},"Figma",{"name":851,"slug":852,"type":14},"Frontend","frontend",{"name":783,"slug":784,"type":14},"2026-04-12T05:06:47.939943",{"slug":856,"name":856,"fn":857,"description":858,"org":859,"tags":860,"stars":767,"repoUrl":768,"updatedAt":870},"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},[861,862,865,866,867],{"name":22,"slug":23,"type":14},{"name":863,"slug":864,"type":14},"Design System","design-system",{"name":849,"slug":842,"type":14},{"name":851,"slug":852,"type":14},{"name":868,"slug":869,"type":14},"UI Components","ui-components","2026-05-10T05:59:52.971881",{"slug":872,"name":872,"fn":873,"description":874,"org":875,"tags":876,"stars":767,"repoUrl":768,"updatedAt":884},"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},[877,878,879,882,883],{"name":22,"slug":23,"type":14},{"name":863,"slug":864,"type":14},{"name":880,"slug":881,"type":14},"Documentation","documentation",{"name":849,"slug":842,"type":14},{"name":851,"slug":852,"type":14},"2026-05-16T06:07:47.821474",{"slug":886,"name":886,"fn":887,"description":888,"org":889,"tags":890,"stars":767,"repoUrl":768,"updatedAt":896},"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},[891,892,893,894,895],{"name":22,"slug":23,"type":14},{"name":849,"slug":842,"type":14},{"name":851,"slug":852,"type":14},{"name":868,"slug":869,"type":14},{"name":765,"slug":766,"type":14},"2026-05-16T06:07:40.583615",{"slug":898,"name":898,"fn":899,"description":900,"org":901,"tags":902,"stars":767,"repoUrl":768,"updatedAt":911},"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},[903,906,907,910],{"name":904,"slug":905,"type":14},"Animation","animation",{"name":800,"slug":801,"type":14},{"name":908,"slug":909,"type":14},"Creative","creative",{"name":22,"slug":23,"type":14},"2026-05-02T05:31:48.48485",{"slug":913,"name":913,"fn":914,"description":915,"org":916,"tags":917,"stars":767,"repoUrl":768,"updatedAt":927},"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},[918,919,920,923,926],{"name":908,"slug":909,"type":14},{"name":22,"slug":23,"type":14},{"name":921,"slug":922,"type":14},"Image Generation","image-generation",{"name":924,"slug":925,"type":14},"Images","images",{"name":9,"slug":8,"type":14},"2026-05-15T06:23:24.312127",675,{"items":930,"total":1030},[931,950,964,975,991,998,1015],{"slug":932,"name":932,"fn":933,"description":934,"org":935,"tags":936,"stars":24,"repoUrl":25,"updatedAt":949},"analyze-account-signals","analyze account signals for sales intelligence","Use when the user wants to know what changed with one account, monitor an owner portfolio or watchlist, or rank accounts needing attention from recent evidence. Produce an evidence-backed account brief or bounded watchlist summary with recommended actions.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[937,940,943,946],{"name":938,"slug":939,"type":14},"Analytics","analytics",{"name":941,"slug":942,"type":14},"CRM","crm",{"name":944,"slug":945,"type":14},"Research","research",{"name":947,"slug":948,"type":14},"Sales","sales","2026-07-01T07:54:11.79288",{"slug":951,"name":951,"fn":952,"description":953,"org":954,"tags":955,"stars":24,"repoUrl":25,"updatedAt":963},"analyze-data-quality","assess data quality for analysis","Assess whether structured data, query results, dashboards, or analytical evidence are trustworthy enough to use. Use when the task is to check data quality, reconcile conflicting sources or metric definitions, or decide whether evidence is safe to cite.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[956,957,960],{"name":13,"slug":4,"type":14},{"name":958,"slug":959,"type":14},"Data Engineering","data-engineering",{"name":961,"slug":962,"type":14},"Data Quality","data-quality","2026-07-01T07:55:01.146961",{"slug":965,"name":965,"fn":966,"description":967,"org":968,"tags":969,"stars":24,"repoUrl":25,"updatedAt":974},"answers-ask-user-input","request missing context from users","Use when a small amount of missing context would materially improve the answer and tappable options plus a free-text answer can gather it efficiently.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[970,973],{"name":971,"slug":972,"type":14},"Communications","communications",{"name":829,"slug":830,"type":14},"2026-07-14T05:43:36.096323",{"slug":976,"name":976,"fn":977,"description":978,"org":979,"tags":980,"stars":24,"repoUrl":25,"updatedAt":990},"apollo","prospect and enrich leads with Apollo","Use only when a focused Sales workflow has selected a present and connected Apollo connector, or the user explicitly asks for Apollo prospecting, enrichment, Company Details, records, sequences, or outbound planning. Apply Apollo v2-specific behavior only after verifying app version 2.0.0 or later.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[981,983,986,989],{"name":982,"slug":976,"type":14},"Apollo",{"name":984,"slug":985,"type":14},"Lead Enrichment","lead-enrichment",{"name":987,"slug":988,"type":14},"Prospecting","prospecting",{"name":947,"slug":948,"type":14},"2026-07-14T05:43:34.800076",{"slug":4,"name":4,"fn":5,"description":6,"org":992,"tags":993,"stars":24,"repoUrl":25,"updatedAt":26},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[994,995,996,997],{"name":13,"slug":4,"type":14},{"name":22,"slug":23,"type":14},{"name":16,"slug":17,"type":14},{"name":19,"slug":20,"type":14},{"slug":999,"name":999,"fn":1000,"description":1001,"org":1002,"tags":1003,"stars":24,"repoUrl":25,"updatedAt":1014},"build-business-case","build customer-led business cases and ROI","Review commercial proposals and build customer-led business cases, ROI or value models, pricing or investment rationales, executive summaries, and customer-ready value stories tied to a customer, workflow, initiative, or decision.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1004,1007,1010,1013],{"name":1005,"slug":1006,"type":14},"Content Creation","content-creation",{"name":1008,"slug":1009,"type":14},"Finance","finance",{"name":1011,"slug":1012,"type":14},"Financial Modeling","financial-modeling",{"name":947,"slug":948,"type":14},"2026-07-01T07:54:02.779003",{"slug":1016,"name":1016,"fn":1017,"description":1018,"org":1019,"tags":1020,"stars":24,"repoUrl":25,"updatedAt":1029},"build-competitive-brief","build competitive briefs and battlecards","Use when the user wants a competitor or vendor comparison, market-landscape analysis, battlecard, objection package, positioning brief, or account-specific competitive view. Produce an evidence-backed comparison, guidance, and brief, using supplied materials, connected research, and public evidence when appropriate.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1021,1024,1027,1028],{"name":1022,"slug":1023,"type":14},"Competitive Intelligence","competitive-intelligence",{"name":1025,"slug":1026,"type":14},"Marketing","marketing",{"name":944,"slug":945,"type":14},{"name":947,"slug":948,"type":14},"2026-07-01T07:54:13.073252",43]