[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-attack-path-analysis":3,"mdc-hypnis-key":33,"related-repo-openai-attack-path-analysis":548,"related-org-openai-attack-path-analysis":672},{"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},"attack-path-analysis","analyze security attack paths and severity","Use when Codex is already in the attack-path-analysis phase of a security scan or the user explicitly asks to trace a security finding from source to sink and calibrate severity. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"openai","OpenAI","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fopenai.png",[12,16,19],{"name":13,"slug":14,"type":15},"Security","security","tag",{"name":17,"slug":18,"type":15},"Codex","codex",{"name":20,"slug":21,"type":15},"Code Analysis","code-analysis",3992,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-05-01T06:02:25.400415",null,465,[],{"repoUrl":23,"stars":22,"forks":26,"topics":29,"description":30},[],"OpenAI Plugins","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fcodex-security\u002Fskills\u002Fattack-path-analysis","---\nname: attack-path-analysis\ndescription: Use when Codex is already in the attack-path-analysis phase of a security scan or the user explicitly asks to trace a security finding from source to sink and calibrate severity. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.\n---\n\n# Security Attack Path Analysis\n\n## Objective\n\nTurn validated or still-plausible findings into explicit attacker stories, structured attack-path analysis facts, severity calibration, and a final reportability decision grounded in the threat model.\n\n## Artifact Resolution\n\nThe path references in this skill are the default locations for this phase.\nIf the user explicitly provides a different path for a required input or output, use the user-provided path instead of the corresponding default path referenced in this skill.\nIf a required input is still missing, stop and ask the user for it before continuing.\nUse the shared scan artifact path conventions in `..\u002F..\u002Freferences\u002Fscan-artifacts.md`.\n\n## Workflow\n\n1. Load the per-scan threat model path from `..\u002F..\u002Freferences\u002Fscan-artifacts.md` as the repo-specific threat-model source of truth. Start from this along with the potential findings. Both inputs are required for this workflow.\n   - For repository-wide and scoped-path scans, include validation closure rows marked `reportable` or `survives: yes` even if they were not assigned polished candidate numbers during discovery.\n2. Determine whether the affected code is in scope for the repository threat model and whether it belongs to a real product surface or real production workflow.\n3. Build a factual attack path using repository evidence only:\n   - service mapping\n   - exposure and entry points\n   - identity, privilege, and trust boundaries\n   - secrets handling and sensitive-data flow\n   - reachability\n   - existing controls and mitigations\n4. Before finalizing scope or reportability-driving facts, identify the strongest repository counterevidence against the key scoping fields and explain why it is or is not dispositive.\n5. Calibrate impact and likelihood from the repository evidence.\n6. Apply a separate final policy-adjustment pass mechanically using those facts and the calibrated severity.\n7. Drop any candidate whose final policy decision is `ignore`.\n8. Save that finding's visible attack-path report to its per-finding attack-path analysis report path from `..\u002F..\u002Freferences\u002Fscan-artifacts.md`.\n9. Append one attack-path receipt per candidate id to that finding's candidate ledger path from `..\u002F..\u002Freferences\u002Fscan-artifacts.md`. The receipt must record the candidate id, attack-path reportability decision, attack-path facts or exact proof gap, and attack-path artifact\u002Freport reference for that candidate finding.\n\n## Scope and Attack Path Checklist\n\nUse this checklist before finalizing the attack-path facts or policy decision:\n\n- Determine whether the finding is actually a real security vulnerability rather than a correctness bug or false positive.\n- Determine whether the affected code belongs to a real product surface or meaningful production workflow.\n- Map the relevant service, component, or workflow context from repository evidence.\n- Establish exposure and entry points from repository evidence such as listeners, ingress, load balancers, service ports, manifests, routing, or network policy.\n- Establish identities, privileges, and trust boundaries that matter for the path.\n- Establish whether sensitive data, secrets references, or privileged control paths are involved.\n- Determine whether a realistic attacker can actually reach and use the issue from an in-scope attack surface.\n- Identify the strongest repository counterevidence against the scoping and reportability-driving fields before finalizing them.\n- Lower confidence or keep fields unknown when repository evidence is incomplete; do not automatically suppress a finding solely because deployment evidence is missing.\n\n## Counterevidence Checklist\n\nFor the most interpretive fields, explicitly ask what repository evidence suggests the opposite and why it does or does not defeat the finding:\n\n- In-Scope Status According to the Threat Model\n- Vector\n- Auth Scope\n- Exposure\n- Cross-Boundary Behavior\n- Preconditions\n- Impact Surface\n\nLook specifically for repository evidence that the path is:\n\n- out of scope\n- internal-only\n- admin-only\n- not cross-boundary\n- not attacker-reachable\n- not meaningfully reportable\n\n## Severity and Policy Checklist\n\nApply severity and policy calibration using `references\u002Fseverity-policy.md`.\n\n## Output Contract\n\nFor each surviving finding include:\n\n- title\n- candidate id, instance key, and ledger row id when provided\n- affected lines from validation, preserving labeled entrypoint\u002Fwrapper, root_control, sink, and concrete_implementation locations\n- attack path steps\n- rendered attack-path facts\n- counterevidence summary and challenges\n- severity calibration\n- final policy decision\n- enough reasoning that a later reader can understand why the finding survived or was suppressed\n\nRender attack-path facts using `references\u002Fattack-path-facts.md`.\n\n## Hard Rules\n\n- Prefer repository evidence first, but use network connectivity when it materially helps confirm deployment context, reachable surfaces, or other reportability-relevant facts.\n- Do not invent attack chains that the code does not support.\n- Do not leave candidate coverage implicit. Every candidate finding that reaches attack-path analysis must leave an attack-path receipt in its candidate-ledger path from `..\u002F..\u002Freferences\u002Fscan-artifacts.md`, even when the final policy decision is `ignore` or the path remains deferred.\n- Do not drop exact affected locations while converting validated findings into attack paths. Repository-wide seeded\u002Froot-control rows that survive validation must keep their root-control file:line even when a wrapper, route, or transport is easier to explain.\n- Do not skip a reportable validation row because a neighboring same-family finding has a cleaner story. Either produce attack-path facts for that exact row or make an explicit final policy decision with repository counterevidence.\n- Missing public-ingress evidence is not by itself dispositive counterevidence.\n- Keep attack-path analysis, severity calibration, and final policy suppression as separate sub-stages.\n- Use the final policy-adjustment matrix mechanically rather than re-arguing severity from scratch after the facts are set.\n- Save a final visible report for each candidate finding using that finding's attack-path analysis report path from `..\u002F..\u002Freferences\u002Fscan-artifacts.md`.\n\n-- Considerations for attack path --\n- A finding should count as a real security issue if a realistic attacker could use it from a reasonable attack surface relevant to the product, especially if it is something that is part of the thread model.\n- The attack surface should generally be one that is plausibly exposed to end users \u002F external actors (or another actor explicitly in scope in the threat model), not an arbitrary internal-only or contrived path.\n",{"data":34,"body":35},{"name":4,"description":6},{"type":36,"children":37},"root",[38,47,54,60,66,80,86,221,227,232,280,286,291,329,334,367,373,385,391,396,444,456,462,530,535],{"type":39,"tag":40,"props":41,"children":43},"element","h1",{"id":42},"security-attack-path-analysis",[44],{"type":45,"value":46},"text","Security Attack Path Analysis",{"type":39,"tag":48,"props":49,"children":51},"h2",{"id":50},"objective",[52],{"type":45,"value":53},"Objective",{"type":39,"tag":55,"props":56,"children":57},"p",{},[58],{"type":45,"value":59},"Turn validated or still-plausible findings into explicit attacker stories, structured attack-path analysis facts, severity calibration, and a final reportability decision grounded in the threat model.",{"type":39,"tag":48,"props":61,"children":63},{"id":62},"artifact-resolution",[64],{"type":45,"value":65},"Artifact Resolution",{"type":39,"tag":55,"props":67,"children":68},{},[69,71,78],{"type":45,"value":70},"The path references in this skill are the default locations for this phase.\nIf the user explicitly provides a different path for a required input or output, use the user-provided path instead of the corresponding default path referenced in this skill.\nIf a required input is still missing, stop and ask the user for it before continuing.\nUse the shared scan artifact path conventions in ",{"type":39,"tag":72,"props":73,"children":75},"code",{"className":74},[],[76],{"type":45,"value":77},"..\u002F..\u002Freferences\u002Fscan-artifacts.md",{"type":45,"value":79},".",{"type":39,"tag":48,"props":81,"children":83},{"id":82},"workflow",[84],{"type":45,"value":85},"Workflow",{"type":39,"tag":87,"props":88,"children":89},"ol",{},[90,128,133,171,176,181,186,198,209],{"type":39,"tag":91,"props":92,"children":93},"li",{},[94,96,101,103],{"type":45,"value":95},"Load the per-scan threat model path from ",{"type":39,"tag":72,"props":97,"children":99},{"className":98},[],[100],{"type":45,"value":77},{"type":45,"value":102}," as the repo-specific threat-model source of truth. Start from this along with the potential findings. Both inputs are required for this workflow.\n",{"type":39,"tag":104,"props":105,"children":106},"ul",{},[107],{"type":39,"tag":91,"props":108,"children":109},{},[110,112,118,120,126],{"type":45,"value":111},"For repository-wide and scoped-path scans, include validation closure rows marked ",{"type":39,"tag":72,"props":113,"children":115},{"className":114},[],[116],{"type":45,"value":117},"reportable",{"type":45,"value":119}," or ",{"type":39,"tag":72,"props":121,"children":123},{"className":122},[],[124],{"type":45,"value":125},"survives: yes",{"type":45,"value":127}," even if they were not assigned polished candidate numbers during discovery.",{"type":39,"tag":91,"props":129,"children":130},{},[131],{"type":45,"value":132},"Determine whether the affected code is in scope for the repository threat model and whether it belongs to a real product surface or real production workflow.",{"type":39,"tag":91,"props":134,"children":135},{},[136,138],{"type":45,"value":137},"Build a factual attack path using repository evidence only:\n",{"type":39,"tag":104,"props":139,"children":140},{},[141,146,151,156,161,166],{"type":39,"tag":91,"props":142,"children":143},{},[144],{"type":45,"value":145},"service mapping",{"type":39,"tag":91,"props":147,"children":148},{},[149],{"type":45,"value":150},"exposure and entry points",{"type":39,"tag":91,"props":152,"children":153},{},[154],{"type":45,"value":155},"identity, privilege, and trust boundaries",{"type":39,"tag":91,"props":157,"children":158},{},[159],{"type":45,"value":160},"secrets handling and sensitive-data flow",{"type":39,"tag":91,"props":162,"children":163},{},[164],{"type":45,"value":165},"reachability",{"type":39,"tag":91,"props":167,"children":168},{},[169],{"type":45,"value":170},"existing controls and mitigations",{"type":39,"tag":91,"props":172,"children":173},{},[174],{"type":45,"value":175},"Before finalizing scope or reportability-driving facts, identify the strongest repository counterevidence against the key scoping fields and explain why it is or is not dispositive.",{"type":39,"tag":91,"props":177,"children":178},{},[179],{"type":45,"value":180},"Calibrate impact and likelihood from the repository evidence.",{"type":39,"tag":91,"props":182,"children":183},{},[184],{"type":45,"value":185},"Apply a separate final policy-adjustment pass mechanically using those facts and the calibrated severity.",{"type":39,"tag":91,"props":187,"children":188},{},[189,191,197],{"type":45,"value":190},"Drop any candidate whose final policy decision is ",{"type":39,"tag":72,"props":192,"children":194},{"className":193},[],[195],{"type":45,"value":196},"ignore",{"type":45,"value":79},{"type":39,"tag":91,"props":199,"children":200},{},[201,203,208],{"type":45,"value":202},"Save that finding's visible attack-path report to its per-finding attack-path analysis report path from ",{"type":39,"tag":72,"props":204,"children":206},{"className":205},[],[207],{"type":45,"value":77},{"type":45,"value":79},{"type":39,"tag":91,"props":210,"children":211},{},[212,214,219],{"type":45,"value":213},"Append one attack-path receipt per candidate id to that finding's candidate ledger path from ",{"type":39,"tag":72,"props":215,"children":217},{"className":216},[],[218],{"type":45,"value":77},{"type":45,"value":220},". The receipt must record the candidate id, attack-path reportability decision, attack-path facts or exact proof gap, and attack-path artifact\u002Freport reference for that candidate finding.",{"type":39,"tag":48,"props":222,"children":224},{"id":223},"scope-and-attack-path-checklist",[225],{"type":45,"value":226},"Scope and Attack Path Checklist",{"type":39,"tag":55,"props":228,"children":229},{},[230],{"type":45,"value":231},"Use this checklist before finalizing the attack-path facts or policy decision:",{"type":39,"tag":104,"props":233,"children":234},{},[235,240,245,250,255,260,265,270,275],{"type":39,"tag":91,"props":236,"children":237},{},[238],{"type":45,"value":239},"Determine whether the finding is actually a real security vulnerability rather than a correctness bug or false positive.",{"type":39,"tag":91,"props":241,"children":242},{},[243],{"type":45,"value":244},"Determine whether the affected code belongs to a real product surface or meaningful production workflow.",{"type":39,"tag":91,"props":246,"children":247},{},[248],{"type":45,"value":249},"Map the relevant service, component, or workflow context from repository evidence.",{"type":39,"tag":91,"props":251,"children":252},{},[253],{"type":45,"value":254},"Establish exposure and entry points from repository evidence such as listeners, ingress, load balancers, service ports, manifests, routing, or network policy.",{"type":39,"tag":91,"props":256,"children":257},{},[258],{"type":45,"value":259},"Establish identities, privileges, and trust boundaries that matter for the path.",{"type":39,"tag":91,"props":261,"children":262},{},[263],{"type":45,"value":264},"Establish whether sensitive data, secrets references, or privileged control paths are involved.",{"type":39,"tag":91,"props":266,"children":267},{},[268],{"type":45,"value":269},"Determine whether a realistic attacker can actually reach and use the issue from an in-scope attack surface.",{"type":39,"tag":91,"props":271,"children":272},{},[273],{"type":45,"value":274},"Identify the strongest repository counterevidence against the scoping and reportability-driving fields before finalizing them.",{"type":39,"tag":91,"props":276,"children":277},{},[278],{"type":45,"value":279},"Lower confidence or keep fields unknown when repository evidence is incomplete; do not automatically suppress a finding solely because deployment evidence is missing.",{"type":39,"tag":48,"props":281,"children":283},{"id":282},"counterevidence-checklist",[284],{"type":45,"value":285},"Counterevidence Checklist",{"type":39,"tag":55,"props":287,"children":288},{},[289],{"type":45,"value":290},"For the most interpretive fields, explicitly ask what repository evidence suggests the opposite and why it does or does not defeat the finding:",{"type":39,"tag":104,"props":292,"children":293},{},[294,299,304,309,314,319,324],{"type":39,"tag":91,"props":295,"children":296},{},[297],{"type":45,"value":298},"In-Scope Status According to the Threat Model",{"type":39,"tag":91,"props":300,"children":301},{},[302],{"type":45,"value":303},"Vector",{"type":39,"tag":91,"props":305,"children":306},{},[307],{"type":45,"value":308},"Auth Scope",{"type":39,"tag":91,"props":310,"children":311},{},[312],{"type":45,"value":313},"Exposure",{"type":39,"tag":91,"props":315,"children":316},{},[317],{"type":45,"value":318},"Cross-Boundary Behavior",{"type":39,"tag":91,"props":320,"children":321},{},[322],{"type":45,"value":323},"Preconditions",{"type":39,"tag":91,"props":325,"children":326},{},[327],{"type":45,"value":328},"Impact Surface",{"type":39,"tag":55,"props":330,"children":331},{},[332],{"type":45,"value":333},"Look specifically for repository evidence that the path is:",{"type":39,"tag":104,"props":335,"children":336},{},[337,342,347,352,357,362],{"type":39,"tag":91,"props":338,"children":339},{},[340],{"type":45,"value":341},"out of scope",{"type":39,"tag":91,"props":343,"children":344},{},[345],{"type":45,"value":346},"internal-only",{"type":39,"tag":91,"props":348,"children":349},{},[350],{"type":45,"value":351},"admin-only",{"type":39,"tag":91,"props":353,"children":354},{},[355],{"type":45,"value":356},"not cross-boundary",{"type":39,"tag":91,"props":358,"children":359},{},[360],{"type":45,"value":361},"not attacker-reachable",{"type":39,"tag":91,"props":363,"children":364},{},[365],{"type":45,"value":366},"not meaningfully reportable",{"type":39,"tag":48,"props":368,"children":370},{"id":369},"severity-and-policy-checklist",[371],{"type":45,"value":372},"Severity and Policy Checklist",{"type":39,"tag":55,"props":374,"children":375},{},[376,378,384],{"type":45,"value":377},"Apply severity and policy calibration using ",{"type":39,"tag":72,"props":379,"children":381},{"className":380},[],[382],{"type":45,"value":383},"references\u002Fseverity-policy.md",{"type":45,"value":79},{"type":39,"tag":48,"props":386,"children":388},{"id":387},"output-contract",[389],{"type":45,"value":390},"Output Contract",{"type":39,"tag":55,"props":392,"children":393},{},[394],{"type":45,"value":395},"For each surviving finding include:",{"type":39,"tag":104,"props":397,"children":398},{},[399,404,409,414,419,424,429,434,439],{"type":39,"tag":91,"props":400,"children":401},{},[402],{"type":45,"value":403},"title",{"type":39,"tag":91,"props":405,"children":406},{},[407],{"type":45,"value":408},"candidate id, instance key, and ledger row id when provided",{"type":39,"tag":91,"props":410,"children":411},{},[412],{"type":45,"value":413},"affected lines from validation, preserving labeled entrypoint\u002Fwrapper, root_control, sink, and concrete_implementation locations",{"type":39,"tag":91,"props":415,"children":416},{},[417],{"type":45,"value":418},"attack path steps",{"type":39,"tag":91,"props":420,"children":421},{},[422],{"type":45,"value":423},"rendered attack-path facts",{"type":39,"tag":91,"props":425,"children":426},{},[427],{"type":45,"value":428},"counterevidence summary and challenges",{"type":39,"tag":91,"props":430,"children":431},{},[432],{"type":45,"value":433},"severity calibration",{"type":39,"tag":91,"props":435,"children":436},{},[437],{"type":45,"value":438},"final policy decision",{"type":39,"tag":91,"props":440,"children":441},{},[442],{"type":45,"value":443},"enough reasoning that a later reader can understand why the finding survived or was suppressed",{"type":39,"tag":55,"props":445,"children":446},{},[447,449,455],{"type":45,"value":448},"Render attack-path facts using ",{"type":39,"tag":72,"props":450,"children":452},{"className":451},[],[453],{"type":45,"value":454},"references\u002Fattack-path-facts.md",{"type":45,"value":79},{"type":39,"tag":48,"props":457,"children":459},{"id":458},"hard-rules",[460],{"type":45,"value":461},"Hard Rules",{"type":39,"tag":104,"props":463,"children":464},{},[465,470,475,494,499,504,509,514,519],{"type":39,"tag":91,"props":466,"children":467},{},[468],{"type":45,"value":469},"Prefer repository evidence first, but use network connectivity when it materially helps confirm deployment context, reachable surfaces, or other reportability-relevant facts.",{"type":39,"tag":91,"props":471,"children":472},{},[473],{"type":45,"value":474},"Do not invent attack chains that the code does not support.",{"type":39,"tag":91,"props":476,"children":477},{},[478,480,485,487,492],{"type":45,"value":479},"Do not leave candidate coverage implicit. Every candidate finding that reaches attack-path analysis must leave an attack-path receipt in its candidate-ledger path from ",{"type":39,"tag":72,"props":481,"children":483},{"className":482},[],[484],{"type":45,"value":77},{"type":45,"value":486},", even when the final policy decision is ",{"type":39,"tag":72,"props":488,"children":490},{"className":489},[],[491],{"type":45,"value":196},{"type":45,"value":493}," or the path remains deferred.",{"type":39,"tag":91,"props":495,"children":496},{},[497],{"type":45,"value":498},"Do not drop exact affected locations while converting validated findings into attack paths. Repository-wide seeded\u002Froot-control rows that survive validation must keep their root-control file:line even when a wrapper, route, or transport is easier to explain.",{"type":39,"tag":91,"props":500,"children":501},{},[502],{"type":45,"value":503},"Do not skip a reportable validation row because a neighboring same-family finding has a cleaner story. Either produce attack-path facts for that exact row or make an explicit final policy decision with repository counterevidence.",{"type":39,"tag":91,"props":505,"children":506},{},[507],{"type":45,"value":508},"Missing public-ingress evidence is not by itself dispositive counterevidence.",{"type":39,"tag":91,"props":510,"children":511},{},[512],{"type":45,"value":513},"Keep attack-path analysis, severity calibration, and final policy suppression as separate sub-stages.",{"type":39,"tag":91,"props":515,"children":516},{},[517],{"type":45,"value":518},"Use the final policy-adjustment matrix mechanically rather than re-arguing severity from scratch after the facts are set.",{"type":39,"tag":91,"props":520,"children":521},{},[522,524,529],{"type":45,"value":523},"Save a final visible report for each candidate finding using that finding's attack-path analysis report path from ",{"type":39,"tag":72,"props":525,"children":527},{"className":526},[],[528],{"type":45,"value":77},{"type":45,"value":79},{"type":39,"tag":55,"props":531,"children":532},{},[533],{"type":45,"value":534},"-- Considerations for attack path --",{"type":39,"tag":104,"props":536,"children":537},{},[538,543],{"type":39,"tag":91,"props":539,"children":540},{},[541],{"type":45,"value":542},"A finding should count as a real security issue if a realistic attacker could use it from a reasonable attack surface relevant to the product, especially if it is something that is part of the thread model.",{"type":39,"tag":91,"props":544,"children":545},{},[546],{"type":45,"value":547},"The attack surface should generally be one that is plausibly exposed to end users \u002F external actors (or another actor explicitly in scope in the threat model), not an arbitrary internal-only or contrived path.",{"items":549,"total":671},[550,569,585,597,617,639,659],{"slug":551,"name":551,"fn":552,"description":553,"org":554,"tags":555,"stars":22,"repoUrl":23,"updatedAt":568},"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},[556,559,562,565],{"name":557,"slug":558,"type":15},"Accessibility","accessibility",{"name":560,"slug":561,"type":15},"Charts","charts",{"name":563,"slug":564,"type":15},"Data Visualization","data-visualization",{"name":566,"slug":567,"type":15},"Design","design","2026-06-30T19:00:57.102",{"slug":570,"name":570,"fn":571,"description":572,"org":573,"tags":574,"stars":22,"repoUrl":23,"updatedAt":584},"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},[575,578,581],{"name":576,"slug":577,"type":15},"Agents","agents",{"name":579,"slug":580,"type":15},"Browser Automation","browser-automation",{"name":582,"slug":583,"type":15},"Testing","testing","2026-04-06T18:41:03.44016",{"slug":586,"name":586,"fn":587,"description":588,"org":589,"tags":590,"stars":22,"repoUrl":23,"updatedAt":596},"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},[591,592,595],{"name":579,"slug":580,"type":15},{"name":593,"slug":594,"type":15},"Local Development","local-development",{"name":582,"slug":583,"type":15},"2026-04-06T18:41:17.526867",{"slug":598,"name":598,"fn":599,"description":600,"org":601,"tags":602,"stars":22,"repoUrl":23,"updatedAt":616},"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},[603,604,607,610,613],{"name":576,"slug":577,"type":15},{"name":605,"slug":606,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":608,"slug":609,"type":15},"SDK","sdk",{"name":611,"slug":612,"type":15},"Serverless","serverless",{"name":614,"slug":615,"type":15},"WebSockets","websockets","2026-04-06T18:39:51.717063",{"slug":618,"name":618,"fn":619,"description":620,"org":621,"tags":622,"stars":22,"repoUrl":23,"updatedAt":638},"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},[623,626,629,632,635],{"name":624,"slug":625,"type":15},"Frontend","frontend",{"name":627,"slug":628,"type":15},"React","react",{"name":630,"slug":631,"type":15},"shadcn\u002Fui","shadcn-ui",{"name":633,"slug":634,"type":15},"UI Components","ui-components",{"name":636,"slug":637,"type":15},"Vercel","vercel","2026-04-06T18:40:59.619419",{"slug":640,"name":640,"fn":641,"description":642,"org":643,"tags":644,"stars":22,"repoUrl":23,"updatedAt":658},"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},[645,648,651,654,657],{"name":646,"slug":647,"type":15},"AI Infrastructure","ai-infrastructure",{"name":649,"slug":650,"type":15},"Cost Optimization","cost-optimization",{"name":652,"slug":653,"type":15},"LLM","llm",{"name":655,"slug":656,"type":15},"Performance","performance",{"name":636,"slug":637,"type":15},"2026-04-06T18:40:44.377464",{"slug":660,"name":660,"fn":661,"description":662,"org":663,"tags":664,"stars":22,"repoUrl":23,"updatedAt":670},"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},[665,666,669],{"name":649,"slug":650,"type":15},{"name":667,"slug":668,"type":15},"Database","database",{"name":652,"slug":653,"type":15},"2026-04-06T18:41:08.513425",600,{"items":673,"total":868},[674,695,718,735,749,766,785,797,811,825,837,852],{"slug":675,"name":675,"fn":676,"description":677,"org":678,"tags":679,"stars":692,"repoUrl":693,"updatedAt":694},"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},[680,683,686,689],{"name":681,"slug":682,"type":15},"Documents","documents",{"name":684,"slug":685,"type":15},"Healthcare","healthcare",{"name":687,"slug":688,"type":15},"Insurance","insurance",{"name":690,"slug":691,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":696,"name":696,"fn":697,"description":698,"org":699,"tags":700,"stars":715,"repoUrl":716,"updatedAt":717},"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},[701,704,706,709,712],{"name":702,"slug":703,"type":15},".NET","dotnet",{"name":705,"slug":696,"type":15},"ASP.NET Core",{"name":707,"slug":708,"type":15},"Blazor","blazor",{"name":710,"slug":711,"type":15},"C#","csharp",{"name":713,"slug":714,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":719,"name":719,"fn":720,"description":721,"org":722,"tags":723,"stars":715,"repoUrl":716,"updatedAt":734},"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},[724,727,730,733],{"name":725,"slug":726,"type":15},"Apps SDK","apps-sdk",{"name":728,"slug":729,"type":15},"ChatGPT","chatgpt",{"name":731,"slug":732,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":736,"name":736,"fn":737,"description":738,"org":739,"tags":740,"stars":715,"repoUrl":716,"updatedAt":748},"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},[741,744,747],{"name":742,"slug":743,"type":15},"API Development","api-development",{"name":745,"slug":746,"type":15},"CLI","cli",{"name":17,"slug":18,"type":15},"2026-04-12T05:07:04.132762",{"slug":750,"name":750,"fn":751,"description":752,"org":753,"tags":754,"stars":715,"repoUrl":716,"updatedAt":765},"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},[755,758,761,762],{"name":756,"slug":757,"type":15},"Cloudflare","cloudflare",{"name":759,"slug":760,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":605,"slug":606,"type":15},{"name":763,"slug":764,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":767,"name":767,"fn":768,"description":769,"org":770,"tags":771,"stars":715,"repoUrl":716,"updatedAt":784},"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},[772,775,778,781],{"name":773,"slug":774,"type":15},"Productivity","productivity",{"name":776,"slug":777,"type":15},"Project Management","project-management",{"name":779,"slug":780,"type":15},"Strategy","strategy",{"name":782,"slug":783,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":786,"name":786,"fn":787,"description":788,"org":789,"tags":790,"stars":715,"repoUrl":716,"updatedAt":796},"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},[791,792,794,795],{"name":566,"slug":567,"type":15},{"name":793,"slug":786,"type":15},"Figma",{"name":624,"slug":625,"type":15},{"name":731,"slug":732,"type":15},"2026-04-12T05:06:47.939943",{"slug":798,"name":798,"fn":799,"description":800,"org":801,"tags":802,"stars":715,"repoUrl":716,"updatedAt":810},"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},[803,804,807,808,809],{"name":566,"slug":567,"type":15},{"name":805,"slug":806,"type":15},"Design System","design-system",{"name":793,"slug":786,"type":15},{"name":624,"slug":625,"type":15},{"name":633,"slug":634,"type":15},"2026-05-10T05:59:52.971881",{"slug":812,"name":812,"fn":813,"description":814,"org":815,"tags":816,"stars":715,"repoUrl":716,"updatedAt":824},"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},[817,818,819,822,823],{"name":566,"slug":567,"type":15},{"name":805,"slug":806,"type":15},{"name":820,"slug":821,"type":15},"Documentation","documentation",{"name":793,"slug":786,"type":15},{"name":624,"slug":625,"type":15},"2026-05-16T06:07:47.821474",{"slug":826,"name":826,"fn":827,"description":828,"org":829,"tags":830,"stars":715,"repoUrl":716,"updatedAt":836},"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},[831,832,833,834,835],{"name":566,"slug":567,"type":15},{"name":793,"slug":786,"type":15},{"name":624,"slug":625,"type":15},{"name":633,"slug":634,"type":15},{"name":713,"slug":714,"type":15},"2026-05-16T06:07:40.583615",{"slug":838,"name":838,"fn":839,"description":840,"org":841,"tags":842,"stars":715,"repoUrl":716,"updatedAt":851},"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},[843,846,847,850],{"name":844,"slug":845,"type":15},"Animation","animation",{"name":17,"slug":18,"type":15},{"name":848,"slug":849,"type":15},"Creative","creative",{"name":566,"slug":567,"type":15},"2026-05-02T05:31:48.48485",{"slug":853,"name":853,"fn":854,"description":855,"org":856,"tags":857,"stars":715,"repoUrl":716,"updatedAt":867},"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},[858,859,860,863,866],{"name":848,"slug":849,"type":15},{"name":566,"slug":567,"type":15},{"name":861,"slug":862,"type":15},"Image Generation","image-generation",{"name":864,"slug":865,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675]