[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-three-statement-model-builder":3,"mdc--z8zpnu-key":36,"related-repo-openai-three-statement-model-builder":973,"related-org-openai-three-statement-model-builder":1075},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":25,"repoUrl":26,"updatedAt":27,"license":28,"forks":29,"topics":30,"repo":31,"sourceUrl":34,"mdContent":35},"three-statement-model-builder","build three-statement operating models","Use when building public-equity three-statement operating model workbooks. Default to the banker formula workbook path for new model builds; use deterministic exports only for controlled support calculations or explicit lightweight runs. Do not use for standalone workbook audits.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"openai","OpenAI","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fopenai.png",[12,16,19,22],{"name":13,"slug":14,"type":15},"Financial Modeling","financial-modeling","tag",{"name":17,"slug":18,"type":15},"Excel","excel",{"name":20,"slug":21,"type":15},"Finance","finance",{"name":23,"slug":24,"type":15},"Accounting","accounting",4888,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-08-28T15:10:11.633957",null,661,[],{"repoUrl":26,"stars":25,"forks":29,"topics":32,"description":33},[],"OpenAI Plugins","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fpublic-equity-investing\u002Fskills\u002Fthree-statement-model-builder","---\nname: three-statement-model-builder\ndescription: Use when building public-equity three-statement operating model workbooks. Default to the banker formula workbook path for new model builds; use deterministic exports only for controlled support calculations or explicit lightweight runs. Do not use for standalone workbook audits.\n---\n\n# Three Statement Model Builder\n\n## Skill Configuration\n\n### Common Skill Instructions\n\nMANDATORY: Before searching connectors, retrieving evidence, or drafting output, read and apply the shared runtime contract in `..\u002Fpublic-equity-investing\u002FSKILL.md## Cross-Skill Runtime Contract`. Then check the router skill map and `..\u002F..\u002Fshared\u002Fplugin-routing-playbook.md` for adjacent skills that should be sequenced with this workflow. Do not run user-context setup or inspection during ordinary workflow work; route only explicit saved-context, source-setup, onboarding, or automation-setup requests to `..\u002Fuser-context\u002FSKILL.md`.\n\n## Relevant Dependency Categories\n\nThese are the source categories most likely to matter for this workflow. Use the router contract to resolve only the categories the task actually needs, prefer user-named sources first, and state any material source limitation.\n\n- `Company Filings & IR`\n- `Portfolio Models & Trackers`\n- `Market Data & Estimates`\n\n## Deliverable Intake\n\nBefore source gathering or analysis for a new substantive hero deliverable, load `..\u002F..\u002Fshared\u002Fdeliverable-intake-policy.md` and use its adaptive `request_user_input` preflight for materially unresolved format, depth, audience\u002Fuse, or focus choices. Reuse resolved preferences in downstream steps; when acting only as input to an owning workflow, do not re-prompt.\n\nOwn formula-first public-company operating model builds: integrated IS\u002FBS\u002FCF, working capital, PP&E and D&A, retained earnings, debt, revolver-style draws, cash sweep, equity-relevant liquidity\u002Fheadroom metrics, scenarios, sensitivities, machine checks, and senior-review reporting.\n\n## Hard Contract\n\n- Default model-build artifact level is `banker_formula_workbook`; use the formula workbook path for normal public-equity 3-statement build, refresh, forecast, and operating-model-package requests.\n- Formula mode is executed through `scripts\u002Fbuild_banker_formula_workbook.py` and must be labeled `banker_formula_workbook` only when its run log, workbook inspection, and `model_citations.json` prove the formula builder ran successfully.\n- Deterministic scripts remain available for controlled computed values, smoke tests, or explicit lightweight support exports. They produce `output\u002Fmodel.xlsx`, `output\u002Fplan.json`, `output\u002Frun_log.json`, `output\u002Fmanifest.json`, and optionally `output\u002Fsupport_note.md`. Legacy `output\u002Freport.md` is written only with `--write-report-md`.\n- Formula scripts produce `banker_formula_workbook.xlsx`, `banker_formula_workbook_run_log.json`, `model_citations.json`, and `manifest.json` in the selected output directory. The workbook is the hero deliverable; citation JSON, run logs, and manifests are support artifacts.\n- `output\u002Fmodel.xlsx` must start with a `Cover` tab that functions as a dashboard: model status, scenario outputs, revenue\u002FEBITDA\u002FFCF\u002Fcash, liquidity trough, leverage\u002Fheadroom, source posture, warnings\u002Fhard failures, workbook map.\n- `run_log.json` and `manifest.json` are required reliability artifacts; hard failures force `not-decision-ready`.\n- Never delete, overwrite, or mutate source data unless explicitly requested. Preserve raw tabs\u002Ffiles and write new outputs under `output\u002F` or a clearly named copy.\n- Material inputs must be evidence-labeled: `source_reported`, `company_provided`, `connector_sourced`, `public_filing`, `web_verified`, `management_guidance`, `analyst_estimate`, `benchmark`, `assumption`, or `placeholder`.\n- If placeholders, stale data, unsupported assumptions, or failed tie-outs remain active, mark the model no higher than `screen-grade`; hard failures mean `not-decision-ready`.\n\n## Routing\n\nUse this skill when the deliverable is a 3-statement build, refresh, rerun, operating model package, or integrated forecast rebuild. Route away when the primary ask is workbook audit\u002Fdebug (`model-audit-tieout`), source hierarchy (`financial-source-of-truth`), raw financial normalization (`financials-normalizer`), spreadsheet cleanup (`excel-data-cleaner`), valuation (`dcf-model-builder`, `comps-valuation`), public estimate update (`equity-model-update`), Credit Markets research, or memo\u002Fdeck polish.\n\nFor complex builds, split the work into source\u002Fevidence, historical normalization, operating drivers, balance sheet and cash, QA, and executive output workstreams. If sub-agents are unavailable, emulate those workstreams and reconcile them into one plan before running scripts.\n\n## When To Invoke Support\n\nLoad `shared\u002Fsupport-layer-routing-contract.md` when support services are needed. Use `financial-source-of-truth` for filings, releases, guidance, consensus, market data, and assumption labels; use `financials-normalizer` before building the plan from messy financials, KPI schedules, segment tables, share count, net debt, capital allocation, or provider exports; use `excel-data-cleaner` before relying on malformed workbook tables; use `model-audit-tieout` for workbook logic, external links, recalc\u002Fcache posture, and final tie-out. Support artifacts stay secondary to the formula workbook or owning dashboard\u002Freport.\n\n## Input Handling\n\n- Preferred input is a `plan.json` matching the schema.\n- No context: run `assets\u002Fplan_template.json` as illustrative, label placeholders, and cap status at `screen-grade`.\n- Partial context: preserve user facts, retain template defaults only when necessary, and label unsupported inputs.\n- Full financial package: normalize IS\u002FBS\u002FCF, reconcile the balance sheet, preserve source data, fill the plan, validate, run, then report checks and caveats.\n\n## Required Workflow\n\n1. Build or receive a valid `plan.json`.\n2. Validate with `python3 scripts\u002Fvalidate_plan.py path\u002Fto\u002Fplan.json`.\n3. Fix validation errors before running; do not silently default conclusion-changing assumptions.\n4. Default path: run `python3 scripts\u002Fbuild_banker_formula_workbook.py path\u002Fto\u002Fplan.json --output-dir output` and inspect `banker_formula_workbook_run_log.json`.\n5. Use `python3 scripts\u002Frun_pipeline.py path\u002Fto\u002Fplan.json` only for controlled computed values, smoke tests, explicit lightweight support exports, or when formula mode fails and the fallback is clearly labeled `deterministic_export`.\n6. Verify the relevant workbook, run log, manifest, and, in formula mode, `model_citations.json`.\n7. Read the run log; hard failures require `not-decision-ready`.\n8. Present the workbook as the hero artifact, with the `Cover` tab carrying the decision read-through, and link the normalized plan, run log, manifest, citation ledger, and optional support note as audit files.\n\nSmoke test:\n\n```bash\npython3 scripts\u002Fvalidate_plan.py assets\u002Fplan_template.json\npython3 scripts\u002Fbuild_banker_formula_workbook.py assets\u002Fplan_template.json --output-dir \u002Ftmp\u002Fpublic-equity-investing-3s-formula\npython3 scripts\u002Frun_pipeline.py assets\u002Fplan_template.json\n```\n\n## Formula Mode Guardrail\n\nLoad `references\u002Fbanker-formula-workbook-contract.md` before using formula mode. If the formula builder fails, the template is missing, required tabs\u002Fformulas\u002Fstyles are not present, external links appear, or `model_citations.json` is absent, do not describe any fallback artifact as a banker formula workbook.\n\n## Status Labels\n\nUse exactly: `decision-grade`, `senior-review-ready`, `screen-grade`, `not-decision-ready`, `blocked`. Use `blocked` only when no reasonable run can be produced before execution.\n\n## Senior Standard\n\nExplain what drives the forecast, what must be true, where cash is consumed, what breaks first in downside, whether EBITDA converts to cash, and which assumptions deserve diligence. Balance-sheet integrity, retained earnings, cash flow linkage, debt roll-forward, PP&E roll-forward, and working-capital roll-forward are non-negotiable.\n\n## Deferred Reference Router\n\nLoad `references\u002Freference-router.md` only when deeper schema, math, QA, integration, industry, or forecast judgment guidance is needed. The router preserves the detailed reference map without loading every reference during invocation.\n\n## Equity Valuation PM Standard\n\nLoad `shared\u002Fequity-valuation-pm-standard.md` and `shared\u002Fpm-judgment-heuristics.md` for substantial model, valuation, scenario, model-update, or audit work.\n\nThe output must state what the current stock price implies, the variant estimate path, whether upside is driven by fundamentals, multiple expansion, mix, capital return, sentiment, or event probability, what breaks first in downside, what changes target, rating, sizing, hedge, trim, exit, or watchlist status, and what evidence is missing.\n\nKeep equity valuation as the center of gravity. Debt is allowed only as an input to common-equity value through net debt, cost of debt, leverage, liquidity, refinancing risk, or downside equity impairment. Use Credit Markets for bond comps, loan comps, CDS, spread\u002Fyield relative value, covenant-package analysis, debt-security valuation, recovery waterfall, restructuring valuation, creditworthiness, private-credit \u002F public-credit instrument underwriting, or distressed claim valuation.\n",{"data":37,"body":38},{"name":4,"description":6},{"type":39,"children":40},"root",[41,49,56,63,94,100,105,137,143,164,169,175,462,468,528,533,539,580,586,631,637,742,747,826,832,851,857,903,909,914,920,932,938,957,962,967],{"type":42,"tag":43,"props":44,"children":45},"element","h1",{"id":4},[46],{"type":47,"value":48},"text","Three Statement Model Builder",{"type":42,"tag":50,"props":51,"children":53},"h2",{"id":52},"skill-configuration",[54],{"type":47,"value":55},"Skill Configuration",{"type":42,"tag":57,"props":58,"children":60},"h3",{"id":59},"common-skill-instructions",[61],{"type":47,"value":62},"Common Skill Instructions",{"type":42,"tag":64,"props":65,"children":66},"p",{},[67,69,76,78,84,86,92],{"type":47,"value":68},"MANDATORY: Before searching connectors, retrieving evidence, or drafting output, read and apply the shared runtime contract in ",{"type":42,"tag":70,"props":71,"children":73},"code",{"className":72},[],[74],{"type":47,"value":75},"..\u002Fpublic-equity-investing\u002FSKILL.md## Cross-Skill Runtime Contract",{"type":47,"value":77},". Then check the router skill map and ",{"type":42,"tag":70,"props":79,"children":81},{"className":80},[],[82],{"type":47,"value":83},"..\u002F..\u002Fshared\u002Fplugin-routing-playbook.md",{"type":47,"value":85}," for adjacent skills that should be sequenced with this workflow. Do not run user-context setup or inspection during ordinary workflow work; route only explicit saved-context, source-setup, onboarding, or automation-setup requests to ",{"type":42,"tag":70,"props":87,"children":89},{"className":88},[],[90],{"type":47,"value":91},"..\u002Fuser-context\u002FSKILL.md",{"type":47,"value":93},".",{"type":42,"tag":50,"props":95,"children":97},{"id":96},"relevant-dependency-categories",[98],{"type":47,"value":99},"Relevant Dependency Categories",{"type":42,"tag":64,"props":101,"children":102},{},[103],{"type":47,"value":104},"These are the source categories most likely to matter for this workflow. Use the router contract to resolve only the categories the task actually needs, prefer user-named sources first, and state any material source limitation.",{"type":42,"tag":106,"props":107,"children":108},"ul",{},[109,119,128],{"type":42,"tag":110,"props":111,"children":112},"li",{},[113],{"type":42,"tag":70,"props":114,"children":116},{"className":115},[],[117],{"type":47,"value":118},"Company Filings & IR",{"type":42,"tag":110,"props":120,"children":121},{},[122],{"type":42,"tag":70,"props":123,"children":125},{"className":124},[],[126],{"type":47,"value":127},"Portfolio Models & Trackers",{"type":42,"tag":110,"props":129,"children":130},{},[131],{"type":42,"tag":70,"props":132,"children":134},{"className":133},[],[135],{"type":47,"value":136},"Market Data & Estimates",{"type":42,"tag":50,"props":138,"children":140},{"id":139},"deliverable-intake",[141],{"type":47,"value":142},"Deliverable Intake",{"type":42,"tag":64,"props":144,"children":145},{},[146,148,154,156,162],{"type":47,"value":147},"Before source gathering or analysis for a new substantive hero deliverable, load ",{"type":42,"tag":70,"props":149,"children":151},{"className":150},[],[152],{"type":47,"value":153},"..\u002F..\u002Fshared\u002Fdeliverable-intake-policy.md",{"type":47,"value":155}," and use its adaptive ",{"type":42,"tag":70,"props":157,"children":159},{"className":158},[],[160],{"type":47,"value":161},"request_user_input",{"type":47,"value":163}," preflight for materially unresolved format, depth, audience\u002Fuse, or focus choices. Reuse resolved preferences in downstream steps; when acting only as input to an owning workflow, do not re-prompt.",{"type":42,"tag":64,"props":165,"children":166},{},[167],{"type":47,"value":168},"Own formula-first public-company operating model builds: integrated IS\u002FBS\u002FCF, working capital, PP&E and D&A, retained earnings, debt, revolver-style draws, cash sweep, equity-relevant liquidity\u002Fheadroom metrics, scenarios, sensitivities, machine checks, and senior-review reporting.",{"type":42,"tag":50,"props":170,"children":172},{"id":171},"hard-contract",[173],{"type":47,"value":174},"Hard Contract",{"type":42,"tag":106,"props":176,"children":177},{},[178,191,219,277,311,329,354,367,443],{"type":42,"tag":110,"props":179,"children":180},{},[181,183,189],{"type":47,"value":182},"Default model-build artifact level is ",{"type":42,"tag":70,"props":184,"children":186},{"className":185},[],[187],{"type":47,"value":188},"banker_formula_workbook",{"type":47,"value":190},"; use the formula workbook path for normal public-equity 3-statement build, refresh, forecast, and operating-model-package requests.",{"type":42,"tag":110,"props":192,"children":193},{},[194,196,202,204,209,211,217],{"type":47,"value":195},"Formula mode is executed through ",{"type":42,"tag":70,"props":197,"children":199},{"className":198},[],[200],{"type":47,"value":201},"scripts\u002Fbuild_banker_formula_workbook.py",{"type":47,"value":203}," and must be labeled ",{"type":42,"tag":70,"props":205,"children":207},{"className":206},[],[208],{"type":47,"value":188},{"type":47,"value":210}," only when its run log, workbook inspection, and ",{"type":42,"tag":70,"props":212,"children":214},{"className":213},[],[215],{"type":47,"value":216},"model_citations.json",{"type":47,"value":218}," prove the formula builder ran successfully.",{"type":42,"tag":110,"props":220,"children":221},{},[222,224,230,232,238,239,245,246,252,254,260,262,268,270,276],{"type":47,"value":223},"Deterministic scripts remain available for controlled computed values, smoke tests, or explicit lightweight support exports. They produce ",{"type":42,"tag":70,"props":225,"children":227},{"className":226},[],[228],{"type":47,"value":229},"output\u002Fmodel.xlsx",{"type":47,"value":231},", ",{"type":42,"tag":70,"props":233,"children":235},{"className":234},[],[236],{"type":47,"value":237},"output\u002Fplan.json",{"type":47,"value":231},{"type":42,"tag":70,"props":240,"children":242},{"className":241},[],[243],{"type":47,"value":244},"output\u002Frun_log.json",{"type":47,"value":231},{"type":42,"tag":70,"props":247,"children":249},{"className":248},[],[250],{"type":47,"value":251},"output\u002Fmanifest.json",{"type":47,"value":253},", and optionally ",{"type":42,"tag":70,"props":255,"children":257},{"className":256},[],[258],{"type":47,"value":259},"output\u002Fsupport_note.md",{"type":47,"value":261},". Legacy ",{"type":42,"tag":70,"props":263,"children":265},{"className":264},[],[266],{"type":47,"value":267},"output\u002Freport.md",{"type":47,"value":269}," is written only with ",{"type":42,"tag":70,"props":271,"children":273},{"className":272},[],[274],{"type":47,"value":275},"--write-report-md",{"type":47,"value":93},{"type":42,"tag":110,"props":278,"children":279},{},[280,282,288,289,295,296,301,303,309],{"type":47,"value":281},"Formula scripts produce ",{"type":42,"tag":70,"props":283,"children":285},{"className":284},[],[286],{"type":47,"value":287},"banker_formula_workbook.xlsx",{"type":47,"value":231},{"type":42,"tag":70,"props":290,"children":292},{"className":291},[],[293],{"type":47,"value":294},"banker_formula_workbook_run_log.json",{"type":47,"value":231},{"type":42,"tag":70,"props":297,"children":299},{"className":298},[],[300],{"type":47,"value":216},{"type":47,"value":302},", and ",{"type":42,"tag":70,"props":304,"children":306},{"className":305},[],[307],{"type":47,"value":308},"manifest.json",{"type":47,"value":310}," in the selected output directory. The workbook is the hero deliverable; citation JSON, run logs, and manifests are support artifacts.",{"type":42,"tag":110,"props":312,"children":313},{},[314,319,321,327],{"type":42,"tag":70,"props":315,"children":317},{"className":316},[],[318],{"type":47,"value":229},{"type":47,"value":320}," must start with a ",{"type":42,"tag":70,"props":322,"children":324},{"className":323},[],[325],{"type":47,"value":326},"Cover",{"type":47,"value":328}," tab that functions as a dashboard: model status, scenario outputs, revenue\u002FEBITDA\u002FFCF\u002Fcash, liquidity trough, leverage\u002Fheadroom, source posture, warnings\u002Fhard failures, workbook map.",{"type":42,"tag":110,"props":330,"children":331},{},[332,338,340,345,347,353],{"type":42,"tag":70,"props":333,"children":335},{"className":334},[],[336],{"type":47,"value":337},"run_log.json",{"type":47,"value":339}," and ",{"type":42,"tag":70,"props":341,"children":343},{"className":342},[],[344],{"type":47,"value":308},{"type":47,"value":346}," are required reliability artifacts; hard failures force ",{"type":42,"tag":70,"props":348,"children":350},{"className":349},[],[351],{"type":47,"value":352},"not-decision-ready",{"type":47,"value":93},{"type":42,"tag":110,"props":355,"children":356},{},[357,359,365],{"type":47,"value":358},"Never delete, overwrite, or mutate source data unless explicitly requested. Preserve raw tabs\u002Ffiles and write new outputs under ",{"type":42,"tag":70,"props":360,"children":362},{"className":361},[],[363],{"type":47,"value":364},"output\u002F",{"type":47,"value":366}," or a clearly named copy.",{"type":42,"tag":110,"props":368,"children":369},{},[370,372,378,379,385,386,392,393,399,400,406,407,413,414,420,421,427,428,434,436,442],{"type":47,"value":371},"Material inputs must be evidence-labeled: ",{"type":42,"tag":70,"props":373,"children":375},{"className":374},[],[376],{"type":47,"value":377},"source_reported",{"type":47,"value":231},{"type":42,"tag":70,"props":380,"children":382},{"className":381},[],[383],{"type":47,"value":384},"company_provided",{"type":47,"value":231},{"type":42,"tag":70,"props":387,"children":389},{"className":388},[],[390],{"type":47,"value":391},"connector_sourced",{"type":47,"value":231},{"type":42,"tag":70,"props":394,"children":396},{"className":395},[],[397],{"type":47,"value":398},"public_filing",{"type":47,"value":231},{"type":42,"tag":70,"props":401,"children":403},{"className":402},[],[404],{"type":47,"value":405},"web_verified",{"type":47,"value":231},{"type":42,"tag":70,"props":408,"children":410},{"className":409},[],[411],{"type":47,"value":412},"management_guidance",{"type":47,"value":231},{"type":42,"tag":70,"props":415,"children":417},{"className":416},[],[418],{"type":47,"value":419},"analyst_estimate",{"type":47,"value":231},{"type":42,"tag":70,"props":422,"children":424},{"className":423},[],[425],{"type":47,"value":426},"benchmark",{"type":47,"value":231},{"type":42,"tag":70,"props":429,"children":431},{"className":430},[],[432],{"type":47,"value":433},"assumption",{"type":47,"value":435},", or ",{"type":42,"tag":70,"props":437,"children":439},{"className":438},[],[440],{"type":47,"value":441},"placeholder",{"type":47,"value":93},{"type":42,"tag":110,"props":444,"children":445},{},[446,448,454,456,461],{"type":47,"value":447},"If placeholders, stale data, unsupported assumptions, or failed tie-outs remain active, mark the model no higher than ",{"type":42,"tag":70,"props":449,"children":451},{"className":450},[],[452],{"type":47,"value":453},"screen-grade",{"type":47,"value":455},"; hard failures mean ",{"type":42,"tag":70,"props":457,"children":459},{"className":458},[],[460],{"type":47,"value":352},{"type":47,"value":93},{"type":42,"tag":50,"props":463,"children":465},{"id":464},"routing",[466],{"type":47,"value":467},"Routing",{"type":42,"tag":64,"props":469,"children":470},{},[471,473,479,481,487,489,495,497,503,505,511,512,518,520,526],{"type":47,"value":472},"Use this skill when the deliverable is a 3-statement build, refresh, rerun, operating model package, or integrated forecast rebuild. Route away when the primary ask is workbook audit\u002Fdebug (",{"type":42,"tag":70,"props":474,"children":476},{"className":475},[],[477],{"type":47,"value":478},"model-audit-tieout",{"type":47,"value":480},"), source hierarchy (",{"type":42,"tag":70,"props":482,"children":484},{"className":483},[],[485],{"type":47,"value":486},"financial-source-of-truth",{"type":47,"value":488},"), raw financial normalization (",{"type":42,"tag":70,"props":490,"children":492},{"className":491},[],[493],{"type":47,"value":494},"financials-normalizer",{"type":47,"value":496},"), spreadsheet cleanup (",{"type":42,"tag":70,"props":498,"children":500},{"className":499},[],[501],{"type":47,"value":502},"excel-data-cleaner",{"type":47,"value":504},"), valuation (",{"type":42,"tag":70,"props":506,"children":508},{"className":507},[],[509],{"type":47,"value":510},"dcf-model-builder",{"type":47,"value":231},{"type":42,"tag":70,"props":513,"children":515},{"className":514},[],[516],{"type":47,"value":517},"comps-valuation",{"type":47,"value":519},"), public estimate update (",{"type":42,"tag":70,"props":521,"children":523},{"className":522},[],[524],{"type":47,"value":525},"equity-model-update",{"type":47,"value":527},"), Credit Markets research, or memo\u002Fdeck polish.",{"type":42,"tag":64,"props":529,"children":530},{},[531],{"type":47,"value":532},"For complex builds, split the work into source\u002Fevidence, historical normalization, operating drivers, balance sheet and cash, QA, and executive output workstreams. If sub-agents are unavailable, emulate those workstreams and reconcile them into one plan before running scripts.",{"type":42,"tag":50,"props":534,"children":536},{"id":535},"when-to-invoke-support",[537],{"type":47,"value":538},"When To Invoke Support",{"type":42,"tag":64,"props":540,"children":541},{},[542,544,550,552,557,559,564,566,571,573,578],{"type":47,"value":543},"Load ",{"type":42,"tag":70,"props":545,"children":547},{"className":546},[],[548],{"type":47,"value":549},"shared\u002Fsupport-layer-routing-contract.md",{"type":47,"value":551}," when support services are needed. Use ",{"type":42,"tag":70,"props":553,"children":555},{"className":554},[],[556],{"type":47,"value":486},{"type":47,"value":558}," for filings, releases, guidance, consensus, market data, and assumption labels; use ",{"type":42,"tag":70,"props":560,"children":562},{"className":561},[],[563],{"type":47,"value":494},{"type":47,"value":565}," before building the plan from messy financials, KPI schedules, segment tables, share count, net debt, capital allocation, or provider exports; use ",{"type":42,"tag":70,"props":567,"children":569},{"className":568},[],[570],{"type":47,"value":502},{"type":47,"value":572}," before relying on malformed workbook tables; use ",{"type":42,"tag":70,"props":574,"children":576},{"className":575},[],[577],{"type":47,"value":478},{"type":47,"value":579}," for workbook logic, external links, recalc\u002Fcache posture, and final tie-out. Support artifacts stay secondary to the formula workbook or owning dashboard\u002Freport.",{"type":42,"tag":50,"props":581,"children":583},{"id":582},"input-handling",[584],{"type":47,"value":585},"Input Handling",{"type":42,"tag":106,"props":587,"children":588},{},[589,602,621,626],{"type":42,"tag":110,"props":590,"children":591},{},[592,594,600],{"type":47,"value":593},"Preferred input is a ",{"type":42,"tag":70,"props":595,"children":597},{"className":596},[],[598],{"type":47,"value":599},"plan.json",{"type":47,"value":601}," matching the schema.",{"type":42,"tag":110,"props":603,"children":604},{},[605,607,613,615,620],{"type":47,"value":606},"No context: run ",{"type":42,"tag":70,"props":608,"children":610},{"className":609},[],[611],{"type":47,"value":612},"assets\u002Fplan_template.json",{"type":47,"value":614}," as illustrative, label placeholders, and cap status at ",{"type":42,"tag":70,"props":616,"children":618},{"className":617},[],[619],{"type":47,"value":453},{"type":47,"value":93},{"type":42,"tag":110,"props":622,"children":623},{},[624],{"type":47,"value":625},"Partial context: preserve user facts, retain template defaults only when necessary, and label unsupported inputs.",{"type":42,"tag":110,"props":627,"children":628},{},[629],{"type":47,"value":630},"Full financial package: normalize IS\u002FBS\u002FCF, reconcile the balance sheet, preserve source data, fill the plan, validate, run, then report checks and caveats.",{"type":42,"tag":50,"props":632,"children":634},{"id":633},"required-workflow",[635],{"type":47,"value":636},"Required Workflow",{"type":42,"tag":638,"props":639,"children":640},"ol",{},[641,652,664,669,688,708,719,730],{"type":42,"tag":110,"props":642,"children":643},{},[644,646,651],{"type":47,"value":645},"Build or receive a valid ",{"type":42,"tag":70,"props":647,"children":649},{"className":648},[],[650],{"type":47,"value":599},{"type":47,"value":93},{"type":42,"tag":110,"props":653,"children":654},{},[655,657,663],{"type":47,"value":656},"Validate with ",{"type":42,"tag":70,"props":658,"children":660},{"className":659},[],[661],{"type":47,"value":662},"python3 scripts\u002Fvalidate_plan.py path\u002Fto\u002Fplan.json",{"type":47,"value":93},{"type":42,"tag":110,"props":665,"children":666},{},[667],{"type":47,"value":668},"Fix validation errors before running; do not silently default conclusion-changing assumptions.",{"type":42,"tag":110,"props":670,"children":671},{},[672,674,680,682,687],{"type":47,"value":673},"Default path: run ",{"type":42,"tag":70,"props":675,"children":677},{"className":676},[],[678],{"type":47,"value":679},"python3 scripts\u002Fbuild_banker_formula_workbook.py path\u002Fto\u002Fplan.json --output-dir output",{"type":47,"value":681}," and inspect ",{"type":42,"tag":70,"props":683,"children":685},{"className":684},[],[686],{"type":47,"value":294},{"type":47,"value":93},{"type":42,"tag":110,"props":689,"children":690},{},[691,693,699,701,707],{"type":47,"value":692},"Use ",{"type":42,"tag":70,"props":694,"children":696},{"className":695},[],[697],{"type":47,"value":698},"python3 scripts\u002Frun_pipeline.py path\u002Fto\u002Fplan.json",{"type":47,"value":700}," only for controlled computed values, smoke tests, explicit lightweight support exports, or when formula mode fails and the fallback is clearly labeled ",{"type":42,"tag":70,"props":702,"children":704},{"className":703},[],[705],{"type":47,"value":706},"deterministic_export",{"type":47,"value":93},{"type":42,"tag":110,"props":709,"children":710},{},[711,713,718],{"type":47,"value":712},"Verify the relevant workbook, run log, manifest, and, in formula mode, ",{"type":42,"tag":70,"props":714,"children":716},{"className":715},[],[717],{"type":47,"value":216},{"type":47,"value":93},{"type":42,"tag":110,"props":720,"children":721},{},[722,724,729],{"type":47,"value":723},"Read the run log; hard failures require ",{"type":42,"tag":70,"props":725,"children":727},{"className":726},[],[728],{"type":47,"value":352},{"type":47,"value":93},{"type":42,"tag":110,"props":731,"children":732},{},[733,735,740],{"type":47,"value":734},"Present the workbook as the hero artifact, with the ",{"type":42,"tag":70,"props":736,"children":738},{"className":737},[],[739],{"type":47,"value":326},{"type":47,"value":741}," tab carrying the decision read-through, and link the normalized plan, run log, manifest, citation ledger, and optional support note as audit files.",{"type":42,"tag":64,"props":743,"children":744},{},[745],{"type":47,"value":746},"Smoke test:",{"type":42,"tag":748,"props":749,"children":754},"pre",{"className":750,"code":751,"language":752,"meta":753,"style":753},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","python3 scripts\u002Fvalidate_plan.py assets\u002Fplan_template.json\npython3 scripts\u002Fbuild_banker_formula_workbook.py assets\u002Fplan_template.json --output-dir \u002Ftmp\u002Fpublic-equity-investing-3s-formula\npython3 scripts\u002Frun_pipeline.py assets\u002Fplan_template.json\n","bash","",[755],{"type":42,"tag":70,"props":756,"children":757},{"__ignoreMap":753},[758,781,809],{"type":42,"tag":759,"props":760,"children":763},"span",{"class":761,"line":762},"line",1,[764,770,776],{"type":42,"tag":759,"props":765,"children":767},{"style":766},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[768],{"type":47,"value":769},"python3",{"type":42,"tag":759,"props":771,"children":773},{"style":772},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[774],{"type":47,"value":775}," scripts\u002Fvalidate_plan.py",{"type":42,"tag":759,"props":777,"children":778},{"style":772},[779],{"type":47,"value":780}," assets\u002Fplan_template.json\n",{"type":42,"tag":759,"props":782,"children":784},{"class":761,"line":783},2,[785,789,794,799,804],{"type":42,"tag":759,"props":786,"children":787},{"style":766},[788],{"type":47,"value":769},{"type":42,"tag":759,"props":790,"children":791},{"style":772},[792],{"type":47,"value":793}," scripts\u002Fbuild_banker_formula_workbook.py",{"type":42,"tag":759,"props":795,"children":796},{"style":772},[797],{"type":47,"value":798}," assets\u002Fplan_template.json",{"type":42,"tag":759,"props":800,"children":801},{"style":772},[802],{"type":47,"value":803}," --output-dir",{"type":42,"tag":759,"props":805,"children":806},{"style":772},[807],{"type":47,"value":808}," \u002Ftmp\u002Fpublic-equity-investing-3s-formula\n",{"type":42,"tag":759,"props":810,"children":812},{"class":761,"line":811},3,[813,817,822],{"type":42,"tag":759,"props":814,"children":815},{"style":766},[816],{"type":47,"value":769},{"type":42,"tag":759,"props":818,"children":819},{"style":772},[820],{"type":47,"value":821}," scripts\u002Frun_pipeline.py",{"type":42,"tag":759,"props":823,"children":824},{"style":772},[825],{"type":47,"value":780},{"type":42,"tag":50,"props":827,"children":829},{"id":828},"formula-mode-guardrail",[830],{"type":47,"value":831},"Formula Mode Guardrail",{"type":42,"tag":64,"props":833,"children":834},{},[835,836,842,844,849],{"type":47,"value":543},{"type":42,"tag":70,"props":837,"children":839},{"className":838},[],[840],{"type":47,"value":841},"references\u002Fbanker-formula-workbook-contract.md",{"type":47,"value":843}," before using formula mode. If the formula builder fails, the template is missing, required tabs\u002Fformulas\u002Fstyles are not present, external links appear, or ",{"type":42,"tag":70,"props":845,"children":847},{"className":846},[],[848],{"type":47,"value":216},{"type":47,"value":850}," is absent, do not describe any fallback artifact as a banker formula workbook.",{"type":42,"tag":50,"props":852,"children":854},{"id":853},"status-labels",[855],{"type":47,"value":856},"Status Labels",{"type":42,"tag":64,"props":858,"children":859},{},[860,862,868,869,875,876,881,882,887,888,894,896,901],{"type":47,"value":861},"Use exactly: ",{"type":42,"tag":70,"props":863,"children":865},{"className":864},[],[866],{"type":47,"value":867},"decision-grade",{"type":47,"value":231},{"type":42,"tag":70,"props":870,"children":872},{"className":871},[],[873],{"type":47,"value":874},"senior-review-ready",{"type":47,"value":231},{"type":42,"tag":70,"props":877,"children":879},{"className":878},[],[880],{"type":47,"value":453},{"type":47,"value":231},{"type":42,"tag":70,"props":883,"children":885},{"className":884},[],[886],{"type":47,"value":352},{"type":47,"value":231},{"type":42,"tag":70,"props":889,"children":891},{"className":890},[],[892],{"type":47,"value":893},"blocked",{"type":47,"value":895},". Use ",{"type":42,"tag":70,"props":897,"children":899},{"className":898},[],[900],{"type":47,"value":893},{"type":47,"value":902}," only when no reasonable run can be produced before execution.",{"type":42,"tag":50,"props":904,"children":906},{"id":905},"senior-standard",[907],{"type":47,"value":908},"Senior Standard",{"type":42,"tag":64,"props":910,"children":911},{},[912],{"type":47,"value":913},"Explain what drives the forecast, what must be true, where cash is consumed, what breaks first in downside, whether EBITDA converts to cash, and which assumptions deserve diligence. Balance-sheet integrity, retained earnings, cash flow linkage, debt roll-forward, PP&E roll-forward, and working-capital roll-forward are non-negotiable.",{"type":42,"tag":50,"props":915,"children":917},{"id":916},"deferred-reference-router",[918],{"type":47,"value":919},"Deferred Reference Router",{"type":42,"tag":64,"props":921,"children":922},{},[923,924,930],{"type":47,"value":543},{"type":42,"tag":70,"props":925,"children":927},{"className":926},[],[928],{"type":47,"value":929},"references\u002Freference-router.md",{"type":47,"value":931}," only when deeper schema, math, QA, integration, industry, or forecast judgment guidance is needed. The router preserves the detailed reference map without loading every reference during invocation.",{"type":42,"tag":50,"props":933,"children":935},{"id":934},"equity-valuation-pm-standard",[936],{"type":47,"value":937},"Equity Valuation PM Standard",{"type":42,"tag":64,"props":939,"children":940},{},[941,942,948,949,955],{"type":47,"value":543},{"type":42,"tag":70,"props":943,"children":945},{"className":944},[],[946],{"type":47,"value":947},"shared\u002Fequity-valuation-pm-standard.md",{"type":47,"value":339},{"type":42,"tag":70,"props":950,"children":952},{"className":951},[],[953],{"type":47,"value":954},"shared\u002Fpm-judgment-heuristics.md",{"type":47,"value":956}," for substantial model, valuation, scenario, model-update, or audit work.",{"type":42,"tag":64,"props":958,"children":959},{},[960],{"type":47,"value":961},"The output must state what the current stock price implies, the variant estimate path, whether upside is driven by fundamentals, multiple expansion, mix, capital return, sentiment, or event probability, what breaks first in downside, what changes target, rating, sizing, hedge, trim, exit, or watchlist status, and what evidence is missing.",{"type":42,"tag":64,"props":963,"children":964},{},[965],{"type":47,"value":966},"Keep equity valuation as the center of gravity. Debt is allowed only as an input to common-equity value through net debt, cost of debt, leverage, liquidity, refinancing risk, or downside equity impairment. Use Credit Markets for bond comps, loan comps, CDS, spread\u002Fyield relative value, covenant-package analysis, debt-security valuation, recovery waterfall, restructuring valuation, creditworthiness, private-credit \u002F public-credit instrument underwriting, or distressed claim valuation.",{"type":42,"tag":968,"props":969,"children":970},"style",{},[971],{"type":47,"value":972},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":974,"total":1074},[975,994,1010,1022,1037,1050,1062],{"slug":976,"name":976,"fn":977,"description":978,"org":979,"tags":980,"stars":25,"repoUrl":26,"updatedAt":993},"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},[981,984,987,990],{"name":982,"slug":983,"type":15},"Accessibility","accessibility",{"name":985,"slug":986,"type":15},"Charts","charts",{"name":988,"slug":989,"type":15},"Data Visualization","data-visualization",{"name":991,"slug":992,"type":15},"Design","design","2026-06-30T19:00:57.102",{"slug":995,"name":995,"fn":996,"description":997,"org":998,"tags":999,"stars":25,"repoUrl":26,"updatedAt":1009},"adobe-batch-edit-photos","apply consistent photo adjustments","Apply consistent photo adjustments across a set of images so they look like they were edited together. Use this skill whenever the user says \"make my photos look cohesive\", \"give all these the same style\", \"apply a warm and golden feel to all of these\", \"make this cinematic\", \"match the look across my photos\", \"edit all my travel photos the same way\", \"batch edit these\", \"make these consistent\", \"fix my phone photos\", or uploads a folder of photos and wants a unified, polished result. Also triggers for requests like \"apply a preset to all of these\", \"make these look professional\", or \"they were shot in mixed lighting — can you fix them all\". Outputs direct final image URLs plus an in-chat preview grid and optional Firefly Board link. Access: 🔐 Signed-In required | Gen AI: ❌\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1000,1003,1006],{"name":1001,"slug":1002,"type":15},"Creative","creative",{"name":1004,"slug":1005,"type":15},"Editing","editing",{"name":1007,"slug":1008,"type":15},"Imaging","imaging","2026-08-28T15:09:11.185865",{"slug":1011,"name":1011,"fn":1012,"description":1013,"org":1014,"tags":1015,"stars":25,"repoUrl":26,"updatedAt":1021},"adobe-create-mockups","create product and scene mockups","Use when a user wants to see their logo, design, or sketch on a product or scene mockup — mugs, t-shirts, business cards, hats, phone screens, posters, billboards, or similar. Triggers on \"create mockups\", \"show my logo on products\", or any logo upload with a request to visualize it on items. Access: 🔐 Signed-In required | Gen AI: ✅ Adobe Firefly via `image_generate` used for design creation, sketch polishing, and mockup scene generation\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1016,1017,1018],{"name":1001,"slug":1002,"type":15},{"name":991,"slug":992,"type":15},{"name":1019,"slug":1020,"type":15},"Graphics","graphics","2026-08-28T15:09:07.42507",{"slug":1023,"name":1023,"fn":1024,"description":1025,"org":1026,"tags":1027,"stars":25,"repoUrl":26,"updatedAt":1036},"adobe-create-social-variations","export platform-ready social media assets","Resize, crop, or export any image or video into platform-ready social media assets using Adobe Creative Cloud tools. Use this skill when a user wants to prepare a photo, image, or video for one or more social platforms — Instagram, TikTok, LinkedIn, Facebook, YouTube, Snapchat, Pinterest, Threads, or X\u002FTwitter. Triggers on: \"prepare my image for Instagram\", \"resize for TikTok\", \"get this ready to post\", \"make versions for all platforms\", \"social media sizes\", \"crop for stories\", \"export for LinkedIn\", \"resize my video for social\", \"make social media assets\", or any request to adapt a photo or video for specific platforms. Handles subject-aware cropping, AI canvas expansion, test previews before full runs, and same-ratio video resizing.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1028,1029,1030,1033],{"name":1001,"slug":1002,"type":15},{"name":1019,"slug":1020,"type":15},{"name":1031,"slug":1032,"type":15},"Marketing","marketing",{"name":1034,"slug":1035,"type":15},"Social Media","social-media","2026-08-28T15:10:07.282096",{"slug":1038,"name":1038,"fn":1039,"description":1040,"org":1041,"tags":1042,"stars":25,"repoUrl":26,"updatedAt":1049},"adobe-design-from-template","create visual designs from templates","Create any visual design using Adobe Express templates — flyers, posters, social media posts (Instagram, Facebook, LinkedIn), business cards, invitations, greeting cards, resumes, cover letters, brochures, newsletters, certificates, presentations, YouTube thumbnails, email headers, logos, menus, and labels. Use this skill whenever the user wants to make, design, or build any visual — even if they just say \"make me a flyer\", \"design a poster\", \"I need something for Instagram\", \"create an event invite\", or \"make a business card\". Also handles browsing templates, editing text, replacing images, changing backgrounds, animating, and exporting designs. Access: 🔐 Signed-In required | Gen AI: ❌ by default — image replacement only where the surface permits generative AI (e.g. Codex); none on Claude\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1043,1044,1045,1046],{"name":1001,"slug":1002,"type":15},{"name":991,"slug":992,"type":15},{"name":1019,"slug":1020,"type":15},{"name":1047,"slug":1048,"type":15},"Templates","templates","2026-08-28T15:10:03.050113",{"slug":1051,"name":1051,"fn":1052,"description":1053,"org":1054,"tags":1055,"stars":25,"repoUrl":26,"updatedAt":1061},"adobe-edit-quick-cut","create video sizzle reels","Create a punchy sizzle reel from a video using Adobe Quick Cut. Use this skill whenever a user wants to cut, trim, or shorten a video into highlights — including phrases like \"make a sizzle reel\", \"make a highlight reel\", \"quick cut this\", \"cut the best parts\", \"shorten this video\", \"make a highlight clip\", \"summarize this video visually\", or any request to produce a shorter edited version of a video. Use this skill for Quick Cut requests before suggesting manual editing in Premiere. Requires the user to upload a video file.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1056,1057,1058],{"name":1001,"slug":1002,"type":15},{"name":1004,"slug":1005,"type":15},{"name":1059,"slug":1060,"type":15},"Video","video","2026-08-28T15:09:07.765245",{"slug":1063,"name":1063,"fn":1064,"description":1065,"org":1066,"tags":1067,"stars":25,"repoUrl":26,"updatedAt":1073},"adobe-retouch-portraits","batch retouch portrait photos","Bulk-retouch a folder of portrait photos using Adobe tools — designed for wedding photographers and event photographers who need fast, walk-away batch processing. Use this skill when the user says \"retouch my photos\", \"batch process these portraits\", \"process my wedding photos\", \"clean up this folder of images\", \"run my headshots through Adobe\", or uploads\u002Fselects a folder of photos and wants them polished and ready to review. Automatically applies auto-straighten, auto-tone, and auto-light to every image. Outputs a preview grid and download folder. Access: 🔐 Signed-In required | Gen AI: ❌ by default — optional background-only cleanup only where the surface permits generative AI (e.g. Codex); none on Claude\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1068,1069,1070],{"name":1001,"slug":1002,"type":15},{"name":1007,"slug":1008,"type":15},{"name":1071,"slug":1072,"type":15},"Photography","photography","2026-08-28T15:09:10.386974",499,{"items":1076,"total":1277},[1077,1098,1121,1138,1154,1173,1192,1206,1222,1236,1248,1261],{"slug":1078,"name":1078,"fn":1079,"description":1080,"org":1081,"tags":1082,"stars":1095,"repoUrl":1096,"updatedAt":1097},"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},[1083,1086,1089,1092],{"name":1084,"slug":1085,"type":15},"Documents","documents",{"name":1087,"slug":1088,"type":15},"Healthcare","healthcare",{"name":1090,"slug":1091,"type":15},"Insurance","insurance",{"name":1093,"slug":1094,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-08-02T05:48:07.395855",{"slug":1099,"name":1099,"fn":1100,"description":1101,"org":1102,"tags":1103,"stars":1118,"repoUrl":1119,"updatedAt":1120},"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},[1104,1107,1109,1112,1115],{"name":1105,"slug":1106,"type":15},".NET","dotnet",{"name":1108,"slug":1099,"type":15},"ASP.NET Core",{"name":1110,"slug":1111,"type":15},"Blazor","blazor",{"name":1113,"slug":1114,"type":15},"C#","csharp",{"name":1116,"slug":1117,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":1122,"name":1122,"fn":1123,"description":1124,"org":1125,"tags":1126,"stars":1118,"repoUrl":1119,"updatedAt":1137},"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},[1127,1130,1133,1136],{"name":1128,"slug":1129,"type":15},"Apps SDK","apps-sdk",{"name":1131,"slug":1132,"type":15},"ChatGPT","chatgpt",{"name":1134,"slug":1135,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":1139,"name":1139,"fn":1140,"description":1141,"org":1142,"tags":1143,"stars":1118,"repoUrl":1119,"updatedAt":1153},"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},[1144,1147,1150],{"name":1145,"slug":1146,"type":15},"API Development","api-development",{"name":1148,"slug":1149,"type":15},"CLI","cli",{"name":1151,"slug":1152,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":1155,"name":1155,"fn":1156,"description":1157,"org":1158,"tags":1159,"stars":1118,"repoUrl":1119,"updatedAt":1172},"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},[1160,1163,1166,1169],{"name":1161,"slug":1162,"type":15},"Cloudflare","cloudflare",{"name":1164,"slug":1165,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":1167,"slug":1168,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":1170,"slug":1171,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":1174,"name":1174,"fn":1175,"description":1176,"org":1177,"tags":1178,"stars":1118,"repoUrl":1119,"updatedAt":1191},"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},[1179,1182,1185,1188],{"name":1180,"slug":1181,"type":15},"Productivity","productivity",{"name":1183,"slug":1184,"type":15},"Project Management","project-management",{"name":1186,"slug":1187,"type":15},"Strategy","strategy",{"name":1189,"slug":1190,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":1193,"name":1193,"fn":1194,"description":1195,"org":1196,"tags":1197,"stars":1118,"repoUrl":1119,"updatedAt":1205},"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},[1198,1199,1201,1204],{"name":991,"slug":992,"type":15},{"name":1200,"slug":1193,"type":15},"Figma",{"name":1202,"slug":1203,"type":15},"Frontend","frontend",{"name":1134,"slug":1135,"type":15},"2026-04-12T05:06:47.939943",{"slug":1207,"name":1207,"fn":1208,"description":1209,"org":1210,"tags":1211,"stars":1118,"repoUrl":1119,"updatedAt":1221},"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},[1212,1213,1216,1217,1218],{"name":991,"slug":992,"type":15},{"name":1214,"slug":1215,"type":15},"Design System","design-system",{"name":1200,"slug":1193,"type":15},{"name":1202,"slug":1203,"type":15},{"name":1219,"slug":1220,"type":15},"UI Components","ui-components","2026-05-10T05:59:52.971881",{"slug":1223,"name":1223,"fn":1224,"description":1225,"org":1226,"tags":1227,"stars":1118,"repoUrl":1119,"updatedAt":1235},"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},[1228,1229,1230,1233,1234],{"name":991,"slug":992,"type":15},{"name":1214,"slug":1215,"type":15},{"name":1231,"slug":1232,"type":15},"Documentation","documentation",{"name":1200,"slug":1193,"type":15},{"name":1202,"slug":1203,"type":15},"2026-05-16T06:07:47.821474",{"slug":1237,"name":1237,"fn":1238,"description":1239,"org":1240,"tags":1241,"stars":1118,"repoUrl":1119,"updatedAt":1247},"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},[1242,1243,1244,1245,1246],{"name":991,"slug":992,"type":15},{"name":1200,"slug":1193,"type":15},{"name":1202,"slug":1203,"type":15},{"name":1219,"slug":1220,"type":15},{"name":1116,"slug":1117,"type":15},"2026-05-16T06:07:40.583615",{"slug":1249,"name":1249,"fn":1250,"description":1251,"org":1252,"tags":1253,"stars":1118,"repoUrl":1119,"updatedAt":1260},"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},[1254,1257,1258,1259],{"name":1255,"slug":1256,"type":15},"Animation","animation",{"name":1151,"slug":1152,"type":15},{"name":1001,"slug":1002,"type":15},{"name":991,"slug":992,"type":15},"2026-05-02T05:31:48.48485",{"slug":1262,"name":1262,"fn":1263,"description":1264,"org":1265,"tags":1266,"stars":1118,"repoUrl":1119,"updatedAt":1276},"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},[1267,1268,1269,1272,1275],{"name":1001,"slug":1002,"type":15},{"name":991,"slug":992,"type":15},{"name":1270,"slug":1271,"type":15},"Image Generation","image-generation",{"name":1273,"slug":1274,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",578]