[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-financials-normalizer":3,"mdc--otyv76-key":36,"related-repo-openai-financials-normalizer":1053,"related-org-openai-financials-normalizer":1155},{"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},"financials-normalizer","normalize public company financial statements","Use when normalizing public-company financials from source materials. Do not use for private data rooms or non-financial cleanup.",{"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},"Finance","finance","tag",{"name":17,"slug":18,"type":15},"Financial Statements","financial-statements",{"name":20,"slug":21,"type":15},"Accounting","accounting",{"name":23,"slug":24,"type":15},"Data Cleaning","data-cleaning",4888,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-08-28T15:09:21.324804",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\u002Ffinancials-normalizer","---\nname: financials-normalizer\ndescription: Use when normalizing public-company financials from source materials. Do not use for private data rooms or non-financial cleanup.\n---\n\n# Financials Normalizer\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### Source Resolution\n\nLoad `..\u002F..\u002Fshared\u002Fworkflow-source-resolution.md`. Resolve only the categories needed for this workflow: `company_filings_ir`, `earnings_transcripts_presentations`, `internal_research`, `portfolio_models_trackers`, and `market_data_estimates`. Use the shared runtime contract to map each attempted category to an available app, connector, file, export, or user-provided input.\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\nWhen invoked as support for an owning workflow, inherit its resolved deliverable preferences and do not re-prompt. Only when this skill independently owns a new substantive standalone normalization deliverable should it, before source gathering, analysis, or rendering, load `..\u002F..\u002Fshared\u002Fdeliverable-intake-policy.md` and perform its adaptive `request_user_input` preflight for materially unresolved preferences.\n\n## Purpose\n\nLoad `shared\u002Fequity-research-support-standard.md` and `shared\u002Fsupport-layer-routing-contract.md` before substantial source, data, QA, or style work.\n\n\nTurn messy public-company source financials into auditable, model-ready normalized statements, KPI schedules, consensus\u002Fguidance inputs, segment schedules, share-count support, net-debt and capital-allocation support, source citations, assumptions, conflicts, and QA flags for downstream Public Equity Investing workflows.\n\nBoundary: shipped scripts create `Source_Index.csv`, `Normalized_Financials_Long.csv`, and `Normalization_Issues.csv`. Wide statements, KPI schedules, adjustment logs, conflict logs, assumption registers, and workbook\u002Fdeck-ready tabs are instruction-led unless explicitly built from staging data.\n\nFor a standalone request for **model-ready normalized financials**, do not treat a long-form staging CSV alone as the analyst deliverable. Create a model-loading package from the staged rows: full-scope wide schedules relevant to the supplied financials, a disclosure\u002Fcomparability bridge when definitions or presentation changed, material QA flags, and logged validation checks. Use XLSX when the user requests a workbook or will load\u002Freview the output in a workbook; otherwise a clearly organized CSV package plus a concise review summary is appropriate. This is a data-first skill; do not force an HTML artifact unless the user requests one.\n\n## Embedded Support Routing\n\nThis is an embedded service under the owning workflow unless the user explicitly asks for standalone normalization. Preserve the `owning_workflow` internally, such as `equity-model-update`, `dcf-model-builder`, `three-statement-model-builder`, `comps-valuation`, `earnings-preview`, `earnings-deep-dive`, `memo-builder`, `thesis-tracker`, `scenario-sensitivity-generator`, `portfolio-risk-management`, or `dashboard-builder`.\n\nFor substantial embedded work, preserve `decision_impact`, `readiness_effect`, `artifact_role`, and `hidden_unless_requested` in internal context or support artifacts. Do not print those internal field names in the owning workflow's user-facing artifact. Do not own the valuation, memo, earnings, or recommendation; state in natural language how normalization issues change estimate confidence, valuation support, target support, sizing, model readiness, or circulation readiness. `Source_Index.csv`, `Normalized_Financials_Long.csv`, `Normalization_Issues.csv`, run logs, manifests, and support notes are secondary\u002Fsupport artifacts when invoked by an owning workflow.\n\n## Non-Negotiables\n\n- Preserve raw\u002Fsource materials.\n- Prefer user files\u002Fcontext, callable runtime apps\u002Fconnectors when actually available, primary public sources, user-provided provider exports, then labeled assumptions. Never imply live provider access when it is unavailable.\n- Never invent missing financials; mark unavailable values as `missing_required_source`.\n- Keep normalized values traceable to source ID, source name\u002Flocation, retrieved-at date, period, units, currency, and evidence label.\n- Missing `source_id` must remain visible as `SRC-UNSPECIFIED`, produce a QA flag, and block decision-grade handoff.\n- Retain conflicts rather than silently choosing values.\n- Flag stale, preliminary, unaudited, OCR-derived, or low-confidence data.\n- Do not infer fiscal period-end dates from quarter labels alone; use an explicit source date or mark the date missing and flag it.\n- Keep issuer outlook or guidance in `kpi_schedule` with `issuer_management_claim`; reserve `consensus_estimate` with `estimate_consensus` for externally sourced consensus estimates.\n- When a segment, KPI, non-GAAP definition, or balance-sheet presentation changes, preserve both bases and create a comparability bridge before calling any series model-loadable.\n- Apply comparability status at the affected series or line-item level. A changed cash presentation does not recast unrelated balance-sheet rows.\n- Use `comparable_rounded` when an unchanged reported series is comparable across periods but only available in rounded narrative units; disclose that it is unsuitable for exact tie-out.\n- Do not backsolve an undisclosed comparable value from rounded amounts or percentage growth for model loading. A labeled directional calculation may appear separately only when useful.\n- Material open exceptions must be surfaced in `QA_Flags` and in the readiness summary; an empty technical `Normalization_Issues` file does not mean the financials are clear for downstream use.\n\n## Workflow\n\n1. **Classify job.** Public-equity issuer financials, earnings\u002Fmodel update, consensus\u002Fprovider export, ETF\u002Findex constituent support, portfolio\u002Fmarket-data support, or equity-risk debt\u002Fliquidity context.\n2. **Build source index.** Capture source ID, name\u002Ftype, owner\u002Fprovider, period, as-of date, retrieved-at date, location, source rank, freshness, and notes.\n3. **Extract long-form staging.** Use `Normalized_Financials_Long` before wide statements; preserve original line labels beside canonical labels.\n4. **Normalize periods, scale, currency, signs, and labels.** Keep reported, adjusted, pro forma, provider-standardized, estimated, and analyst-adjusted values separate.\n5. **Reconcile disclosure changes.** Identify renamed, regrouped, newly introduced, discontinued, recast, or definition-changed segments\u002FKPIs\u002Fnon-GAAP lines; preserve legacy and new bases; create a disclosure\u002Fcomparability bridge with model treatment.\n6. **Reconcile and QA.** Check subtotals, roll-forwards, balance sheet balance, cash flow bridge, units\u002Fcurrency, duplicate periods, missing sources, stale\u002Fconflicting values, signs, unsupported KPIs, and completeness of the intended model-loading scope. Log performed checks and results; do not claim a check count that is not preserved in an output.\n7. **Produce package.** For standalone model-ready work, produce loadable wide schedules plus `QA_Flags` and `Validation_Checks` from the audited staging layer; include a disclosure\u002Fcomparability bridge whenever presentation changed. For narrower extraction\u002Fsupport work, return only the deterministic CSV outputs or instruction-led tabs actually created.\n8. **Hand off.** State what is loadable, what is audit-only, and what remains partial or blocked before routing to models, earnings, comps, memo, thesis, scenario, risk, ETF\u002Findex, or deck\u002Freport skills. Route covenant\u002Frecovery\u002Fdebt-security normalization to Credit Markets.\n\n## Sub-agent decomposition\n\nFor complex medium\u002Flarge requests, use sub-agents where available; otherwise emulate the split as named workstreams. Suggested lanes: source inventory, line-item mapping, period\u002Funit normalization, conflict log, and QA. Keep this skill as the lead: reconcile conflicts, source labels, assumptions, open items, final QA, and the user-facing answer.\n\nWhen embedded in a broader workflow, \"lead\" means lead for normalization only; the owning workflow remains the investment-artifact owner.\n\n\n## Evidence Labels\n\nUse exact labels from `references\u002Fnormalization-schema.md`, including `fact_source_reported`, `fact_provider_standardized`, `derived_calculation`, `issuer_management_claim`, `management_adjusted`, `analyst_adjusted`, `analyst_interpretation`, `assumption_user_provided`, `assumption_inferred`, `estimate_consensus`, `stale_source`, `contradicted_source`, `missing_required_source`, and `unknown`.\n\nConfidence labels are `high`, `medium`, or `low`.\n\n## Scripts\n\n```bash\npython scripts\u002Fnormalize_extracted_financials.py path\u002Fto\u002Finput.csv --output-dir output\npython scripts\u002Fvalidate_normalized_financials.py output\u002FNormalized_Financials_Long.csv\n```\n\nFor workbook inputs, first extract the relevant tab\u002Frange with spreadsheet tools into a table\u002FCSV; scripts must not destructively modify workbooks.\n\n## Final Response\n\nReturn:\n\n1. what was normalized: entity, sources, periods, units, currency, scope;\n2. outputs created;\n3. what can be loaded into a model and what remains audit-only, partial, or blocked;\n4. material QA findings and disclosure\u002Fcomparability breaks;\n5. fact versus assumption summary and validation checks actually performed;\n6. recommended next step or missing source.\n\n## Reference Map\n\n- `references\u002Fsource-protocol.md`: hierarchy, stale data, citations, conflicts.\n- `references\u002Fnormalization-schema.md`: output schema, signs, scales, labels.\n- `references\u002Fline-item-taxonomy.md`: statement\u002FKPI mappings.\n- `references\u002Fqa-rules.md`: reconciliation tests and red flags.\n- `references\u002Fintegration-guide.md`: downstream Public Equity Investing handoffs.\n",{"data":37,"body":38},{"name":4,"description":6},{"type":39,"children":40},"root",[41,49,56,63,94,100,151,157,162,194,200,221,227,247,252,279,292,298,389,442,448,599,605,711,717,722,727,733,841,867,873,935,940,946,951,984,990,1047],{"type":42,"tag":43,"props":44,"children":45},"element","h1",{"id":4},[46],{"type":47,"value":48},"text","Financials Normalizer",{"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":57,"props":95,"children":97},{"id":96},"source-resolution",[98],{"type":47,"value":99},"Source Resolution",{"type":42,"tag":64,"props":101,"children":102},{},[103,105,111,113,119,121,127,128,134,135,141,143,149],{"type":47,"value":104},"Load ",{"type":42,"tag":70,"props":106,"children":108},{"className":107},[],[109],{"type":47,"value":110},"..\u002F..\u002Fshared\u002Fworkflow-source-resolution.md",{"type":47,"value":112},". Resolve only the categories needed for this workflow: ",{"type":42,"tag":70,"props":114,"children":116},{"className":115},[],[117],{"type":47,"value":118},"company_filings_ir",{"type":47,"value":120},", ",{"type":42,"tag":70,"props":122,"children":124},{"className":123},[],[125],{"type":47,"value":126},"earnings_transcripts_presentations",{"type":47,"value":120},{"type":42,"tag":70,"props":129,"children":131},{"className":130},[],[132],{"type":47,"value":133},"internal_research",{"type":47,"value":120},{"type":42,"tag":70,"props":136,"children":138},{"className":137},[],[139],{"type":47,"value":140},"portfolio_models_trackers",{"type":47,"value":142},", and ",{"type":42,"tag":70,"props":144,"children":146},{"className":145},[],[147],{"type":47,"value":148},"market_data_estimates",{"type":47,"value":150},". Use the shared runtime contract to map each attempted category to an available app, connector, file, export, or user-provided input.",{"type":42,"tag":50,"props":152,"children":154},{"id":153},"relevant-dependency-categories",[155],{"type":47,"value":156},"Relevant Dependency Categories",{"type":42,"tag":64,"props":158,"children":159},{},[160],{"type":47,"value":161},"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":163,"props":164,"children":165},"ul",{},[166,176,185],{"type":42,"tag":167,"props":168,"children":169},"li",{},[170],{"type":42,"tag":70,"props":171,"children":173},{"className":172},[],[174],{"type":47,"value":175},"Company Filings & IR",{"type":42,"tag":167,"props":177,"children":178},{},[179],{"type":42,"tag":70,"props":180,"children":182},{"className":181},[],[183],{"type":47,"value":184},"Portfolio Models & Trackers",{"type":42,"tag":167,"props":186,"children":187},{},[188],{"type":42,"tag":70,"props":189,"children":191},{"className":190},[],[192],{"type":47,"value":193},"Market Data & Estimates",{"type":42,"tag":50,"props":195,"children":197},{"id":196},"deliverable-intake",[198],{"type":47,"value":199},"Deliverable Intake",{"type":42,"tag":64,"props":201,"children":202},{},[203,205,211,213,219],{"type":47,"value":204},"When invoked as support for an owning workflow, inherit its resolved deliverable preferences and do not re-prompt. Only when this skill independently owns a new substantive standalone normalization deliverable should it, before source gathering, analysis, or rendering, load ",{"type":42,"tag":70,"props":206,"children":208},{"className":207},[],[209],{"type":47,"value":210},"..\u002F..\u002Fshared\u002Fdeliverable-intake-policy.md",{"type":47,"value":212}," and perform its adaptive ",{"type":42,"tag":70,"props":214,"children":216},{"className":215},[],[217],{"type":47,"value":218},"request_user_input",{"type":47,"value":220}," preflight for materially unresolved preferences.",{"type":42,"tag":50,"props":222,"children":224},{"id":223},"purpose",[225],{"type":47,"value":226},"Purpose",{"type":42,"tag":64,"props":228,"children":229},{},[230,231,237,239,245],{"type":47,"value":104},{"type":42,"tag":70,"props":232,"children":234},{"className":233},[],[235],{"type":47,"value":236},"shared\u002Fequity-research-support-standard.md",{"type":47,"value":238}," and ",{"type":42,"tag":70,"props":240,"children":242},{"className":241},[],[243],{"type":47,"value":244},"shared\u002Fsupport-layer-routing-contract.md",{"type":47,"value":246}," before substantial source, data, QA, or style work.",{"type":42,"tag":64,"props":248,"children":249},{},[250],{"type":47,"value":251},"Turn messy public-company source financials into auditable, model-ready normalized statements, KPI schedules, consensus\u002Fguidance inputs, segment schedules, share-count support, net-debt and capital-allocation support, source citations, assumptions, conflicts, and QA flags for downstream Public Equity Investing workflows.",{"type":42,"tag":64,"props":253,"children":254},{},[255,257,263,264,270,271,277],{"type":47,"value":256},"Boundary: shipped scripts create ",{"type":42,"tag":70,"props":258,"children":260},{"className":259},[],[261],{"type":47,"value":262},"Source_Index.csv",{"type":47,"value":120},{"type":42,"tag":70,"props":265,"children":267},{"className":266},[],[268],{"type":47,"value":269},"Normalized_Financials_Long.csv",{"type":47,"value":142},{"type":42,"tag":70,"props":272,"children":274},{"className":273},[],[275],{"type":47,"value":276},"Normalization_Issues.csv",{"type":47,"value":278},". Wide statements, KPI schedules, adjustment logs, conflict logs, assumption registers, and workbook\u002Fdeck-ready tabs are instruction-led unless explicitly built from staging data.",{"type":42,"tag":64,"props":280,"children":281},{},[282,284,290],{"type":47,"value":283},"For a standalone request for ",{"type":42,"tag":285,"props":286,"children":287},"strong",{},[288],{"type":47,"value":289},"model-ready normalized financials",{"type":47,"value":291},", do not treat a long-form staging CSV alone as the analyst deliverable. Create a model-loading package from the staged rows: full-scope wide schedules relevant to the supplied financials, a disclosure\u002Fcomparability bridge when definitions or presentation changed, material QA flags, and logged validation checks. Use XLSX when the user requests a workbook or will load\u002Freview the output in a workbook; otherwise a clearly organized CSV package plus a concise review summary is appropriate. This is a data-first skill; do not force an HTML artifact unless the user requests one.",{"type":42,"tag":50,"props":293,"children":295},{"id":294},"embedded-support-routing",[296],{"type":47,"value":297},"Embedded Support Routing",{"type":42,"tag":64,"props":299,"children":300},{},[301,303,309,311,317,318,324,325,331,332,338,339,345,346,352,353,359,360,366,367,373,374,380,382,388],{"type":47,"value":302},"This is an embedded service under the owning workflow unless the user explicitly asks for standalone normalization. Preserve the ",{"type":42,"tag":70,"props":304,"children":306},{"className":305},[],[307],{"type":47,"value":308},"owning_workflow",{"type":47,"value":310}," internally, such as ",{"type":42,"tag":70,"props":312,"children":314},{"className":313},[],[315],{"type":47,"value":316},"equity-model-update",{"type":47,"value":120},{"type":42,"tag":70,"props":319,"children":321},{"className":320},[],[322],{"type":47,"value":323},"dcf-model-builder",{"type":47,"value":120},{"type":42,"tag":70,"props":326,"children":328},{"className":327},[],[329],{"type":47,"value":330},"three-statement-model-builder",{"type":47,"value":120},{"type":42,"tag":70,"props":333,"children":335},{"className":334},[],[336],{"type":47,"value":337},"comps-valuation",{"type":47,"value":120},{"type":42,"tag":70,"props":340,"children":342},{"className":341},[],[343],{"type":47,"value":344},"earnings-preview",{"type":47,"value":120},{"type":42,"tag":70,"props":347,"children":349},{"className":348},[],[350],{"type":47,"value":351},"earnings-deep-dive",{"type":47,"value":120},{"type":42,"tag":70,"props":354,"children":356},{"className":355},[],[357],{"type":47,"value":358},"memo-builder",{"type":47,"value":120},{"type":42,"tag":70,"props":361,"children":363},{"className":362},[],[364],{"type":47,"value":365},"thesis-tracker",{"type":47,"value":120},{"type":42,"tag":70,"props":368,"children":370},{"className":369},[],[371],{"type":47,"value":372},"scenario-sensitivity-generator",{"type":47,"value":120},{"type":42,"tag":70,"props":375,"children":377},{"className":376},[],[378],{"type":47,"value":379},"portfolio-risk-management",{"type":47,"value":381},", or ",{"type":42,"tag":70,"props":383,"children":385},{"className":384},[],[386],{"type":47,"value":387},"dashboard-builder",{"type":47,"value":93},{"type":42,"tag":64,"props":390,"children":391},{},[392,394,400,401,407,408,414,415,421,423,428,429,434,435,440],{"type":47,"value":393},"For substantial embedded work, preserve ",{"type":42,"tag":70,"props":395,"children":397},{"className":396},[],[398],{"type":47,"value":399},"decision_impact",{"type":47,"value":120},{"type":42,"tag":70,"props":402,"children":404},{"className":403},[],[405],{"type":47,"value":406},"readiness_effect",{"type":47,"value":120},{"type":42,"tag":70,"props":409,"children":411},{"className":410},[],[412],{"type":47,"value":413},"artifact_role",{"type":47,"value":142},{"type":42,"tag":70,"props":416,"children":418},{"className":417},[],[419],{"type":47,"value":420},"hidden_unless_requested",{"type":47,"value":422}," in internal context or support artifacts. Do not print those internal field names in the owning workflow's user-facing artifact. Do not own the valuation, memo, earnings, or recommendation; state in natural language how normalization issues change estimate confidence, valuation support, target support, sizing, model readiness, or circulation readiness. ",{"type":42,"tag":70,"props":424,"children":426},{"className":425},[],[427],{"type":47,"value":262},{"type":47,"value":120},{"type":42,"tag":70,"props":430,"children":432},{"className":431},[],[433],{"type":47,"value":269},{"type":47,"value":120},{"type":42,"tag":70,"props":436,"children":438},{"className":437},[],[439],{"type":47,"value":276},{"type":47,"value":441},", run logs, manifests, and support notes are secondary\u002Fsupport artifacts when invoked by an owning workflow.",{"type":42,"tag":50,"props":443,"children":445},{"id":444},"non-negotiables",[446],{"type":47,"value":447},"Non-Negotiables",{"type":42,"tag":163,"props":449,"children":450},{},[451,456,461,473,478,499,504,509,514,550,555,560,573,578],{"type":42,"tag":167,"props":452,"children":453},{},[454],{"type":47,"value":455},"Preserve raw\u002Fsource materials.",{"type":42,"tag":167,"props":457,"children":458},{},[459],{"type":47,"value":460},"Prefer user files\u002Fcontext, callable runtime apps\u002Fconnectors when actually available, primary public sources, user-provided provider exports, then labeled assumptions. Never imply live provider access when it is unavailable.",{"type":42,"tag":167,"props":462,"children":463},{},[464,466,472],{"type":47,"value":465},"Never invent missing financials; mark unavailable values as ",{"type":42,"tag":70,"props":467,"children":469},{"className":468},[],[470],{"type":47,"value":471},"missing_required_source",{"type":47,"value":93},{"type":42,"tag":167,"props":474,"children":475},{},[476],{"type":47,"value":477},"Keep normalized values traceable to source ID, source name\u002Flocation, retrieved-at date, period, units, currency, and evidence label.",{"type":42,"tag":167,"props":479,"children":480},{},[481,483,489,491,497],{"type":47,"value":482},"Missing ",{"type":42,"tag":70,"props":484,"children":486},{"className":485},[],[487],{"type":47,"value":488},"source_id",{"type":47,"value":490}," must remain visible as ",{"type":42,"tag":70,"props":492,"children":494},{"className":493},[],[495],{"type":47,"value":496},"SRC-UNSPECIFIED",{"type":47,"value":498},", produce a QA flag, and block decision-grade handoff.",{"type":42,"tag":167,"props":500,"children":501},{},[502],{"type":47,"value":503},"Retain conflicts rather than silently choosing values.",{"type":42,"tag":167,"props":505,"children":506},{},[507],{"type":47,"value":508},"Flag stale, preliminary, unaudited, OCR-derived, or low-confidence data.",{"type":42,"tag":167,"props":510,"children":511},{},[512],{"type":47,"value":513},"Do not infer fiscal period-end dates from quarter labels alone; use an explicit source date or mark the date missing and flag it.",{"type":42,"tag":167,"props":515,"children":516},{},[517,519,525,527,533,535,541,542,548],{"type":47,"value":518},"Keep issuer outlook or guidance in ",{"type":42,"tag":70,"props":520,"children":522},{"className":521},[],[523],{"type":47,"value":524},"kpi_schedule",{"type":47,"value":526}," with ",{"type":42,"tag":70,"props":528,"children":530},{"className":529},[],[531],{"type":47,"value":532},"issuer_management_claim",{"type":47,"value":534},"; reserve ",{"type":42,"tag":70,"props":536,"children":538},{"className":537},[],[539],{"type":47,"value":540},"consensus_estimate",{"type":47,"value":526},{"type":42,"tag":70,"props":543,"children":545},{"className":544},[],[546],{"type":47,"value":547},"estimate_consensus",{"type":47,"value":549}," for externally sourced consensus estimates.",{"type":42,"tag":167,"props":551,"children":552},{},[553],{"type":47,"value":554},"When a segment, KPI, non-GAAP definition, or balance-sheet presentation changes, preserve both bases and create a comparability bridge before calling any series model-loadable.",{"type":42,"tag":167,"props":556,"children":557},{},[558],{"type":47,"value":559},"Apply comparability status at the affected series or line-item level. A changed cash presentation does not recast unrelated balance-sheet rows.",{"type":42,"tag":167,"props":561,"children":562},{},[563,565,571],{"type":47,"value":564},"Use ",{"type":42,"tag":70,"props":566,"children":568},{"className":567},[],[569],{"type":47,"value":570},"comparable_rounded",{"type":47,"value":572}," when an unchanged reported series is comparable across periods but only available in rounded narrative units; disclose that it is unsuitable for exact tie-out.",{"type":42,"tag":167,"props":574,"children":575},{},[576],{"type":47,"value":577},"Do not backsolve an undisclosed comparable value from rounded amounts or percentage growth for model loading. A labeled directional calculation may appear separately only when useful.",{"type":42,"tag":167,"props":579,"children":580},{},[581,583,589,591,597],{"type":47,"value":582},"Material open exceptions must be surfaced in ",{"type":42,"tag":70,"props":584,"children":586},{"className":585},[],[587],{"type":47,"value":588},"QA_Flags",{"type":47,"value":590}," and in the readiness summary; an empty technical ",{"type":42,"tag":70,"props":592,"children":594},{"className":593},[],[595],{"type":47,"value":596},"Normalization_Issues",{"type":47,"value":598}," file does not mean the financials are clear for downstream use.",{"type":42,"tag":50,"props":600,"children":602},{"id":601},"workflow",[603],{"type":47,"value":604},"Workflow",{"type":42,"tag":606,"props":607,"children":608},"ol",{},[609,619,629,647,657,667,677,701],{"type":42,"tag":167,"props":610,"children":611},{},[612,617],{"type":42,"tag":285,"props":613,"children":614},{},[615],{"type":47,"value":616},"Classify job.",{"type":47,"value":618}," Public-equity issuer financials, earnings\u002Fmodel update, consensus\u002Fprovider export, ETF\u002Findex constituent support, portfolio\u002Fmarket-data support, or equity-risk debt\u002Fliquidity context.",{"type":42,"tag":167,"props":620,"children":621},{},[622,627],{"type":42,"tag":285,"props":623,"children":624},{},[625],{"type":47,"value":626},"Build source index.",{"type":47,"value":628}," Capture source ID, name\u002Ftype, owner\u002Fprovider, period, as-of date, retrieved-at date, location, source rank, freshness, and notes.",{"type":42,"tag":167,"props":630,"children":631},{},[632,637,639,645],{"type":42,"tag":285,"props":633,"children":634},{},[635],{"type":47,"value":636},"Extract long-form staging.",{"type":47,"value":638}," Use ",{"type":42,"tag":70,"props":640,"children":642},{"className":641},[],[643],{"type":47,"value":644},"Normalized_Financials_Long",{"type":47,"value":646}," before wide statements; preserve original line labels beside canonical labels.",{"type":42,"tag":167,"props":648,"children":649},{},[650,655],{"type":42,"tag":285,"props":651,"children":652},{},[653],{"type":47,"value":654},"Normalize periods, scale, currency, signs, and labels.",{"type":47,"value":656}," Keep reported, adjusted, pro forma, provider-standardized, estimated, and analyst-adjusted values separate.",{"type":42,"tag":167,"props":658,"children":659},{},[660,665],{"type":42,"tag":285,"props":661,"children":662},{},[663],{"type":47,"value":664},"Reconcile disclosure changes.",{"type":47,"value":666}," Identify renamed, regrouped, newly introduced, discontinued, recast, or definition-changed segments\u002FKPIs\u002Fnon-GAAP lines; preserve legacy and new bases; create a disclosure\u002Fcomparability bridge with model treatment.",{"type":42,"tag":167,"props":668,"children":669},{},[670,675],{"type":42,"tag":285,"props":671,"children":672},{},[673],{"type":47,"value":674},"Reconcile and QA.",{"type":47,"value":676}," Check subtotals, roll-forwards, balance sheet balance, cash flow bridge, units\u002Fcurrency, duplicate periods, missing sources, stale\u002Fconflicting values, signs, unsupported KPIs, and completeness of the intended model-loading scope. Log performed checks and results; do not claim a check count that is not preserved in an output.",{"type":42,"tag":167,"props":678,"children":679},{},[680,685,687,692,693,699],{"type":42,"tag":285,"props":681,"children":682},{},[683],{"type":47,"value":684},"Produce package.",{"type":47,"value":686}," For standalone model-ready work, produce loadable wide schedules plus ",{"type":42,"tag":70,"props":688,"children":690},{"className":689},[],[691],{"type":47,"value":588},{"type":47,"value":238},{"type":42,"tag":70,"props":694,"children":696},{"className":695},[],[697],{"type":47,"value":698},"Validation_Checks",{"type":47,"value":700}," from the audited staging layer; include a disclosure\u002Fcomparability bridge whenever presentation changed. For narrower extraction\u002Fsupport work, return only the deterministic CSV outputs or instruction-led tabs actually created.",{"type":42,"tag":167,"props":702,"children":703},{},[704,709],{"type":42,"tag":285,"props":705,"children":706},{},[707],{"type":47,"value":708},"Hand off.",{"type":47,"value":710}," State what is loadable, what is audit-only, and what remains partial or blocked before routing to models, earnings, comps, memo, thesis, scenario, risk, ETF\u002Findex, or deck\u002Freport skills. Route covenant\u002Frecovery\u002Fdebt-security normalization to Credit Markets.",{"type":42,"tag":50,"props":712,"children":714},{"id":713},"sub-agent-decomposition",[715],{"type":47,"value":716},"Sub-agent decomposition",{"type":42,"tag":64,"props":718,"children":719},{},[720],{"type":47,"value":721},"For complex medium\u002Flarge requests, use sub-agents where available; otherwise emulate the split as named workstreams. Suggested lanes: source inventory, line-item mapping, period\u002Funit normalization, conflict log, and QA. Keep this skill as the lead: reconcile conflicts, source labels, assumptions, open items, final QA, and the user-facing answer.",{"type":42,"tag":64,"props":723,"children":724},{},[725],{"type":47,"value":726},"When embedded in a broader workflow, \"lead\" means lead for normalization only; the owning workflow remains the investment-artifact owner.",{"type":42,"tag":50,"props":728,"children":730},{"id":729},"evidence-labels",[731],{"type":47,"value":732},"Evidence Labels",{"type":42,"tag":64,"props":734,"children":735},{},[736,738,744,746,752,753,759,760,766,767,772,773,779,780,786,787,793,794,800,801,807,808,813,814,820,821,827,828,833,834,840],{"type":47,"value":737},"Use exact labels from ",{"type":42,"tag":70,"props":739,"children":741},{"className":740},[],[742],{"type":47,"value":743},"references\u002Fnormalization-schema.md",{"type":47,"value":745},", including ",{"type":42,"tag":70,"props":747,"children":749},{"className":748},[],[750],{"type":47,"value":751},"fact_source_reported",{"type":47,"value":120},{"type":42,"tag":70,"props":754,"children":756},{"className":755},[],[757],{"type":47,"value":758},"fact_provider_standardized",{"type":47,"value":120},{"type":42,"tag":70,"props":761,"children":763},{"className":762},[],[764],{"type":47,"value":765},"derived_calculation",{"type":47,"value":120},{"type":42,"tag":70,"props":768,"children":770},{"className":769},[],[771],{"type":47,"value":532},{"type":47,"value":120},{"type":42,"tag":70,"props":774,"children":776},{"className":775},[],[777],{"type":47,"value":778},"management_adjusted",{"type":47,"value":120},{"type":42,"tag":70,"props":781,"children":783},{"className":782},[],[784],{"type":47,"value":785},"analyst_adjusted",{"type":47,"value":120},{"type":42,"tag":70,"props":788,"children":790},{"className":789},[],[791],{"type":47,"value":792},"analyst_interpretation",{"type":47,"value":120},{"type":42,"tag":70,"props":795,"children":797},{"className":796},[],[798],{"type":47,"value":799},"assumption_user_provided",{"type":47,"value":120},{"type":42,"tag":70,"props":802,"children":804},{"className":803},[],[805],{"type":47,"value":806},"assumption_inferred",{"type":47,"value":120},{"type":42,"tag":70,"props":809,"children":811},{"className":810},[],[812],{"type":47,"value":547},{"type":47,"value":120},{"type":42,"tag":70,"props":815,"children":817},{"className":816},[],[818],{"type":47,"value":819},"stale_source",{"type":47,"value":120},{"type":42,"tag":70,"props":822,"children":824},{"className":823},[],[825],{"type":47,"value":826},"contradicted_source",{"type":47,"value":120},{"type":42,"tag":70,"props":829,"children":831},{"className":830},[],[832],{"type":47,"value":471},{"type":47,"value":142},{"type":42,"tag":70,"props":835,"children":837},{"className":836},[],[838],{"type":47,"value":839},"unknown",{"type":47,"value":93},{"type":42,"tag":64,"props":842,"children":843},{},[844,846,852,853,859,860,866],{"type":47,"value":845},"Confidence labels are ",{"type":42,"tag":70,"props":847,"children":849},{"className":848},[],[850],{"type":47,"value":851},"high",{"type":47,"value":120},{"type":42,"tag":70,"props":854,"children":856},{"className":855},[],[857],{"type":47,"value":858},"medium",{"type":47,"value":381},{"type":42,"tag":70,"props":861,"children":863},{"className":862},[],[864],{"type":47,"value":865},"low",{"type":47,"value":93},{"type":42,"tag":50,"props":868,"children":870},{"id":869},"scripts",[871],{"type":47,"value":872},"Scripts",{"type":42,"tag":874,"props":875,"children":880},"pre",{"className":876,"code":877,"language":878,"meta":879,"style":879},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","python scripts\u002Fnormalize_extracted_financials.py path\u002Fto\u002Finput.csv --output-dir output\npython scripts\u002Fvalidate_normalized_financials.py output\u002FNormalized_Financials_Long.csv\n","bash","",[881],{"type":42,"tag":70,"props":882,"children":883},{"__ignoreMap":879},[884,917],{"type":42,"tag":885,"props":886,"children":889},"span",{"class":887,"line":888},"line",1,[890,896,902,907,912],{"type":42,"tag":885,"props":891,"children":893},{"style":892},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[894],{"type":47,"value":895},"python",{"type":42,"tag":885,"props":897,"children":899},{"style":898},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[900],{"type":47,"value":901}," scripts\u002Fnormalize_extracted_financials.py",{"type":42,"tag":885,"props":903,"children":904},{"style":898},[905],{"type":47,"value":906}," path\u002Fto\u002Finput.csv",{"type":42,"tag":885,"props":908,"children":909},{"style":898},[910],{"type":47,"value":911}," --output-dir",{"type":42,"tag":885,"props":913,"children":914},{"style":898},[915],{"type":47,"value":916}," output\n",{"type":42,"tag":885,"props":918,"children":920},{"class":887,"line":919},2,[921,925,930],{"type":42,"tag":885,"props":922,"children":923},{"style":892},[924],{"type":47,"value":895},{"type":42,"tag":885,"props":926,"children":927},{"style":898},[928],{"type":47,"value":929}," scripts\u002Fvalidate_normalized_financials.py",{"type":42,"tag":885,"props":931,"children":932},{"style":898},[933],{"type":47,"value":934}," output\u002FNormalized_Financials_Long.csv\n",{"type":42,"tag":64,"props":936,"children":937},{},[938],{"type":47,"value":939},"For workbook inputs, first extract the relevant tab\u002Frange with spreadsheet tools into a table\u002FCSV; scripts must not destructively modify workbooks.",{"type":42,"tag":50,"props":941,"children":943},{"id":942},"final-response",[944],{"type":47,"value":945},"Final Response",{"type":42,"tag":64,"props":947,"children":948},{},[949],{"type":47,"value":950},"Return:",{"type":42,"tag":606,"props":952,"children":953},{},[954,959,964,969,974,979],{"type":42,"tag":167,"props":955,"children":956},{},[957],{"type":47,"value":958},"what was normalized: entity, sources, periods, units, currency, scope;",{"type":42,"tag":167,"props":960,"children":961},{},[962],{"type":47,"value":963},"outputs created;",{"type":42,"tag":167,"props":965,"children":966},{},[967],{"type":47,"value":968},"what can be loaded into a model and what remains audit-only, partial, or blocked;",{"type":42,"tag":167,"props":970,"children":971},{},[972],{"type":47,"value":973},"material QA findings and disclosure\u002Fcomparability breaks;",{"type":42,"tag":167,"props":975,"children":976},{},[977],{"type":47,"value":978},"fact versus assumption summary and validation checks actually performed;",{"type":42,"tag":167,"props":980,"children":981},{},[982],{"type":47,"value":983},"recommended next step or missing source.",{"type":42,"tag":50,"props":985,"children":987},{"id":986},"reference-map",[988],{"type":47,"value":989},"Reference Map",{"type":42,"tag":163,"props":991,"children":992},{},[993,1004,1014,1025,1036],{"type":42,"tag":167,"props":994,"children":995},{},[996,1002],{"type":42,"tag":70,"props":997,"children":999},{"className":998},[],[1000],{"type":47,"value":1001},"references\u002Fsource-protocol.md",{"type":47,"value":1003},": hierarchy, stale data, citations, conflicts.",{"type":42,"tag":167,"props":1005,"children":1006},{},[1007,1012],{"type":42,"tag":70,"props":1008,"children":1010},{"className":1009},[],[1011],{"type":47,"value":743},{"type":47,"value":1013},": output schema, signs, scales, labels.",{"type":42,"tag":167,"props":1015,"children":1016},{},[1017,1023],{"type":42,"tag":70,"props":1018,"children":1020},{"className":1019},[],[1021],{"type":47,"value":1022},"references\u002Fline-item-taxonomy.md",{"type":47,"value":1024},": statement\u002FKPI mappings.",{"type":42,"tag":167,"props":1026,"children":1027},{},[1028,1034],{"type":42,"tag":70,"props":1029,"children":1031},{"className":1030},[],[1032],{"type":47,"value":1033},"references\u002Fqa-rules.md",{"type":47,"value":1035},": reconciliation tests and red flags.",{"type":42,"tag":167,"props":1037,"children":1038},{},[1039,1045],{"type":42,"tag":70,"props":1040,"children":1042},{"className":1041},[],[1043],{"type":47,"value":1044},"references\u002Fintegration-guide.md",{"type":47,"value":1046},": downstream Public Equity Investing handoffs.",{"type":42,"tag":1048,"props":1049,"children":1050},"style",{},[1051],{"type":47,"value":1052},"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":1054,"total":1154},[1055,1074,1090,1102,1117,1130,1142],{"slug":1056,"name":1056,"fn":1057,"description":1058,"org":1059,"tags":1060,"stars":25,"repoUrl":26,"updatedAt":1073},"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},[1061,1064,1067,1070],{"name":1062,"slug":1063,"type":15},"Accessibility","accessibility",{"name":1065,"slug":1066,"type":15},"Charts","charts",{"name":1068,"slug":1069,"type":15},"Data Visualization","data-visualization",{"name":1071,"slug":1072,"type":15},"Design","design","2026-06-30T19:00:57.102",{"slug":1075,"name":1075,"fn":1076,"description":1077,"org":1078,"tags":1079,"stars":25,"repoUrl":26,"updatedAt":1089},"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},[1080,1083,1086],{"name":1081,"slug":1082,"type":15},"Creative","creative",{"name":1084,"slug":1085,"type":15},"Editing","editing",{"name":1087,"slug":1088,"type":15},"Imaging","imaging","2026-08-28T15:09:11.185865",{"slug":1091,"name":1091,"fn":1092,"description":1093,"org":1094,"tags":1095,"stars":25,"repoUrl":26,"updatedAt":1101},"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},[1096,1097,1098],{"name":1081,"slug":1082,"type":15},{"name":1071,"slug":1072,"type":15},{"name":1099,"slug":1100,"type":15},"Graphics","graphics","2026-08-28T15:09:07.42507",{"slug":1103,"name":1103,"fn":1104,"description":1105,"org":1106,"tags":1107,"stars":25,"repoUrl":26,"updatedAt":1116},"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},[1108,1109,1110,1113],{"name":1081,"slug":1082,"type":15},{"name":1099,"slug":1100,"type":15},{"name":1111,"slug":1112,"type":15},"Marketing","marketing",{"name":1114,"slug":1115,"type":15},"Social Media","social-media","2026-08-28T15:10:07.282096",{"slug":1118,"name":1118,"fn":1119,"description":1120,"org":1121,"tags":1122,"stars":25,"repoUrl":26,"updatedAt":1129},"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},[1123,1124,1125,1126],{"name":1081,"slug":1082,"type":15},{"name":1071,"slug":1072,"type":15},{"name":1099,"slug":1100,"type":15},{"name":1127,"slug":1128,"type":15},"Templates","templates","2026-08-28T15:10:03.050113",{"slug":1131,"name":1131,"fn":1132,"description":1133,"org":1134,"tags":1135,"stars":25,"repoUrl":26,"updatedAt":1141},"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},[1136,1137,1138],{"name":1081,"slug":1082,"type":15},{"name":1084,"slug":1085,"type":15},{"name":1139,"slug":1140,"type":15},"Video","video","2026-08-28T15:09:07.765245",{"slug":1143,"name":1143,"fn":1144,"description":1145,"org":1146,"tags":1147,"stars":25,"repoUrl":26,"updatedAt":1153},"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},[1148,1149,1150],{"name":1081,"slug":1082,"type":15},{"name":1087,"slug":1088,"type":15},{"name":1151,"slug":1152,"type":15},"Photography","photography","2026-08-28T15:09:10.386974",499,{"items":1156,"total":1357},[1157,1178,1201,1218,1234,1253,1272,1286,1302,1316,1328,1341],{"slug":1158,"name":1158,"fn":1159,"description":1160,"org":1161,"tags":1162,"stars":1175,"repoUrl":1176,"updatedAt":1177},"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},[1163,1166,1169,1172],{"name":1164,"slug":1165,"type":15},"Documents","documents",{"name":1167,"slug":1168,"type":15},"Healthcare","healthcare",{"name":1170,"slug":1171,"type":15},"Insurance","insurance",{"name":1173,"slug":1174,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-08-02T05:48:07.395855",{"slug":1179,"name":1179,"fn":1180,"description":1181,"org":1182,"tags":1183,"stars":1198,"repoUrl":1199,"updatedAt":1200},"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},[1184,1187,1189,1192,1195],{"name":1185,"slug":1186,"type":15},".NET","dotnet",{"name":1188,"slug":1179,"type":15},"ASP.NET Core",{"name":1190,"slug":1191,"type":15},"Blazor","blazor",{"name":1193,"slug":1194,"type":15},"C#","csharp",{"name":1196,"slug":1197,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":1202,"name":1202,"fn":1203,"description":1204,"org":1205,"tags":1206,"stars":1198,"repoUrl":1199,"updatedAt":1217},"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},[1207,1210,1213,1216],{"name":1208,"slug":1209,"type":15},"Apps SDK","apps-sdk",{"name":1211,"slug":1212,"type":15},"ChatGPT","chatgpt",{"name":1214,"slug":1215,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":1219,"name":1219,"fn":1220,"description":1221,"org":1222,"tags":1223,"stars":1198,"repoUrl":1199,"updatedAt":1233},"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},[1224,1227,1230],{"name":1225,"slug":1226,"type":15},"API Development","api-development",{"name":1228,"slug":1229,"type":15},"CLI","cli",{"name":1231,"slug":1232,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":1235,"name":1235,"fn":1236,"description":1237,"org":1238,"tags":1239,"stars":1198,"repoUrl":1199,"updatedAt":1252},"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},[1240,1243,1246,1249],{"name":1241,"slug":1242,"type":15},"Cloudflare","cloudflare",{"name":1244,"slug":1245,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":1247,"slug":1248,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":1250,"slug":1251,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":1254,"name":1254,"fn":1255,"description":1256,"org":1257,"tags":1258,"stars":1198,"repoUrl":1199,"updatedAt":1271},"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},[1259,1262,1265,1268],{"name":1260,"slug":1261,"type":15},"Productivity","productivity",{"name":1263,"slug":1264,"type":15},"Project Management","project-management",{"name":1266,"slug":1267,"type":15},"Strategy","strategy",{"name":1269,"slug":1270,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":1273,"name":1273,"fn":1274,"description":1275,"org":1276,"tags":1277,"stars":1198,"repoUrl":1199,"updatedAt":1285},"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},[1278,1279,1281,1284],{"name":1071,"slug":1072,"type":15},{"name":1280,"slug":1273,"type":15},"Figma",{"name":1282,"slug":1283,"type":15},"Frontend","frontend",{"name":1214,"slug":1215,"type":15},"2026-04-12T05:06:47.939943",{"slug":1287,"name":1287,"fn":1288,"description":1289,"org":1290,"tags":1291,"stars":1198,"repoUrl":1199,"updatedAt":1301},"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},[1292,1293,1296,1297,1298],{"name":1071,"slug":1072,"type":15},{"name":1294,"slug":1295,"type":15},"Design System","design-system",{"name":1280,"slug":1273,"type":15},{"name":1282,"slug":1283,"type":15},{"name":1299,"slug":1300,"type":15},"UI Components","ui-components","2026-05-10T05:59:52.971881",{"slug":1303,"name":1303,"fn":1304,"description":1305,"org":1306,"tags":1307,"stars":1198,"repoUrl":1199,"updatedAt":1315},"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},[1308,1309,1310,1313,1314],{"name":1071,"slug":1072,"type":15},{"name":1294,"slug":1295,"type":15},{"name":1311,"slug":1312,"type":15},"Documentation","documentation",{"name":1280,"slug":1273,"type":15},{"name":1282,"slug":1283,"type":15},"2026-05-16T06:07:47.821474",{"slug":1317,"name":1317,"fn":1318,"description":1319,"org":1320,"tags":1321,"stars":1198,"repoUrl":1199,"updatedAt":1327},"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},[1322,1323,1324,1325,1326],{"name":1071,"slug":1072,"type":15},{"name":1280,"slug":1273,"type":15},{"name":1282,"slug":1283,"type":15},{"name":1299,"slug":1300,"type":15},{"name":1196,"slug":1197,"type":15},"2026-05-16T06:07:40.583615",{"slug":1329,"name":1329,"fn":1330,"description":1331,"org":1332,"tags":1333,"stars":1198,"repoUrl":1199,"updatedAt":1340},"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},[1334,1337,1338,1339],{"name":1335,"slug":1336,"type":15},"Animation","animation",{"name":1231,"slug":1232,"type":15},{"name":1081,"slug":1082,"type":15},{"name":1071,"slug":1072,"type":15},"2026-05-02T05:31:48.48485",{"slug":1342,"name":1342,"fn":1343,"description":1344,"org":1345,"tags":1346,"stars":1198,"repoUrl":1199,"updatedAt":1356},"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},[1347,1348,1349,1352,1355],{"name":1081,"slug":1082,"type":15},{"name":1071,"slug":1072,"type":15},{"name":1350,"slug":1351,"type":15},"Image Generation","image-generation",{"name":1353,"slug":1354,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",578]