[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-model-audit-tieout":3,"mdc-pb479r-key":36,"related-repo-openai-model-audit-tieout":1149,"related-org-openai-model-audit-tieout":1251},{"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},"model-audit-tieout","audit public equity investment models","Use when auditing existing Public Equity Investing models or spreadsheets. Do not use to build a new model from scratch.",{"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},"Audit","audit",4888,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-08-28T15:09:15.303481",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\u002Fmodel-audit-tieout","---\nname: model-audit-tieout\ndescription: Use when auditing existing Public Equity Investing models or spreadsheets. Do not use to build a new model from scratch.\n---\n\n# Model Audit Tie-Out\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- `Portfolio Models & Trackers`\n- `Company Filings & IR`\n- `Market Data & Estimates`\n\n## Internal Support\n\nWhen the audit requires evidence control, generic data cleaning, dashboard rendering, style application, or sector context, route that support through the visible `public-equity-investing` router and its bundled internal playbooks. This visible skill remains the owner of the model-review deliverable.\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. For a substantive standalone review of an existing model or explicit HTML model-audit request, the default resolves the presentation surface to a polished standalone HTML model-audit report unless the user requests an alternate surface, a quick\u002Fno-file answer, remediation output, or a standardized dashboard. In interactive runs, ask only remaining material choices such as depth, audience\u002Fuse, materiality, or focus; in non-interactive runs, default to the HTML model-audit report and `Full working analysis` while disclosing those assumptions outside the artifact. Reuse resolved preferences in downstream steps; when acting only as input to an owning workflow, do not re-prompt.\n\n## Purpose\n\nReview an existing public-equity model, workbook, forecast, valuation file, estimate update, comps workbook, sensitivity deck, or model-derived output and produce a decision-useful audit pack. This skill is a QA layer for formula integrity, source support, assumption hygiene, scenario quality, controls, and decision readiness.\n\nDo not rebuild the model unless the user explicitly asks for remediation. Default to an audit memo, issue log, source tie-out ledger, and prioritized fix list.\n\nThe headline output is an audit verdict on permitted use: `Ready`, `Ready with caveats`, `Not ready`, or `Not assessable`. This skill does not turn an unsupported model into an investment recommendation. When required valuation, scenario, or market-price outputs are absent, state that the model or model package cannot support portfolio action until remediated and re-audited.\n\n## Core Principles\n\n- Review before changing; never overwrite formulas, assumptions, outputs, or tabs unless asked.\n- Separate model mechanics from investment judgment.\n- Tie material outputs to workbook tabs\u002Fcells, source documents, or explicit assumptions.\n- Prioritize by decision impact, not issue count.\n- Escalate unsupported decision drivers even when formulas are mechanically clean.\n- Distinguish a broken model from an undocumented or unsupported underwriting assumption, a stale forecast, a missing source bridge, and a missing decision-output layer.\n- A three-statement operating model need not itself contain target price or valuation; for portfolio-decision use, require a linked valuation\u002Fscenario decision output in the model package before concluding that forecasts support action.\n- Label auditor-created stresses as `Illustrative audit sensitivity` unless the user explicitly approves them as revised base-case assumptions.\n\n## Workflow\n\n1. **Confirm audit mandate.** Identify model type, intended model-package scope, decision context, materiality threshold, and requested output. Determine whether the workbook is expected to contain decision outputs or to feed a separate linked valuation\u002Fscenario layer.\n2. **Run workbook inspection when available.** For `.xlsx` workbooks, use the helper as a starting point:\n\n```bash\npython scripts\u002Faudit_workbook.py path\u002Fto\u002Fmodel.xlsx --out-dir audit_output\n```\n\nDependency note: the helper requires `openpyxl`; install the local dependency file in a fresh environment:\n\n```bash\npython -m pip install -r scripts\u002Frequirements.txt\n```\n\n3. **Map key outputs.** Trace valuation, target-price, estimate, earnings, event, risk, or common-equity downside outputs back to assumptions, formulas, source tabs, and source documents.\n4. **Apply formula and workbook controls.** Check inconsistent formulas, hardcodes, broken links, hidden sheets, volatile functions, bypassed assumption tabs, circularity, plugs, unsupported checks, and formulas that do not tie to schedules.\n5. **Review first-tab decision readiness.** Flag missing or thin first-visible `Cover` tabs when net read, key outputs, scenario metrics, model status, source posture, warnings\u002Fhard failures, chart-ready data, and workbook navigation are buried.\n6. **Tie assumptions to evidence.** Use `references\u002Ftieout-and-source-checks.md` and `financial-source-of-truth` standards to label primary facts, claims, estimates, assumptions, inferences, and unsupported items.\n7. **Review scenarios and downside.** Test whether scenarios focus on true value\u002Frisk drivers and whether downside captures liquidity\u002Frefinancing risk as common-equity impairment, multiple compression, estimate cuts, cash-burn dilution, or event failure as relevant. Treat auditor-created replacement assumptions or stress math as diagnostic illustrations, not repaired model forecasts.\n8. **Build issue log.** Include severity, finding type, category, location, finding, decision impact, recommended fix, and owner. Use reader-facing finding types: `Formula\u002Fcontrol defect`, `Source contradiction`, `Unsupported assumption`, `Missing forecast refresh`, `Missing decision output`, or `Not comparable without bridge`.\n9. **Deliver audit pack.** Choose rapid screen or full audit pack based on user need.\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: workbook controls, formula review, source tie-out, scenario\u002Fdownside review, and issue prioritization. Keep this skill as the lead: reconcile conflicts, source labels, assumptions, open items, final QA, and the user-facing answer.\n\n\n## Output Contract\n\n**Rapid screen**\n\n- model health score;\n- top issues by severity;\n- decision readiness;\n- immediate fixes.\n\n**Full audit pack**\n\nDefault substantial workbook audits to a reader-facing `model_audit_report.html`, produced as a polished standalone HTML model-audit report following `..\u002F..\u002Fshared\u002Fhtml-artifact-standard.md`, plus an optional `model_audit_issues.xlsx` companion workbook. Keep `model_audit_findings.json`, `formula_exception_log.csv`, `source_tieout_ledger.csv`, raw workbook maps, and support notes behind the HTML\u002Fworkbook unless the user asks for audit files. In the default delivery message, link only the primary HTML report and any requested user-facing workbook; mention supporting audit files without linking them unless the user asks.\n\n- executive summary;\n- readiness posture;\n- issue log;\n- formula\u002Fworkbook controls;\n- source tie-out findings;\n- assumption and scenario critique;\n- sensitivity review;\n- remediation sequence;\n- open evidence requests;\n- appendix with formula exceptions and tie-out ledger.\n\nUse `dashboard-builder` and `references\u002Fdashboard-map.md` only when the user explicitly requests a standardized dashboard, reusable validated template, model-health cockpit, remediation tracker, or structured payload-driven render. A substantial ordinary audit should remain a flexible standalone HTML report rather than a fixed dashboard-module package.\n\n## HTML Guidance\n\nFor a substantive standalone HTML model-audit report, load `..\u002F..\u002Fshared\u002Fhtml-artifact-standard.md` and use this audit-specific hierarchy:\n\n1. Audit verdict and permitted use: whether the model may support the stated decision, the top blocker, the scope reviewed, and any limitations on recalculation or source verification.\n2. Critical blockers and what appears mechanically sound, separated clearly so a linked workbook is not confused with an underwritten forecast.\n3. Decision-output assessment: whether a linked valuation\u002Fscenario layer, current-price anchor, estimate bridge, or downside view exists and is supportable for the requested use.\n4. Priority issue log with workbook location, finding type, decision impact, and remediation.\n5. Source tie-out findings, diagnostic sensitivities, controls, remediation sequence, evidence requests, and method\u002Flimitations.\n\nAdditional rules:\n\n- Keep the headline as an audit verdict. When decision outputs are absent or unreliable, say `Do not use for portfolio action until remediated and re-audited`; do not imply an `add`, `trim`, `exit`, `hedge`, or `wait for proof` recommendation from an audit-only mandate.\n- Classify decision-relevant findings as `Formula\u002Fcontrol defect`, `Source contradiction`, `Unsupported assumption`, `Missing forecast refresh`, `Missing decision output`, or `Not comparable without bridge`; do not make every unsupported forecast assumption sound like a formula error.\n- Display auditor-created cash, leverage, EPS, valuation, or scenario stresses as `Illustrative audit sensitivity`; do not represent a diagnostic stress as a corrected forecast or revised base case.\n- When reviewing an operating or three-statement model, distinguish absence of valuation inside that workbook from absence of a linked valuation\u002Fscenario decision output in the overall package. The latter blocks portfolio-decision use when required by the mandate; the former is not automatically a model defect.\n- Do not feature a current-price or market-data anchor in the verdict, headline KPI row, or decision-output assessment unless the cited source has been verified for the correct security and as-of date; if it cannot be verified, state that the external price anchor is unavailable.\n- Cite critical findings with workbook sheet\u002Fcell or range plus controlling source location where available. Keep source\u002Fas-of posture and limitations such as cached outputs versus native recalculation visible.\n- Visually inspect local HTML via local headless-browser screenshots, not the in-app Browser plugin, and iterate on hierarchy, legibility, table density, citation rendering, and whether the audit verdict and top fixes are immediately visible.\n\n## Handoffs\n\n- `financial-source-of-truth`: evidence hierarchy, stale\u002Fconflicting data, citations, labels.\n- `excel-data-cleaner`: malformed tables or unclear row\u002Fcolumn grain before audit.\n- Model\u002Fresearch builders: rebuild, refresh, expand, or stress-test after audit.\n- `memo-builder`: convert audit findings into a decision memo.\n- `deck-report-qc`: reconcile audited model outputs to decks, board packs, IC memos, or client presentations.\n\n## Resources\n\n- `scripts\u002Faudit_workbook.py`: static workbook inspection helper.\n- `scripts\u002Frequirements.txt`: workbook helper dependency declaration.\n- `references\u002Faudit-playbook.md`: audit modes by model type.\n- `references\u002Fformula-and-workbook-controls.md`: formula and architecture checks.\n- `references\u002Ftieout-and-source-checks.md`: source tie-out process and evidence labels.\n- `references\u002Fissue-taxonomy.md`: severity and issue categories.\n- `references\u002Foutput-templates.md`: audit memo, issue log, tie-out ledger, and IC-ready templates.\n- `references\u002Fdashboard-map.md`: dashboard mapping for model health, formula exceptions, source tie-outs, and readiness.\n- `references\u002Fp0-integrations.md`: coordination with launch skills.\n\n## Final QA\n\nConfirm severity is tied to decision impact, model issues are separated from evidence issues, audit sensitivities are identified as illustrative rather than repaired forecasts, missing decision-layer scope is not confused with a formula defect, source\u002Fas-of dates are visible, unsupported assumptions are not buried, remediation steps are concrete, and no user workbook content was destructively changed.\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",[41,50,57,64,95,101,106,138,144,157,163,192,198,203,208,244,250,301,307,340,384,397,436,576,582,587,593,601,624,632,683,736,756,762,774,802,807,933,939,990,996,1096,1102,1107,1113,1133,1138,1143],{"type":42,"tag":43,"props":44,"children":46},"element","h1",{"id":45},"model-audit-tie-out",[47],{"type":48,"value":49},"text","Model Audit Tie-Out",{"type":42,"tag":51,"props":52,"children":54},"h2",{"id":53},"skill-configuration",[55],{"type":48,"value":56},"Skill Configuration",{"type":42,"tag":58,"props":59,"children":61},"h3",{"id":60},"common-skill-instructions",[62],{"type":48,"value":63},"Common Skill Instructions",{"type":42,"tag":65,"props":66,"children":67},"p",{},[68,70,77,79,85,87,93],{"type":48,"value":69},"MANDATORY: Before searching connectors, retrieving evidence, or drafting output, read and apply the shared runtime contract in ",{"type":42,"tag":71,"props":72,"children":74},"code",{"className":73},[],[75],{"type":48,"value":76},"..\u002Fpublic-equity-investing\u002FSKILL.md## Cross-Skill Runtime Contract",{"type":48,"value":78},". Then check the router skill map and ",{"type":42,"tag":71,"props":80,"children":82},{"className":81},[],[83],{"type":48,"value":84},"..\u002F..\u002Fshared\u002Fplugin-routing-playbook.md",{"type":48,"value":86}," 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":71,"props":88,"children":90},{"className":89},[],[91],{"type":48,"value":92},"..\u002Fuser-context\u002FSKILL.md",{"type":48,"value":94},".",{"type":42,"tag":51,"props":96,"children":98},{"id":97},"relevant-dependency-categories",[99],{"type":48,"value":100},"Relevant Dependency Categories",{"type":42,"tag":65,"props":102,"children":103},{},[104],{"type":48,"value":105},"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":107,"props":108,"children":109},"ul",{},[110,120,129],{"type":42,"tag":111,"props":112,"children":113},"li",{},[114],{"type":42,"tag":71,"props":115,"children":117},{"className":116},[],[118],{"type":48,"value":119},"Portfolio Models & Trackers",{"type":42,"tag":111,"props":121,"children":122},{},[123],{"type":42,"tag":71,"props":124,"children":126},{"className":125},[],[127],{"type":48,"value":128},"Company Filings & IR",{"type":42,"tag":111,"props":130,"children":131},{},[132],{"type":42,"tag":71,"props":133,"children":135},{"className":134},[],[136],{"type":48,"value":137},"Market Data & Estimates",{"type":42,"tag":51,"props":139,"children":141},{"id":140},"internal-support",[142],{"type":48,"value":143},"Internal Support",{"type":42,"tag":65,"props":145,"children":146},{},[147,149,155],{"type":48,"value":148},"When the audit requires evidence control, generic data cleaning, dashboard rendering, style application, or sector context, route that support through the visible ",{"type":42,"tag":71,"props":150,"children":152},{"className":151},[],[153],{"type":48,"value":154},"public-equity-investing",{"type":48,"value":156}," router and its bundled internal playbooks. This visible skill remains the owner of the model-review deliverable.",{"type":42,"tag":51,"props":158,"children":160},{"id":159},"deliverable-intake",[161],{"type":48,"value":162},"Deliverable Intake",{"type":42,"tag":65,"props":164,"children":165},{},[166,168,174,176,182,184,190],{"type":48,"value":167},"Before source gathering or analysis for a new substantive hero deliverable, load ",{"type":42,"tag":71,"props":169,"children":171},{"className":170},[],[172],{"type":48,"value":173},"..\u002F..\u002Fshared\u002Fdeliverable-intake-policy.md",{"type":48,"value":175}," and use its adaptive ",{"type":42,"tag":71,"props":177,"children":179},{"className":178},[],[180],{"type":48,"value":181},"request_user_input",{"type":48,"value":183}," preflight for materially unresolved format, depth, audience\u002Fuse, or focus choices. For a substantive standalone review of an existing model or explicit HTML model-audit request, the default resolves the presentation surface to a polished standalone HTML model-audit report unless the user requests an alternate surface, a quick\u002Fno-file answer, remediation output, or a standardized dashboard. In interactive runs, ask only remaining material choices such as depth, audience\u002Fuse, materiality, or focus; in non-interactive runs, default to the HTML model-audit report and ",{"type":42,"tag":71,"props":185,"children":187},{"className":186},[],[188],{"type":48,"value":189},"Full working analysis",{"type":48,"value":191}," while disclosing those assumptions outside the artifact. Reuse resolved preferences in downstream steps; when acting only as input to an owning workflow, do not re-prompt.",{"type":42,"tag":51,"props":193,"children":195},{"id":194},"purpose",[196],{"type":48,"value":197},"Purpose",{"type":42,"tag":65,"props":199,"children":200},{},[201],{"type":48,"value":202},"Review an existing public-equity model, workbook, forecast, valuation file, estimate update, comps workbook, sensitivity deck, or model-derived output and produce a decision-useful audit pack. This skill is a QA layer for formula integrity, source support, assumption hygiene, scenario quality, controls, and decision readiness.",{"type":42,"tag":65,"props":204,"children":205},{},[206],{"type":48,"value":207},"Do not rebuild the model unless the user explicitly asks for remediation. Default to an audit memo, issue log, source tie-out ledger, and prioritized fix list.",{"type":42,"tag":65,"props":209,"children":210},{},[211,213,219,221,227,228,234,236,242],{"type":48,"value":212},"The headline output is an audit verdict on permitted use: ",{"type":42,"tag":71,"props":214,"children":216},{"className":215},[],[217],{"type":48,"value":218},"Ready",{"type":48,"value":220},", ",{"type":42,"tag":71,"props":222,"children":224},{"className":223},[],[225],{"type":48,"value":226},"Ready with caveats",{"type":48,"value":220},{"type":42,"tag":71,"props":229,"children":231},{"className":230},[],[232],{"type":48,"value":233},"Not ready",{"type":48,"value":235},", or ",{"type":42,"tag":71,"props":237,"children":239},{"className":238},[],[240],{"type":48,"value":241},"Not assessable",{"type":48,"value":243},". This skill does not turn an unsupported model into an investment recommendation. When required valuation, scenario, or market-price outputs are absent, state that the model or model package cannot support portfolio action until remediated and re-audited.",{"type":42,"tag":51,"props":245,"children":247},{"id":246},"core-principles",[248],{"type":48,"value":249},"Core Principles",{"type":42,"tag":107,"props":251,"children":252},{},[253,258,263,268,273,278,283,288],{"type":42,"tag":111,"props":254,"children":255},{},[256],{"type":48,"value":257},"Review before changing; never overwrite formulas, assumptions, outputs, or tabs unless asked.",{"type":42,"tag":111,"props":259,"children":260},{},[261],{"type":48,"value":262},"Separate model mechanics from investment judgment.",{"type":42,"tag":111,"props":264,"children":265},{},[266],{"type":48,"value":267},"Tie material outputs to workbook tabs\u002Fcells, source documents, or explicit assumptions.",{"type":42,"tag":111,"props":269,"children":270},{},[271],{"type":48,"value":272},"Prioritize by decision impact, not issue count.",{"type":42,"tag":111,"props":274,"children":275},{},[276],{"type":48,"value":277},"Escalate unsupported decision drivers even when formulas are mechanically clean.",{"type":42,"tag":111,"props":279,"children":280},{},[281],{"type":48,"value":282},"Distinguish a broken model from an undocumented or unsupported underwriting assumption, a stale forecast, a missing source bridge, and a missing decision-output layer.",{"type":42,"tag":111,"props":284,"children":285},{},[286],{"type":48,"value":287},"A three-statement operating model need not itself contain target price or valuation; for portfolio-decision use, require a linked valuation\u002Fscenario decision output in the model package before concluding that forecasts support action.",{"type":42,"tag":111,"props":289,"children":290},{},[291,293,299],{"type":48,"value":292},"Label auditor-created stresses as ",{"type":42,"tag":71,"props":294,"children":296},{"className":295},[],[297],{"type":48,"value":298},"Illustrative audit sensitivity",{"type":48,"value":300}," unless the user explicitly approves them as revised base-case assumptions.",{"type":42,"tag":51,"props":302,"children":304},{"id":303},"workflow",[305],{"type":48,"value":306},"Workflow",{"type":42,"tag":308,"props":309,"children":310},"ol",{},[311,322],{"type":42,"tag":111,"props":312,"children":313},{},[314,320],{"type":42,"tag":315,"props":316,"children":317},"strong",{},[318],{"type":48,"value":319},"Confirm audit mandate.",{"type":48,"value":321}," Identify model type, intended model-package scope, decision context, materiality threshold, and requested output. Determine whether the workbook is expected to contain decision outputs or to feed a separate linked valuation\u002Fscenario layer.",{"type":42,"tag":111,"props":323,"children":324},{},[325,330,332,338],{"type":42,"tag":315,"props":326,"children":327},{},[328],{"type":48,"value":329},"Run workbook inspection when available.",{"type":48,"value":331}," For ",{"type":42,"tag":71,"props":333,"children":335},{"className":334},[],[336],{"type":48,"value":337},".xlsx",{"type":48,"value":339}," workbooks, use the helper as a starting point:",{"type":42,"tag":341,"props":342,"children":347},"pre",{"className":343,"code":344,"language":345,"meta":346,"style":346},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","python scripts\u002Faudit_workbook.py path\u002Fto\u002Fmodel.xlsx --out-dir audit_output\n","bash","",[348],{"type":42,"tag":71,"props":349,"children":350},{"__ignoreMap":346},[351],{"type":42,"tag":352,"props":353,"children":356},"span",{"class":354,"line":355},"line",1,[357,363,369,374,379],{"type":42,"tag":352,"props":358,"children":360},{"style":359},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[361],{"type":48,"value":362},"python",{"type":42,"tag":352,"props":364,"children":366},{"style":365},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[367],{"type":48,"value":368}," scripts\u002Faudit_workbook.py",{"type":42,"tag":352,"props":370,"children":371},{"style":365},[372],{"type":48,"value":373}," path\u002Fto\u002Fmodel.xlsx",{"type":42,"tag":352,"props":375,"children":376},{"style":365},[377],{"type":48,"value":378}," --out-dir",{"type":42,"tag":352,"props":380,"children":381},{"style":365},[382],{"type":48,"value":383}," audit_output\n",{"type":42,"tag":65,"props":385,"children":386},{},[387,389,395],{"type":48,"value":388},"Dependency note: the helper requires ",{"type":42,"tag":71,"props":390,"children":392},{"className":391},[],[393],{"type":48,"value":394},"openpyxl",{"type":48,"value":396},"; install the local dependency file in a fresh environment:",{"type":42,"tag":341,"props":398,"children":400},{"className":343,"code":399,"language":345,"meta":346,"style":346},"python -m pip install -r scripts\u002Frequirements.txt\n",[401],{"type":42,"tag":71,"props":402,"children":403},{"__ignoreMap":346},[404],{"type":42,"tag":352,"props":405,"children":406},{"class":354,"line":355},[407,411,416,421,426,431],{"type":42,"tag":352,"props":408,"children":409},{"style":359},[410],{"type":48,"value":362},{"type":42,"tag":352,"props":412,"children":413},{"style":365},[414],{"type":48,"value":415}," -m",{"type":42,"tag":352,"props":417,"children":418},{"style":365},[419],{"type":48,"value":420}," pip",{"type":42,"tag":352,"props":422,"children":423},{"style":365},[424],{"type":48,"value":425}," install",{"type":42,"tag":352,"props":427,"children":428},{"style":365},[429],{"type":48,"value":430}," -r",{"type":42,"tag":352,"props":432,"children":433},{"style":365},[434],{"type":48,"value":435}," scripts\u002Frequirements.txt\n",{"type":42,"tag":308,"props":437,"children":439},{"start":438},3,[440,450,460,478,504,514,566],{"type":42,"tag":111,"props":441,"children":442},{},[443,448],{"type":42,"tag":315,"props":444,"children":445},{},[446],{"type":48,"value":447},"Map key outputs.",{"type":48,"value":449}," Trace valuation, target-price, estimate, earnings, event, risk, or common-equity downside outputs back to assumptions, formulas, source tabs, and source documents.",{"type":42,"tag":111,"props":451,"children":452},{},[453,458],{"type":42,"tag":315,"props":454,"children":455},{},[456],{"type":48,"value":457},"Apply formula and workbook controls.",{"type":48,"value":459}," Check inconsistent formulas, hardcodes, broken links, hidden sheets, volatile functions, bypassed assumption tabs, circularity, plugs, unsupported checks, and formulas that do not tie to schedules.",{"type":42,"tag":111,"props":461,"children":462},{},[463,468,470,476],{"type":42,"tag":315,"props":464,"children":465},{},[466],{"type":48,"value":467},"Review first-tab decision readiness.",{"type":48,"value":469}," Flag missing or thin first-visible ",{"type":42,"tag":71,"props":471,"children":473},{"className":472},[],[474],{"type":48,"value":475},"Cover",{"type":48,"value":477}," tabs when net read, key outputs, scenario metrics, model status, source posture, warnings\u002Fhard failures, chart-ready data, and workbook navigation are buried.",{"type":42,"tag":111,"props":479,"children":480},{},[481,486,488,494,496,502],{"type":42,"tag":315,"props":482,"children":483},{},[484],{"type":48,"value":485},"Tie assumptions to evidence.",{"type":48,"value":487}," Use ",{"type":42,"tag":71,"props":489,"children":491},{"className":490},[],[492],{"type":48,"value":493},"references\u002Ftieout-and-source-checks.md",{"type":48,"value":495}," and ",{"type":42,"tag":71,"props":497,"children":499},{"className":498},[],[500],{"type":48,"value":501},"financial-source-of-truth",{"type":48,"value":503}," standards to label primary facts, claims, estimates, assumptions, inferences, and unsupported items.",{"type":42,"tag":111,"props":505,"children":506},{},[507,512],{"type":42,"tag":315,"props":508,"children":509},{},[510],{"type":48,"value":511},"Review scenarios and downside.",{"type":48,"value":513}," Test whether scenarios focus on true value\u002Frisk drivers and whether downside captures liquidity\u002Frefinancing risk as common-equity impairment, multiple compression, estimate cuts, cash-burn dilution, or event failure as relevant. Treat auditor-created replacement assumptions or stress math as diagnostic illustrations, not repaired model forecasts.",{"type":42,"tag":111,"props":515,"children":516},{},[517,522,524,530,531,537,538,544,545,551,552,558,559,565],{"type":42,"tag":315,"props":518,"children":519},{},[520],{"type":48,"value":521},"Build issue log.",{"type":48,"value":523}," Include severity, finding type, category, location, finding, decision impact, recommended fix, and owner. Use reader-facing finding types: ",{"type":42,"tag":71,"props":525,"children":527},{"className":526},[],[528],{"type":48,"value":529},"Formula\u002Fcontrol defect",{"type":48,"value":220},{"type":42,"tag":71,"props":532,"children":534},{"className":533},[],[535],{"type":48,"value":536},"Source contradiction",{"type":48,"value":220},{"type":42,"tag":71,"props":539,"children":541},{"className":540},[],[542],{"type":48,"value":543},"Unsupported assumption",{"type":48,"value":220},{"type":42,"tag":71,"props":546,"children":548},{"className":547},[],[549],{"type":48,"value":550},"Missing forecast refresh",{"type":48,"value":220},{"type":42,"tag":71,"props":553,"children":555},{"className":554},[],[556],{"type":48,"value":557},"Missing decision output",{"type":48,"value":235},{"type":42,"tag":71,"props":560,"children":562},{"className":561},[],[563],{"type":48,"value":564},"Not comparable without bridge",{"type":48,"value":94},{"type":42,"tag":111,"props":567,"children":568},{},[569,574],{"type":42,"tag":315,"props":570,"children":571},{},[572],{"type":48,"value":573},"Deliver audit pack.",{"type":48,"value":575}," Choose rapid screen or full audit pack based on user need.",{"type":42,"tag":51,"props":577,"children":579},{"id":578},"sub-agent-decomposition",[580],{"type":48,"value":581},"Sub-agent decomposition",{"type":42,"tag":65,"props":583,"children":584},{},[585],{"type":48,"value":586},"For complex medium\u002Flarge requests, use sub-agents where available; otherwise emulate the split as named workstreams. Suggested lanes: workbook controls, formula review, source tie-out, scenario\u002Fdownside review, and issue prioritization. Keep this skill as the lead: reconcile conflicts, source labels, assumptions, open items, final QA, and the user-facing answer.",{"type":42,"tag":51,"props":588,"children":590},{"id":589},"output-contract",[591],{"type":48,"value":592},"Output Contract",{"type":42,"tag":65,"props":594,"children":595},{},[596],{"type":42,"tag":315,"props":597,"children":598},{},[599],{"type":48,"value":600},"Rapid screen",{"type":42,"tag":107,"props":602,"children":603},{},[604,609,614,619],{"type":42,"tag":111,"props":605,"children":606},{},[607],{"type":48,"value":608},"model health score;",{"type":42,"tag":111,"props":610,"children":611},{},[612],{"type":48,"value":613},"top issues by severity;",{"type":42,"tag":111,"props":615,"children":616},{},[617],{"type":48,"value":618},"decision readiness;",{"type":42,"tag":111,"props":620,"children":621},{},[622],{"type":48,"value":623},"immediate fixes.",{"type":42,"tag":65,"props":625,"children":626},{},[627],{"type":42,"tag":315,"props":628,"children":629},{},[630],{"type":48,"value":631},"Full audit pack",{"type":42,"tag":65,"props":633,"children":634},{},[635,637,643,645,651,653,659,661,667,668,674,675,681],{"type":48,"value":636},"Default substantial workbook audits to a reader-facing ",{"type":42,"tag":71,"props":638,"children":640},{"className":639},[],[641],{"type":48,"value":642},"model_audit_report.html",{"type":48,"value":644},", produced as a polished standalone HTML model-audit report following ",{"type":42,"tag":71,"props":646,"children":648},{"className":647},[],[649],{"type":48,"value":650},"..\u002F..\u002Fshared\u002Fhtml-artifact-standard.md",{"type":48,"value":652},", plus an optional ",{"type":42,"tag":71,"props":654,"children":656},{"className":655},[],[657],{"type":48,"value":658},"model_audit_issues.xlsx",{"type":48,"value":660}," companion workbook. Keep ",{"type":42,"tag":71,"props":662,"children":664},{"className":663},[],[665],{"type":48,"value":666},"model_audit_findings.json",{"type":48,"value":220},{"type":42,"tag":71,"props":669,"children":671},{"className":670},[],[672],{"type":48,"value":673},"formula_exception_log.csv",{"type":48,"value":220},{"type":42,"tag":71,"props":676,"children":678},{"className":677},[],[679],{"type":48,"value":680},"source_tieout_ledger.csv",{"type":48,"value":682},", raw workbook maps, and support notes behind the HTML\u002Fworkbook unless the user asks for audit files. In the default delivery message, link only the primary HTML report and any requested user-facing workbook; mention supporting audit files without linking them unless the user asks.",{"type":42,"tag":107,"props":684,"children":685},{},[686,691,696,701,706,711,716,721,726,731],{"type":42,"tag":111,"props":687,"children":688},{},[689],{"type":48,"value":690},"executive summary;",{"type":42,"tag":111,"props":692,"children":693},{},[694],{"type":48,"value":695},"readiness posture;",{"type":42,"tag":111,"props":697,"children":698},{},[699],{"type":48,"value":700},"issue log;",{"type":42,"tag":111,"props":702,"children":703},{},[704],{"type":48,"value":705},"formula\u002Fworkbook controls;",{"type":42,"tag":111,"props":707,"children":708},{},[709],{"type":48,"value":710},"source tie-out findings;",{"type":42,"tag":111,"props":712,"children":713},{},[714],{"type":48,"value":715},"assumption and scenario critique;",{"type":42,"tag":111,"props":717,"children":718},{},[719],{"type":48,"value":720},"sensitivity review;",{"type":42,"tag":111,"props":722,"children":723},{},[724],{"type":48,"value":725},"remediation sequence;",{"type":42,"tag":111,"props":727,"children":728},{},[729],{"type":48,"value":730},"open evidence requests;",{"type":42,"tag":111,"props":732,"children":733},{},[734],{"type":48,"value":735},"appendix with formula exceptions and tie-out ledger.",{"type":42,"tag":65,"props":737,"children":738},{},[739,741,747,748,754],{"type":48,"value":740},"Use ",{"type":42,"tag":71,"props":742,"children":744},{"className":743},[],[745],{"type":48,"value":746},"dashboard-builder",{"type":48,"value":495},{"type":42,"tag":71,"props":749,"children":751},{"className":750},[],[752],{"type":48,"value":753},"references\u002Fdashboard-map.md",{"type":48,"value":755}," only when the user explicitly requests a standardized dashboard, reusable validated template, model-health cockpit, remediation tracker, or structured payload-driven render. A substantial ordinary audit should remain a flexible standalone HTML report rather than a fixed dashboard-module package.",{"type":42,"tag":51,"props":757,"children":759},{"id":758},"html-guidance",[760],{"type":48,"value":761},"HTML Guidance",{"type":42,"tag":65,"props":763,"children":764},{},[765,767,772],{"type":48,"value":766},"For a substantive standalone HTML model-audit report, load ",{"type":42,"tag":71,"props":768,"children":770},{"className":769},[],[771],{"type":48,"value":650},{"type":48,"value":773}," and use this audit-specific hierarchy:",{"type":42,"tag":308,"props":775,"children":776},{},[777,782,787,792,797],{"type":42,"tag":111,"props":778,"children":779},{},[780],{"type":48,"value":781},"Audit verdict and permitted use: whether the model may support the stated decision, the top blocker, the scope reviewed, and any limitations on recalculation or source verification.",{"type":42,"tag":111,"props":783,"children":784},{},[785],{"type":48,"value":786},"Critical blockers and what appears mechanically sound, separated clearly so a linked workbook is not confused with an underwritten forecast.",{"type":42,"tag":111,"props":788,"children":789},{},[790],{"type":48,"value":791},"Decision-output assessment: whether a linked valuation\u002Fscenario layer, current-price anchor, estimate bridge, or downside view exists and is supportable for the requested use.",{"type":42,"tag":111,"props":793,"children":794},{},[795],{"type":48,"value":796},"Priority issue log with workbook location, finding type, decision impact, and remediation.",{"type":42,"tag":111,"props":798,"children":799},{},[800],{"type":48,"value":801},"Source tie-out findings, diagnostic sensitivities, controls, remediation sequence, evidence requests, and method\u002Flimitations.",{"type":42,"tag":65,"props":803,"children":804},{},[805],{"type":48,"value":806},"Additional rules:",{"type":42,"tag":107,"props":808,"children":809},{},[810,859,901,913,918,923,928],{"type":42,"tag":111,"props":811,"children":812},{},[813,815,821,823,829,830,836,837,843,844,850,851,857],{"type":48,"value":814},"Keep the headline as an audit verdict. When decision outputs are absent or unreliable, say ",{"type":42,"tag":71,"props":816,"children":818},{"className":817},[],[819],{"type":48,"value":820},"Do not use for portfolio action until remediated and re-audited",{"type":48,"value":822},"; do not imply an ",{"type":42,"tag":71,"props":824,"children":826},{"className":825},[],[827],{"type":48,"value":828},"add",{"type":48,"value":220},{"type":42,"tag":71,"props":831,"children":833},{"className":832},[],[834],{"type":48,"value":835},"trim",{"type":48,"value":220},{"type":42,"tag":71,"props":838,"children":840},{"className":839},[],[841],{"type":48,"value":842},"exit",{"type":48,"value":220},{"type":42,"tag":71,"props":845,"children":847},{"className":846},[],[848],{"type":48,"value":849},"hedge",{"type":48,"value":235},{"type":42,"tag":71,"props":852,"children":854},{"className":853},[],[855],{"type":48,"value":856},"wait for proof",{"type":48,"value":858}," recommendation from an audit-only mandate.",{"type":42,"tag":111,"props":860,"children":861},{},[862,864,869,870,875,876,881,882,887,888,893,894,899],{"type":48,"value":863},"Classify decision-relevant findings as ",{"type":42,"tag":71,"props":865,"children":867},{"className":866},[],[868],{"type":48,"value":529},{"type":48,"value":220},{"type":42,"tag":71,"props":871,"children":873},{"className":872},[],[874],{"type":48,"value":536},{"type":48,"value":220},{"type":42,"tag":71,"props":877,"children":879},{"className":878},[],[880],{"type":48,"value":543},{"type":48,"value":220},{"type":42,"tag":71,"props":883,"children":885},{"className":884},[],[886],{"type":48,"value":550},{"type":48,"value":220},{"type":42,"tag":71,"props":889,"children":891},{"className":890},[],[892],{"type":48,"value":557},{"type":48,"value":235},{"type":42,"tag":71,"props":895,"children":897},{"className":896},[],[898],{"type":48,"value":564},{"type":48,"value":900},"; do not make every unsupported forecast assumption sound like a formula error.",{"type":42,"tag":111,"props":902,"children":903},{},[904,906,911],{"type":48,"value":905},"Display auditor-created cash, leverage, EPS, valuation, or scenario stresses as ",{"type":42,"tag":71,"props":907,"children":909},{"className":908},[],[910],{"type":48,"value":298},{"type":48,"value":912},"; do not represent a diagnostic stress as a corrected forecast or revised base case.",{"type":42,"tag":111,"props":914,"children":915},{},[916],{"type":48,"value":917},"When reviewing an operating or three-statement model, distinguish absence of valuation inside that workbook from absence of a linked valuation\u002Fscenario decision output in the overall package. The latter blocks portfolio-decision use when required by the mandate; the former is not automatically a model defect.",{"type":42,"tag":111,"props":919,"children":920},{},[921],{"type":48,"value":922},"Do not feature a current-price or market-data anchor in the verdict, headline KPI row, or decision-output assessment unless the cited source has been verified for the correct security and as-of date; if it cannot be verified, state that the external price anchor is unavailable.",{"type":42,"tag":111,"props":924,"children":925},{},[926],{"type":48,"value":927},"Cite critical findings with workbook sheet\u002Fcell or range plus controlling source location where available. Keep source\u002Fas-of posture and limitations such as cached outputs versus native recalculation visible.",{"type":42,"tag":111,"props":929,"children":930},{},[931],{"type":48,"value":932},"Visually inspect local HTML via local headless-browser screenshots, not the in-app Browser plugin, and iterate on hierarchy, legibility, table density, citation rendering, and whether the audit verdict and top fixes are immediately visible.",{"type":42,"tag":51,"props":934,"children":936},{"id":935},"handoffs",[937],{"type":48,"value":938},"Handoffs",{"type":42,"tag":107,"props":940,"children":941},{},[942,952,963,968,979],{"type":42,"tag":111,"props":943,"children":944},{},[945,950],{"type":42,"tag":71,"props":946,"children":948},{"className":947},[],[949],{"type":48,"value":501},{"type":48,"value":951},": evidence hierarchy, stale\u002Fconflicting data, citations, labels.",{"type":42,"tag":111,"props":953,"children":954},{},[955,961],{"type":42,"tag":71,"props":956,"children":958},{"className":957},[],[959],{"type":48,"value":960},"excel-data-cleaner",{"type":48,"value":962},": malformed tables or unclear row\u002Fcolumn grain before audit.",{"type":42,"tag":111,"props":964,"children":965},{},[966],{"type":48,"value":967},"Model\u002Fresearch builders: rebuild, refresh, expand, or stress-test after audit.",{"type":42,"tag":111,"props":969,"children":970},{},[971,977],{"type":42,"tag":71,"props":972,"children":974},{"className":973},[],[975],{"type":48,"value":976},"memo-builder",{"type":48,"value":978},": convert audit findings into a decision memo.",{"type":42,"tag":111,"props":980,"children":981},{},[982,988],{"type":42,"tag":71,"props":983,"children":985},{"className":984},[],[986],{"type":48,"value":987},"deck-report-qc",{"type":48,"value":989},": reconcile audited model outputs to decks, board packs, IC memos, or client presentations.",{"type":42,"tag":51,"props":991,"children":993},{"id":992},"resources",[994],{"type":48,"value":995},"Resources",{"type":42,"tag":107,"props":997,"children":998},{},[999,1010,1021,1032,1043,1053,1064,1075,1085],{"type":42,"tag":111,"props":1000,"children":1001},{},[1002,1008],{"type":42,"tag":71,"props":1003,"children":1005},{"className":1004},[],[1006],{"type":48,"value":1007},"scripts\u002Faudit_workbook.py",{"type":48,"value":1009},": static workbook inspection helper.",{"type":42,"tag":111,"props":1011,"children":1012},{},[1013,1019],{"type":42,"tag":71,"props":1014,"children":1016},{"className":1015},[],[1017],{"type":48,"value":1018},"scripts\u002Frequirements.txt",{"type":48,"value":1020},": workbook helper dependency declaration.",{"type":42,"tag":111,"props":1022,"children":1023},{},[1024,1030],{"type":42,"tag":71,"props":1025,"children":1027},{"className":1026},[],[1028],{"type":48,"value":1029},"references\u002Faudit-playbook.md",{"type":48,"value":1031},": audit modes by model type.",{"type":42,"tag":111,"props":1033,"children":1034},{},[1035,1041],{"type":42,"tag":71,"props":1036,"children":1038},{"className":1037},[],[1039],{"type":48,"value":1040},"references\u002Fformula-and-workbook-controls.md",{"type":48,"value":1042},": formula and architecture checks.",{"type":42,"tag":111,"props":1044,"children":1045},{},[1046,1051],{"type":42,"tag":71,"props":1047,"children":1049},{"className":1048},[],[1050],{"type":48,"value":493},{"type":48,"value":1052},": source tie-out process and evidence labels.",{"type":42,"tag":111,"props":1054,"children":1055},{},[1056,1062],{"type":42,"tag":71,"props":1057,"children":1059},{"className":1058},[],[1060],{"type":48,"value":1061},"references\u002Fissue-taxonomy.md",{"type":48,"value":1063},": severity and issue categories.",{"type":42,"tag":111,"props":1065,"children":1066},{},[1067,1073],{"type":42,"tag":71,"props":1068,"children":1070},{"className":1069},[],[1071],{"type":48,"value":1072},"references\u002Foutput-templates.md",{"type":48,"value":1074},": audit memo, issue log, tie-out ledger, and IC-ready templates.",{"type":42,"tag":111,"props":1076,"children":1077},{},[1078,1083],{"type":42,"tag":71,"props":1079,"children":1081},{"className":1080},[],[1082],{"type":48,"value":753},{"type":48,"value":1084},": dashboard mapping for model health, formula exceptions, source tie-outs, and readiness.",{"type":42,"tag":111,"props":1086,"children":1087},{},[1088,1094],{"type":42,"tag":71,"props":1089,"children":1091},{"className":1090},[],[1092],{"type":48,"value":1093},"references\u002Fp0-integrations.md",{"type":48,"value":1095},": coordination with launch skills.",{"type":42,"tag":51,"props":1097,"children":1099},{"id":1098},"final-qa",[1100],{"type":48,"value":1101},"Final QA",{"type":42,"tag":65,"props":1103,"children":1104},{},[1105],{"type":48,"value":1106},"Confirm severity is tied to decision impact, model issues are separated from evidence issues, audit sensitivities are identified as illustrative rather than repaired forecasts, missing decision-layer scope is not confused with a formula defect, source\u002Fas-of dates are visible, unsupported assumptions are not buried, remediation steps are concrete, and no user workbook content was destructively changed.",{"type":42,"tag":51,"props":1108,"children":1110},{"id":1109},"equity-valuation-pm-standard",[1111],{"type":48,"value":1112},"Equity Valuation PM Standard",{"type":42,"tag":65,"props":1114,"children":1115},{},[1116,1118,1124,1125,1131],{"type":48,"value":1117},"Load ",{"type":42,"tag":71,"props":1119,"children":1121},{"className":1120},[],[1122],{"type":48,"value":1123},"shared\u002Fequity-valuation-pm-standard.md",{"type":48,"value":495},{"type":42,"tag":71,"props":1126,"children":1128},{"className":1127},[],[1129],{"type":48,"value":1130},"shared\u002Fpm-judgment-heuristics.md",{"type":48,"value":1132}," for substantial model, valuation, scenario, model-update, or audit work.",{"type":42,"tag":65,"props":1134,"children":1135},{},[1136],{"type":48,"value":1137},"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":65,"props":1139,"children":1140},{},[1141],{"type":48,"value":1142},"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":1144,"props":1145,"children":1146},"style",{},[1147],{"type":48,"value":1148},"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":1150,"total":1250},[1151,1170,1186,1198,1213,1226,1238],{"slug":1152,"name":1152,"fn":1153,"description":1154,"org":1155,"tags":1156,"stars":25,"repoUrl":26,"updatedAt":1169},"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},[1157,1160,1163,1166],{"name":1158,"slug":1159,"type":15},"Accessibility","accessibility",{"name":1161,"slug":1162,"type":15},"Charts","charts",{"name":1164,"slug":1165,"type":15},"Data Visualization","data-visualization",{"name":1167,"slug":1168,"type":15},"Design","design","2026-06-30T19:00:57.102",{"slug":1171,"name":1171,"fn":1172,"description":1173,"org":1174,"tags":1175,"stars":25,"repoUrl":26,"updatedAt":1185},"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},[1176,1179,1182],{"name":1177,"slug":1178,"type":15},"Creative","creative",{"name":1180,"slug":1181,"type":15},"Editing","editing",{"name":1183,"slug":1184,"type":15},"Imaging","imaging","2026-08-28T15:09:11.185865",{"slug":1187,"name":1187,"fn":1188,"description":1189,"org":1190,"tags":1191,"stars":25,"repoUrl":26,"updatedAt":1197},"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},[1192,1193,1194],{"name":1177,"slug":1178,"type":15},{"name":1167,"slug":1168,"type":15},{"name":1195,"slug":1196,"type":15},"Graphics","graphics","2026-08-28T15:09:07.42507",{"slug":1199,"name":1199,"fn":1200,"description":1201,"org":1202,"tags":1203,"stars":25,"repoUrl":26,"updatedAt":1212},"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},[1204,1205,1206,1209],{"name":1177,"slug":1178,"type":15},{"name":1195,"slug":1196,"type":15},{"name":1207,"slug":1208,"type":15},"Marketing","marketing",{"name":1210,"slug":1211,"type":15},"Social Media","social-media","2026-08-28T15:10:07.282096",{"slug":1214,"name":1214,"fn":1215,"description":1216,"org":1217,"tags":1218,"stars":25,"repoUrl":26,"updatedAt":1225},"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},[1219,1220,1221,1222],{"name":1177,"slug":1178,"type":15},{"name":1167,"slug":1168,"type":15},{"name":1195,"slug":1196,"type":15},{"name":1223,"slug":1224,"type":15},"Templates","templates","2026-08-28T15:10:03.050113",{"slug":1227,"name":1227,"fn":1228,"description":1229,"org":1230,"tags":1231,"stars":25,"repoUrl":26,"updatedAt":1237},"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},[1232,1233,1234],{"name":1177,"slug":1178,"type":15},{"name":1180,"slug":1181,"type":15},{"name":1235,"slug":1236,"type":15},"Video","video","2026-08-28T15:09:07.765245",{"slug":1239,"name":1239,"fn":1240,"description":1241,"org":1242,"tags":1243,"stars":25,"repoUrl":26,"updatedAt":1249},"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},[1244,1245,1246],{"name":1177,"slug":1178,"type":15},{"name":1183,"slug":1184,"type":15},{"name":1247,"slug":1248,"type":15},"Photography","photography","2026-08-28T15:09:10.386974",499,{"items":1252,"total":1453},[1253,1274,1297,1314,1330,1349,1368,1382,1398,1412,1424,1437],{"slug":1254,"name":1254,"fn":1255,"description":1256,"org":1257,"tags":1258,"stars":1271,"repoUrl":1272,"updatedAt":1273},"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},[1259,1262,1265,1268],{"name":1260,"slug":1261,"type":15},"Documents","documents",{"name":1263,"slug":1264,"type":15},"Healthcare","healthcare",{"name":1266,"slug":1267,"type":15},"Insurance","insurance",{"name":1269,"slug":1270,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-08-02T05:48:07.395855",{"slug":1275,"name":1275,"fn":1276,"description":1277,"org":1278,"tags":1279,"stars":1294,"repoUrl":1295,"updatedAt":1296},"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},[1280,1283,1285,1288,1291],{"name":1281,"slug":1282,"type":15},".NET","dotnet",{"name":1284,"slug":1275,"type":15},"ASP.NET Core",{"name":1286,"slug":1287,"type":15},"Blazor","blazor",{"name":1289,"slug":1290,"type":15},"C#","csharp",{"name":1292,"slug":1293,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":1298,"name":1298,"fn":1299,"description":1300,"org":1301,"tags":1302,"stars":1294,"repoUrl":1295,"updatedAt":1313},"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},[1303,1306,1309,1312],{"name":1304,"slug":1305,"type":15},"Apps SDK","apps-sdk",{"name":1307,"slug":1308,"type":15},"ChatGPT","chatgpt",{"name":1310,"slug":1311,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":1315,"name":1315,"fn":1316,"description":1317,"org":1318,"tags":1319,"stars":1294,"repoUrl":1295,"updatedAt":1329},"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},[1320,1323,1326],{"name":1321,"slug":1322,"type":15},"API Development","api-development",{"name":1324,"slug":1325,"type":15},"CLI","cli",{"name":1327,"slug":1328,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":1331,"name":1331,"fn":1332,"description":1333,"org":1334,"tags":1335,"stars":1294,"repoUrl":1295,"updatedAt":1348},"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},[1336,1339,1342,1345],{"name":1337,"slug":1338,"type":15},"Cloudflare","cloudflare",{"name":1340,"slug":1341,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":1343,"slug":1344,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":1346,"slug":1347,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":1350,"name":1350,"fn":1351,"description":1352,"org":1353,"tags":1354,"stars":1294,"repoUrl":1295,"updatedAt":1367},"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},[1355,1358,1361,1364],{"name":1356,"slug":1357,"type":15},"Productivity","productivity",{"name":1359,"slug":1360,"type":15},"Project Management","project-management",{"name":1362,"slug":1363,"type":15},"Strategy","strategy",{"name":1365,"slug":1366,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":1369,"name":1369,"fn":1370,"description":1371,"org":1372,"tags":1373,"stars":1294,"repoUrl":1295,"updatedAt":1381},"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},[1374,1375,1377,1380],{"name":1167,"slug":1168,"type":15},{"name":1376,"slug":1369,"type":15},"Figma",{"name":1378,"slug":1379,"type":15},"Frontend","frontend",{"name":1310,"slug":1311,"type":15},"2026-04-12T05:06:47.939943",{"slug":1383,"name":1383,"fn":1384,"description":1385,"org":1386,"tags":1387,"stars":1294,"repoUrl":1295,"updatedAt":1397},"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},[1388,1389,1392,1393,1394],{"name":1167,"slug":1168,"type":15},{"name":1390,"slug":1391,"type":15},"Design System","design-system",{"name":1376,"slug":1369,"type":15},{"name":1378,"slug":1379,"type":15},{"name":1395,"slug":1396,"type":15},"UI Components","ui-components","2026-05-10T05:59:52.971881",{"slug":1399,"name":1399,"fn":1400,"description":1401,"org":1402,"tags":1403,"stars":1294,"repoUrl":1295,"updatedAt":1411},"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},[1404,1405,1406,1409,1410],{"name":1167,"slug":1168,"type":15},{"name":1390,"slug":1391,"type":15},{"name":1407,"slug":1408,"type":15},"Documentation","documentation",{"name":1376,"slug":1369,"type":15},{"name":1378,"slug":1379,"type":15},"2026-05-16T06:07:47.821474",{"slug":1413,"name":1413,"fn":1414,"description":1415,"org":1416,"tags":1417,"stars":1294,"repoUrl":1295,"updatedAt":1423},"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},[1418,1419,1420,1421,1422],{"name":1167,"slug":1168,"type":15},{"name":1376,"slug":1369,"type":15},{"name":1378,"slug":1379,"type":15},{"name":1395,"slug":1396,"type":15},{"name":1292,"slug":1293,"type":15},"2026-05-16T06:07:40.583615",{"slug":1425,"name":1425,"fn":1426,"description":1427,"org":1428,"tags":1429,"stars":1294,"repoUrl":1295,"updatedAt":1436},"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},[1430,1433,1434,1435],{"name":1431,"slug":1432,"type":15},"Animation","animation",{"name":1327,"slug":1328,"type":15},{"name":1177,"slug":1178,"type":15},{"name":1167,"slug":1168,"type":15},"2026-05-02T05:31:48.48485",{"slug":1438,"name":1438,"fn":1439,"description":1440,"org":1441,"tags":1442,"stars":1294,"repoUrl":1295,"updatedAt":1452},"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},[1443,1444,1445,1448,1451],{"name":1177,"slug":1178,"type":15},{"name":1167,"slug":1168,"type":15},{"name":1446,"slug":1447,"type":15},"Image Generation","image-generation",{"name":1449,"slug":1450,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",578]