[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-earnings-deep-dive":3,"mdc-qy4w9y-key":33,"related-org-openai-earnings-deep-dive":913,"related-repo-openai-earnings-deep-dive":1120},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":22,"repoUrl":23,"updatedAt":24,"license":25,"forks":26,"topics":27,"repo":28,"sourceUrl":31,"mdContent":32},"earnings-deep-dive","analyze public company earnings reports","Use when analyzing public-company earnings after results, guidance, transcript, or call commentary. Do not use for pre-print previews.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"openai","OpenAI","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fopenai.png",[12,16,19],{"name":13,"slug":14,"type":15},"Analysis","analysis","tag",{"name":17,"slug":18,"type":15},"Finance","finance",{"name":20,"slug":21,"type":15},"Equity Research","equity-research",4888,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-08-28T15:09:11.954689",null,661,[],{"repoUrl":23,"stars":22,"forks":26,"topics":29,"description":30},[],"OpenAI Plugins","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fpublic-equity-investing\u002Fskills\u002Fearnings-deep-dive","---\nname: earnings-deep-dive\ndescription: Use when analyzing public-company earnings after results, guidance, transcript, or call commentary. Do not use for pre-print previews.\n---\n\n# Earnings Deep Dive\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- `Earnings Transcripts & Events`\n- `Company Filings & IR`\n- `Market Data & Estimates`\n- `Portfolio Models & Trackers`\n- `Internal Research`\n\n## Internal Support\n\nWhen this workflow needs rendering, evidence\u002Fdata preparation, style, or sector context, route support through the visible `public-equity-investing` router and its bundled internal playbooks. Route workbook or model QA through the visible `model-audit-tieout` workflow.\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 an explicit `deep dive`, `full report`, or reusable\u002Fsource-heavy post-print package, resolve presentation to a polished standalone HTML post-earnings report unless the user requests another format, a quick\u002Fno-file answer, or workbook\u002Fmodel-update output. In interactive runs, ask only remaining material questions such as depth, audience\u002Fuse, or focus; narrower post-result questions continue to use normal intake. Reuse resolved preferences in downstream steps; when acting only as input to an owning workflow, do not re-prompt.\n\nProduce a decision-grade, audit-ready post-print package after results are available.\n\nDefault to the full post-print package. Chat can be the surface for narrow or explicitly no-file asks, but an explicit deep dive, full report, or source-heavy reusable post-print package should be a polished standalone HTML post-earnings report following `..\u002F..\u002Fshared\u002Fhtml-artifact-standard.md`. Use `dashboard-builder` only for the optional standardized-dashboard route below. Use deterministic file mode only when the user supplies `plan.json`, normalized CSVs, model-update inputs, or explicitly asks for files.\n\n## Route\n\n- `full deep dive`: default analytical route for post-earnings deep dives, earnings-print analysis, and investor-facing post-print questions. An explicit deep dive, full report, or reusable\u002Fsource-heavy package defaults to polished standalone HTML.\n- `one-page tear sheet`: use only when the user explicitly asks for a summary, one-pager, quick read, brief, or TL;DR.\n- `audit-ready model update`: use only when the user supplies or references a model\u002Fworkbook, driver registry, output registry, normalized CSVs, model-update inputs, or explicit data to update a model.\n- `quote and debate map`: standalone only when the user asks only for transcript quotes\u002Fdebate; otherwise include it inside the full deep dive.\n- `standardized dashboard`: only when the user explicitly asks for a standardized dashboard, reusable dashboard template, PM cockpit, tabbed dashboard, or structured payload-driven render, keep this skill as the analysis owner and hand the resulting `public_equity_investing_dashboard.v1` payload to `dashboard-builder`. Use `references\u002FDASHBOARD_PACK.md` for module mapping.\n- `deterministic file mode`: validate inputs, run shipped scripts, fail QA on unresolved user-facing placeholders, and disclose packet versus workbook-apply path.\n\nLoad `references\u002FREFERENCE_ROUTER.md` first, then only the route-specific reference needed for the selected artifact.\n\n## Non-Negotiables\n\n- Never invent numbers, quotes, guidance, definitions, accounting facts, estimate timestamps, source tags, or catalyst dates.\n- Use official filings\u002Freleases before decks and transcripts; transcripts support narrative and call-only guidance, not primary GAAP numbers.\n- Every reported number and every quote needs a source tag; analyst-derived numbers need formula\u002Fassumption and confidence.\n- Full deep dives must include transcript evidence and a debate-map treatment when transcript evidence is available. If no transcript is available, show a concise visible limitation labelled `transcript not provided` or `transcript source not found` and list the exact missing artifact; do not render an empty Q&A table.\n- For transcript Q&A, capture questioner name, firm if available, answering executive, topic, section, source tag, why it matters, bull\u002Fbear implication, and falsifier\u002Fnext check.\n- Keep GAAP\u002Fnon-GAAP, reported\u002Fconstant-currency, company-guided\u002Fanalyst-derived, units\u002Fscale, and unavailable-data labels explicit.\n- Always run an EPS quality screen: ask whether headline EPS could misstate recurring operating performance. Include a full EPS quality \u002F ex-gain bridge when GAAP EPS surprise is distorted by below-the-line, tax, mark-to-market, equity-investment, FX, restructuring, litigation, asset-sale, impairment, share-count, or other non-recurring items; otherwise state that no material EPS-quality trigger was identified from available sources.\n- Full deep dives must include quarterly key metrics and growth trajectory using the issuer's actual business drivers, not only generic revenue\u002FEPS\u002Fmargin. Use sector-context-overlay when the company-specific KPI set is not obvious.\n- For HTML reports or standardized dashboard handoffs, include earnings visualizations when source-backed data exists: quarterly revenue, gross profit, net income, and the best source-backed profitability margin history; estimated EPS versus actual EPS for the past five quarters on a consistent basis; and equity-price history annotated with material market events. Omit any chart whose required series is missing, stale, or not comparable, and surface that gap clearly.\n- Treat margin selection as an analytical decision, not a template default. Default to net margin only when net income is a fair recurring-profitability proxy. Prefer operating margin when net income is distorted by below-the-line, tax, mark-to-market, equity-investment, FX, restructuring, litigation, asset-sale, impairment, or other non-recurring items. Prefer adjusted operating margin, EBITDA margin, contribution margin, or FCF margin when that is the issuer's source-backed investor KPI. For dashboard payloads, set `financial_trend_chart.data.margin_metric`, `margin_label`, and `margin_rationale` whenever the line is not plain net margin.\n- Rank highlight\u002Fsnapshot metrics by investor salience. A growth rate, acceleration, surprise %, guide delta, backlog growth, margin inflection, or clean\u002Fnormalized metric should be the tile value when it better explains the stock-moving point than the absolute reported amount; put the absolute amount in the detail.\n- Full deep dives must include read-throughs when the print, filing, transcript, or management interviews mention customers, suppliers, peers, competitors, platforms, channels, commodities, regions, or adjacent industries.\n- Full deep dives must include major news coverage and market events when recent or upcoming events change the interpretation of the print, guidance, estimate revisions, multiple, risk, positioning, or read-throughs. Scan the last quarter, last twelve months, and forward-looking anticipated events; cite every event and label uncertain windows.\n- Capture catalysts learned from the release, filing, transcript, Q&A, and management interviews. Separate dated catalysts from inferred monitoring windows.\n- Use precise absence labels: `not guided`, `not disclosed`, `not provided`, `source not provided`, or `MISSING: \u003Cdependency>` only where appropriate.\n- Generated Markdown support notes must not contain unresolved bracket tokens, `TODO`, or authoring placeholders.\n\n## Chat Contract\n\nDefault sections for full deep dive: setup\u002Fsource posture, dense executive summary, PM bottom line, granular beat\u002Fmiss or guide-versus-bar, EPS quality screen, quarterly key metrics, growth trajectory, guidance delta\u002Fdeep dive, what changed, revision\u002Fstock setup, load-bearing drivers, transcript quote\u002FQ&A and debate map, read-throughs, major news and market events, model\u002Fthesis impact, catalysts\u002Fwatch list\u002Ffalsifiers, source limitations, and open questions. For investor-facing prompts add thesis change, likely estimate revision, stock\u002Fvaluation skew, and next catalyst.\n\nUse the evidence pack that supports the selected artifact without shrinking the user-facing analysis:\n\n- Full deep dive: release\u002Ffiling, deck\u002Fprepared remarks, transcript, estimates, and prior-quarter\u002Fprior-guide sources where available.\n- Explicit summary or one-page tear sheet: release or 8-K, deck if available, estimate source, and transcript only for high-signal quotes.\n- Audit-ready model update: release\u002Ffiling\u002Fdeck, estimate set, prior guide, and model\u002Fworkbook or normalized driver inputs supplied or referenced by the user.\n- Standalone quote\u002Fdebate: transcript plus release\u002Fdeck to cross-check numeric claims.\n\n## HTML Guidance\n\nFor a substantive HTML deep dive, load `..\u002F..\u002Fshared\u002Fhtml-artifact-standard.md` and let the company-specific investment debate determine the layout.\n\n- Title the artifact as a post-earnings deep dive identifying the company, ticker, and reported period.\n- Start with a direct verdict answering the investor's question, 4-6 high-signal metric tiles, one compact decision box, and a quality-of-print bridge separating headline results from recurring operating evidence.\n- Use only distinct decision-relevant tiles. Prefer 4-5 tiles when additional metrics repeat the same analytical point; combine related buyback, leverage, interest-expense, or cash-flow signals into one capital-allocation-quality tile when that improves readability.\n- Put supporting analysis below that first read: beat\u002Fmiss and guidance, EPS quality, company-specific growth drivers, capital allocation, valuation\u002Fstock setup, catalysts, falsifiers, source limitations, and evidence ledger as relevant.\n- Give each first-read element a distinct job: the verdict answers the investment question and explains why; the decision box states thesis change, estimate direction, valuation\u002Fstock skew, action discipline, and next proof point; metric tiles show evidence rather than restating the verdict; the quality-of-print bridge reconciles headline results to recurring equity value. Do not repeat the same conclusion across these elements.\n- Describe evidence posture in reader-facing terms by naming sources obtained and important confirmations still missing, for example `Company release reviewed; filing and transcript confirmation pending`. Avoid internal-sounding quality labels such as `research-grade` in the visible artifact.\n- Include transcript Q&A, read-throughs, market-events tables, scenario sections, and charts only when substantive and evidence-supported. A missing transcript should be a concise limitation callout, not an empty table.\n- Do not render blank scenario cards, placeholder modules, or visible source cells marked unsourced when the claim has a cited source.\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: release and filing numbers, transcript\u002FQ&A, estimates and guidance, model\u002Fthesis impact, and source QA. Keep this skill as the lead: reconcile conflicts, source labels, assumptions, open items, final QA, and the user-facing answer.\n\n\n## Deterministic Contract\n\nUse only when requested or file\u002Fmodel inputs are supplied:\n\n- `scripts\u002Fvalidate_plan.py`\n- `scripts\u002Fvalidate_normalized_inputs.py`\n- `scripts\u002Frun_plan.py`\n- `scripts\u002Fapply_model_updates.py`\n- `scripts\u002Fmodel_diff.py`\n- `scripts\u002Fverify_tearsheet.py`\n\nIf workbook apply fails or is unsafe, deliver a driver update packet and explain the limitation. The bundled plan defaults to packet\u002Fdry-run mode and writes outside the skill tree.\n\n## Standardized Dashboard Handoff\n\nUse `dashboard-builder` only when the user explicitly selects the standardized dashboard, reusable dashboard-template, or structured payload-driven rendering path. This skill still owns the analysis and maps it into `references\u002FDASHBOARD_PACK.md`; prefer `layout: \"single_page\"` with sticky contents for full PM diligence dashboards unless the user explicitly asks for tabs. Ordinary standalone HTML deep dives use the flexible HTML guidance above rather than a fixed module inventory.\n\n## Public Equity PM Judgment Layer\n\nFor substantial post-print work, load `shared\u002Fpm-judgment-heuristics.md` before finalizing. Audience modes: `long_only_pm`, `long_short_hf`, `sell_side_research`, `etf_index_diligence`, `public_equity_diligence`.\n\nDefault PM question: did the quarter change the thesis, estimates, valuation support, or sizing?\n\nRequired PM judgment:\n- Lead with thesis change, estimate revision direction, valuation support, and position action.\n- Bridge headline versus clean result, guide delta, quality of beat\u002Fmiss, transcript evidence, management credibility, and next falsifier.\n- Separate reported facts, management claims, consensus, market data, model output, assumptions, and PM judgment.\n- For sell-side mode, add rating\u002Ftarget implications and risk-to-rating. For hedge fund mode, add add\u002Ftrim\u002Fcover triggers.\n",{"data":34,"body":35},{"name":4,"description":6},{"type":36,"children":37},"root",[38,46,53,60,91,97,148,154,159,209,215,236,242,278,283,312,318,409,421,427,593,599,604,609,632,638,650,709,715,720,726,731,788,793,799,826,832,880,885,890],{"type":39,"tag":40,"props":41,"children":42},"element","h1",{"id":4},[43],{"type":44,"value":45},"text","Earnings Deep Dive",{"type":39,"tag":47,"props":48,"children":50},"h2",{"id":49},"skill-configuration",[51],{"type":44,"value":52},"Skill Configuration",{"type":39,"tag":54,"props":55,"children":57},"h3",{"id":56},"common-skill-instructions",[58],{"type":44,"value":59},"Common Skill Instructions",{"type":39,"tag":61,"props":62,"children":63},"p",{},[64,66,73,75,81,83,89],{"type":44,"value":65},"MANDATORY: Before searching connectors, retrieving evidence, or drafting output, read and apply the shared runtime contract in ",{"type":39,"tag":67,"props":68,"children":70},"code",{"className":69},[],[71],{"type":44,"value":72},"..\u002Fpublic-equity-investing\u002FSKILL.md## Cross-Skill Runtime Contract",{"type":44,"value":74},". Then check the router skill map and ",{"type":39,"tag":67,"props":76,"children":78},{"className":77},[],[79],{"type":44,"value":80},"..\u002F..\u002Fshared\u002Fplugin-routing-playbook.md",{"type":44,"value":82}," 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":39,"tag":67,"props":84,"children":86},{"className":85},[],[87],{"type":44,"value":88},"..\u002Fuser-context\u002FSKILL.md",{"type":44,"value":90},".",{"type":39,"tag":54,"props":92,"children":94},{"id":93},"source-resolution",[95],{"type":44,"value":96},"Source Resolution",{"type":39,"tag":61,"props":98,"children":99},{},[100,102,108,110,116,118,124,125,131,132,138,140,146],{"type":44,"value":101},"Load ",{"type":39,"tag":67,"props":103,"children":105},{"className":104},[],[106],{"type":44,"value":107},"..\u002F..\u002Fshared\u002Fworkflow-source-resolution.md",{"type":44,"value":109},". Resolve only the categories needed for this workflow: ",{"type":39,"tag":67,"props":111,"children":113},{"className":112},[],[114],{"type":44,"value":115},"company_filings_ir",{"type":44,"value":117},", ",{"type":39,"tag":67,"props":119,"children":121},{"className":120},[],[122],{"type":44,"value":123},"earnings_transcripts_presentations",{"type":44,"value":117},{"type":39,"tag":67,"props":126,"children":128},{"className":127},[],[129],{"type":44,"value":130},"internal_research",{"type":44,"value":117},{"type":39,"tag":67,"props":133,"children":135},{"className":134},[],[136],{"type":44,"value":137},"portfolio_models_trackers",{"type":44,"value":139},", and ",{"type":39,"tag":67,"props":141,"children":143},{"className":142},[],[144],{"type":44,"value":145},"market_data_estimates",{"type":44,"value":147},". Use the shared runtime contract to map each attempted category to an available app, connector, file, export, or user-provided input.",{"type":39,"tag":47,"props":149,"children":151},{"id":150},"relevant-dependency-categories",[152],{"type":44,"value":153},"Relevant Dependency Categories",{"type":39,"tag":61,"props":155,"children":156},{},[157],{"type":44,"value":158},"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":39,"tag":160,"props":161,"children":162},"ul",{},[163,173,182,191,200],{"type":39,"tag":164,"props":165,"children":166},"li",{},[167],{"type":39,"tag":67,"props":168,"children":170},{"className":169},[],[171],{"type":44,"value":172},"Earnings Transcripts & Events",{"type":39,"tag":164,"props":174,"children":175},{},[176],{"type":39,"tag":67,"props":177,"children":179},{"className":178},[],[180],{"type":44,"value":181},"Company Filings & IR",{"type":39,"tag":164,"props":183,"children":184},{},[185],{"type":39,"tag":67,"props":186,"children":188},{"className":187},[],[189],{"type":44,"value":190},"Market Data & Estimates",{"type":39,"tag":164,"props":192,"children":193},{},[194],{"type":39,"tag":67,"props":195,"children":197},{"className":196},[],[198],{"type":44,"value":199},"Portfolio Models & Trackers",{"type":39,"tag":164,"props":201,"children":202},{},[203],{"type":39,"tag":67,"props":204,"children":206},{"className":205},[],[207],{"type":44,"value":208},"Internal Research",{"type":39,"tag":47,"props":210,"children":212},{"id":211},"internal-support",[213],{"type":44,"value":214},"Internal Support",{"type":39,"tag":61,"props":216,"children":217},{},[218,220,226,228,234],{"type":44,"value":219},"When this workflow needs rendering, evidence\u002Fdata preparation, style, or sector context, route support through the visible ",{"type":39,"tag":67,"props":221,"children":223},{"className":222},[],[224],{"type":44,"value":225},"public-equity-investing",{"type":44,"value":227}," router and its bundled internal playbooks. Route workbook or model QA through the visible ",{"type":39,"tag":67,"props":229,"children":231},{"className":230},[],[232],{"type":44,"value":233},"model-audit-tieout",{"type":44,"value":235}," workflow.",{"type":39,"tag":47,"props":237,"children":239},{"id":238},"deliverable-intake",[240],{"type":44,"value":241},"Deliverable Intake",{"type":39,"tag":61,"props":243,"children":244},{},[245,247,253,255,261,263,269,270,276],{"type":44,"value":246},"Before source gathering or analysis for a new substantive hero deliverable, load ",{"type":39,"tag":67,"props":248,"children":250},{"className":249},[],[251],{"type":44,"value":252},"..\u002F..\u002Fshared\u002Fdeliverable-intake-policy.md",{"type":44,"value":254}," and use its adaptive ",{"type":39,"tag":67,"props":256,"children":258},{"className":257},[],[259],{"type":44,"value":260},"request_user_input",{"type":44,"value":262}," preflight for materially unresolved format, depth, audience\u002Fuse, or focus choices. For an explicit ",{"type":39,"tag":67,"props":264,"children":266},{"className":265},[],[267],{"type":44,"value":268},"deep dive",{"type":44,"value":117},{"type":39,"tag":67,"props":271,"children":273},{"className":272},[],[274],{"type":44,"value":275},"full report",{"type":44,"value":277},", or reusable\u002Fsource-heavy post-print package, resolve presentation to a polished standalone HTML post-earnings report unless the user requests another format, a quick\u002Fno-file answer, or workbook\u002Fmodel-update output. In interactive runs, ask only remaining material questions such as depth, audience\u002Fuse, or focus; narrower post-result questions continue to use normal intake. Reuse resolved preferences in downstream steps; when acting only as input to an owning workflow, do not re-prompt.",{"type":39,"tag":61,"props":279,"children":280},{},[281],{"type":44,"value":282},"Produce a decision-grade, audit-ready post-print package after results are available.",{"type":39,"tag":61,"props":284,"children":285},{},[286,288,294,296,302,304,310],{"type":44,"value":287},"Default to the full post-print package. Chat can be the surface for narrow or explicitly no-file asks, but an explicit deep dive, full report, or source-heavy reusable post-print package should be a polished standalone HTML post-earnings report following ",{"type":39,"tag":67,"props":289,"children":291},{"className":290},[],[292],{"type":44,"value":293},"..\u002F..\u002Fshared\u002Fhtml-artifact-standard.md",{"type":44,"value":295},". Use ",{"type":39,"tag":67,"props":297,"children":299},{"className":298},[],[300],{"type":44,"value":301},"dashboard-builder",{"type":44,"value":303}," only for the optional standardized-dashboard route below. Use deterministic file mode only when the user supplies ",{"type":39,"tag":67,"props":305,"children":307},{"className":306},[],[308],{"type":44,"value":309},"plan.json",{"type":44,"value":311},", normalized CSVs, model-update inputs, or explicitly asks for files.",{"type":39,"tag":47,"props":313,"children":315},{"id":314},"route",[316],{"type":44,"value":317},"Route",{"type":39,"tag":160,"props":319,"children":320},{},[321,332,343,354,365,398],{"type":39,"tag":164,"props":322,"children":323},{},[324,330],{"type":39,"tag":67,"props":325,"children":327},{"className":326},[],[328],{"type":44,"value":329},"full deep dive",{"type":44,"value":331},": default analytical route for post-earnings deep dives, earnings-print analysis, and investor-facing post-print questions. An explicit deep dive, full report, or reusable\u002Fsource-heavy package defaults to polished standalone HTML.",{"type":39,"tag":164,"props":333,"children":334},{},[335,341],{"type":39,"tag":67,"props":336,"children":338},{"className":337},[],[339],{"type":44,"value":340},"one-page tear sheet",{"type":44,"value":342},": use only when the user explicitly asks for a summary, one-pager, quick read, brief, or TL;DR.",{"type":39,"tag":164,"props":344,"children":345},{},[346,352],{"type":39,"tag":67,"props":347,"children":349},{"className":348},[],[350],{"type":44,"value":351},"audit-ready model update",{"type":44,"value":353},": use only when the user supplies or references a model\u002Fworkbook, driver registry, output registry, normalized CSVs, model-update inputs, or explicit data to update a model.",{"type":39,"tag":164,"props":355,"children":356},{},[357,363],{"type":39,"tag":67,"props":358,"children":360},{"className":359},[],[361],{"type":44,"value":362},"quote and debate map",{"type":44,"value":364},": standalone only when the user asks only for transcript quotes\u002Fdebate; otherwise include it inside the full deep dive.",{"type":39,"tag":164,"props":366,"children":367},{},[368,374,376,382,384,389,390,396],{"type":39,"tag":67,"props":369,"children":371},{"className":370},[],[372],{"type":44,"value":373},"standardized dashboard",{"type":44,"value":375},": only when the user explicitly asks for a standardized dashboard, reusable dashboard template, PM cockpit, tabbed dashboard, or structured payload-driven render, keep this skill as the analysis owner and hand the resulting ",{"type":39,"tag":67,"props":377,"children":379},{"className":378},[],[380],{"type":44,"value":381},"public_equity_investing_dashboard.v1",{"type":44,"value":383}," payload to ",{"type":39,"tag":67,"props":385,"children":387},{"className":386},[],[388],{"type":44,"value":301},{"type":44,"value":295},{"type":39,"tag":67,"props":391,"children":393},{"className":392},[],[394],{"type":44,"value":395},"references\u002FDASHBOARD_PACK.md",{"type":44,"value":397}," for module mapping.",{"type":39,"tag":164,"props":399,"children":400},{},[401,407],{"type":39,"tag":67,"props":402,"children":404},{"className":403},[],[405],{"type":44,"value":406},"deterministic file mode",{"type":44,"value":408},": validate inputs, run shipped scripts, fail QA on unresolved user-facing placeholders, and disclose packet versus workbook-apply path.",{"type":39,"tag":61,"props":410,"children":411},{},[412,413,419],{"type":44,"value":101},{"type":39,"tag":67,"props":414,"children":416},{"className":415},[],[417],{"type":44,"value":418},"references\u002FREFERENCE_ROUTER.md",{"type":44,"value":420}," first, then only the route-specific reference needed for the selected artifact.",{"type":39,"tag":47,"props":422,"children":424},{"id":423},"non-negotiables",[425],{"type":44,"value":426},"Non-Negotiables",{"type":39,"tag":160,"props":428,"children":429},{},[430,435,440,445,466,471,476,481,486,491,518,523,528,533,538,580],{"type":39,"tag":164,"props":431,"children":432},{},[433],{"type":44,"value":434},"Never invent numbers, quotes, guidance, definitions, accounting facts, estimate timestamps, source tags, or catalyst dates.",{"type":39,"tag":164,"props":436,"children":437},{},[438],{"type":44,"value":439},"Use official filings\u002Freleases before decks and transcripts; transcripts support narrative and call-only guidance, not primary GAAP numbers.",{"type":39,"tag":164,"props":441,"children":442},{},[443],{"type":44,"value":444},"Every reported number and every quote needs a source tag; analyst-derived numbers need formula\u002Fassumption and confidence.",{"type":39,"tag":164,"props":446,"children":447},{},[448,450,456,458,464],{"type":44,"value":449},"Full deep dives must include transcript evidence and a debate-map treatment when transcript evidence is available. If no transcript is available, show a concise visible limitation labelled ",{"type":39,"tag":67,"props":451,"children":453},{"className":452},[],[454],{"type":44,"value":455},"transcript not provided",{"type":44,"value":457}," or ",{"type":39,"tag":67,"props":459,"children":461},{"className":460},[],[462],{"type":44,"value":463},"transcript source not found",{"type":44,"value":465}," and list the exact missing artifact; do not render an empty Q&A table.",{"type":39,"tag":164,"props":467,"children":468},{},[469],{"type":44,"value":470},"For transcript Q&A, capture questioner name, firm if available, answering executive, topic, section, source tag, why it matters, bull\u002Fbear implication, and falsifier\u002Fnext check.",{"type":39,"tag":164,"props":472,"children":473},{},[474],{"type":44,"value":475},"Keep GAAP\u002Fnon-GAAP, reported\u002Fconstant-currency, company-guided\u002Fanalyst-derived, units\u002Fscale, and unavailable-data labels explicit.",{"type":39,"tag":164,"props":477,"children":478},{},[479],{"type":44,"value":480},"Always run an EPS quality screen: ask whether headline EPS could misstate recurring operating performance. Include a full EPS quality \u002F ex-gain bridge when GAAP EPS surprise is distorted by below-the-line, tax, mark-to-market, equity-investment, FX, restructuring, litigation, asset-sale, impairment, share-count, or other non-recurring items; otherwise state that no material EPS-quality trigger was identified from available sources.",{"type":39,"tag":164,"props":482,"children":483},{},[484],{"type":44,"value":485},"Full deep dives must include quarterly key metrics and growth trajectory using the issuer's actual business drivers, not only generic revenue\u002FEPS\u002Fmargin. Use sector-context-overlay when the company-specific KPI set is not obvious.",{"type":39,"tag":164,"props":487,"children":488},{},[489],{"type":44,"value":490},"For HTML reports or standardized dashboard handoffs, include earnings visualizations when source-backed data exists: quarterly revenue, gross profit, net income, and the best source-backed profitability margin history; estimated EPS versus actual EPS for the past five quarters on a consistent basis; and equity-price history annotated with material market events. Omit any chart whose required series is missing, stale, or not comparable, and surface that gap clearly.",{"type":39,"tag":164,"props":492,"children":493},{},[494,496,502,503,509,510,516],{"type":44,"value":495},"Treat margin selection as an analytical decision, not a template default. Default to net margin only when net income is a fair recurring-profitability proxy. Prefer operating margin when net income is distorted by below-the-line, tax, mark-to-market, equity-investment, FX, restructuring, litigation, asset-sale, impairment, or other non-recurring items. Prefer adjusted operating margin, EBITDA margin, contribution margin, or FCF margin when that is the issuer's source-backed investor KPI. For dashboard payloads, set ",{"type":39,"tag":67,"props":497,"children":499},{"className":498},[],[500],{"type":44,"value":501},"financial_trend_chart.data.margin_metric",{"type":44,"value":117},{"type":39,"tag":67,"props":504,"children":506},{"className":505},[],[507],{"type":44,"value":508},"margin_label",{"type":44,"value":139},{"type":39,"tag":67,"props":511,"children":513},{"className":512},[],[514],{"type":44,"value":515},"margin_rationale",{"type":44,"value":517}," whenever the line is not plain net margin.",{"type":39,"tag":164,"props":519,"children":520},{},[521],{"type":44,"value":522},"Rank highlight\u002Fsnapshot metrics by investor salience. A growth rate, acceleration, surprise %, guide delta, backlog growth, margin inflection, or clean\u002Fnormalized metric should be the tile value when it better explains the stock-moving point than the absolute reported amount; put the absolute amount in the detail.",{"type":39,"tag":164,"props":524,"children":525},{},[526],{"type":44,"value":527},"Full deep dives must include read-throughs when the print, filing, transcript, or management interviews mention customers, suppliers, peers, competitors, platforms, channels, commodities, regions, or adjacent industries.",{"type":39,"tag":164,"props":529,"children":530},{},[531],{"type":44,"value":532},"Full deep dives must include major news coverage and market events when recent or upcoming events change the interpretation of the print, guidance, estimate revisions, multiple, risk, positioning, or read-throughs. Scan the last quarter, last twelve months, and forward-looking anticipated events; cite every event and label uncertain windows.",{"type":39,"tag":164,"props":534,"children":535},{},[536],{"type":44,"value":537},"Capture catalysts learned from the release, filing, transcript, Q&A, and management interviews. Separate dated catalysts from inferred monitoring windows.",{"type":39,"tag":164,"props":539,"children":540},{},[541,543,549,550,556,557,563,564,570,572,578],{"type":44,"value":542},"Use precise absence labels: ",{"type":39,"tag":67,"props":544,"children":546},{"className":545},[],[547],{"type":44,"value":548},"not guided",{"type":44,"value":117},{"type":39,"tag":67,"props":551,"children":553},{"className":552},[],[554],{"type":44,"value":555},"not disclosed",{"type":44,"value":117},{"type":39,"tag":67,"props":558,"children":560},{"className":559},[],[561],{"type":44,"value":562},"not provided",{"type":44,"value":117},{"type":39,"tag":67,"props":565,"children":567},{"className":566},[],[568],{"type":44,"value":569},"source not provided",{"type":44,"value":571},", or ",{"type":39,"tag":67,"props":573,"children":575},{"className":574},[],[576],{"type":44,"value":577},"MISSING: \u003Cdependency>",{"type":44,"value":579}," only where appropriate.",{"type":39,"tag":164,"props":581,"children":582},{},[583,585,591],{"type":44,"value":584},"Generated Markdown support notes must not contain unresolved bracket tokens, ",{"type":39,"tag":67,"props":586,"children":588},{"className":587},[],[589],{"type":44,"value":590},"TODO",{"type":44,"value":592},", or authoring placeholders.",{"type":39,"tag":47,"props":594,"children":596},{"id":595},"chat-contract",[597],{"type":44,"value":598},"Chat Contract",{"type":39,"tag":61,"props":600,"children":601},{},[602],{"type":44,"value":603},"Default sections for full deep dive: setup\u002Fsource posture, dense executive summary, PM bottom line, granular beat\u002Fmiss or guide-versus-bar, EPS quality screen, quarterly key metrics, growth trajectory, guidance delta\u002Fdeep dive, what changed, revision\u002Fstock setup, load-bearing drivers, transcript quote\u002FQ&A and debate map, read-throughs, major news and market events, model\u002Fthesis impact, catalysts\u002Fwatch list\u002Ffalsifiers, source limitations, and open questions. For investor-facing prompts add thesis change, likely estimate revision, stock\u002Fvaluation skew, and next catalyst.",{"type":39,"tag":61,"props":605,"children":606},{},[607],{"type":44,"value":608},"Use the evidence pack that supports the selected artifact without shrinking the user-facing analysis:",{"type":39,"tag":160,"props":610,"children":611},{},[612,617,622,627],{"type":39,"tag":164,"props":613,"children":614},{},[615],{"type":44,"value":616},"Full deep dive: release\u002Ffiling, deck\u002Fprepared remarks, transcript, estimates, and prior-quarter\u002Fprior-guide sources where available.",{"type":39,"tag":164,"props":618,"children":619},{},[620],{"type":44,"value":621},"Explicit summary or one-page tear sheet: release or 8-K, deck if available, estimate source, and transcript only for high-signal quotes.",{"type":39,"tag":164,"props":623,"children":624},{},[625],{"type":44,"value":626},"Audit-ready model update: release\u002Ffiling\u002Fdeck, estimate set, prior guide, and model\u002Fworkbook or normalized driver inputs supplied or referenced by the user.",{"type":39,"tag":164,"props":628,"children":629},{},[630],{"type":44,"value":631},"Standalone quote\u002Fdebate: transcript plus release\u002Fdeck to cross-check numeric claims.",{"type":39,"tag":47,"props":633,"children":635},{"id":634},"html-guidance",[636],{"type":44,"value":637},"HTML Guidance",{"type":39,"tag":61,"props":639,"children":640},{},[641,643,648],{"type":44,"value":642},"For a substantive HTML deep dive, load ",{"type":39,"tag":67,"props":644,"children":646},{"className":645},[],[647],{"type":44,"value":293},{"type":44,"value":649}," and let the company-specific investment debate determine the layout.",{"type":39,"tag":160,"props":651,"children":652},{},[653,658,663,668,673,678,699,704],{"type":39,"tag":164,"props":654,"children":655},{},[656],{"type":44,"value":657},"Title the artifact as a post-earnings deep dive identifying the company, ticker, and reported period.",{"type":39,"tag":164,"props":659,"children":660},{},[661],{"type":44,"value":662},"Start with a direct verdict answering the investor's question, 4-6 high-signal metric tiles, one compact decision box, and a quality-of-print bridge separating headline results from recurring operating evidence.",{"type":39,"tag":164,"props":664,"children":665},{},[666],{"type":44,"value":667},"Use only distinct decision-relevant tiles. Prefer 4-5 tiles when additional metrics repeat the same analytical point; combine related buyback, leverage, interest-expense, or cash-flow signals into one capital-allocation-quality tile when that improves readability.",{"type":39,"tag":164,"props":669,"children":670},{},[671],{"type":44,"value":672},"Put supporting analysis below that first read: beat\u002Fmiss and guidance, EPS quality, company-specific growth drivers, capital allocation, valuation\u002Fstock setup, catalysts, falsifiers, source limitations, and evidence ledger as relevant.",{"type":39,"tag":164,"props":674,"children":675},{},[676],{"type":44,"value":677},"Give each first-read element a distinct job: the verdict answers the investment question and explains why; the decision box states thesis change, estimate direction, valuation\u002Fstock skew, action discipline, and next proof point; metric tiles show evidence rather than restating the verdict; the quality-of-print bridge reconciles headline results to recurring equity value. Do not repeat the same conclusion across these elements.",{"type":39,"tag":164,"props":679,"children":680},{},[681,683,689,691,697],{"type":44,"value":682},"Describe evidence posture in reader-facing terms by naming sources obtained and important confirmations still missing, for example ",{"type":39,"tag":67,"props":684,"children":686},{"className":685},[],[687],{"type":44,"value":688},"Company release reviewed; filing and transcript confirmation pending",{"type":44,"value":690},". Avoid internal-sounding quality labels such as ",{"type":39,"tag":67,"props":692,"children":694},{"className":693},[],[695],{"type":44,"value":696},"research-grade",{"type":44,"value":698}," in the visible artifact.",{"type":39,"tag":164,"props":700,"children":701},{},[702],{"type":44,"value":703},"Include transcript Q&A, read-throughs, market-events tables, scenario sections, and charts only when substantive and evidence-supported. A missing transcript should be a concise limitation callout, not an empty table.",{"type":39,"tag":164,"props":705,"children":706},{},[707],{"type":44,"value":708},"Do not render blank scenario cards, placeholder modules, or visible source cells marked unsourced when the claim has a cited source.",{"type":39,"tag":47,"props":710,"children":712},{"id":711},"sub-agent-decomposition",[713],{"type":44,"value":714},"Sub-agent decomposition",{"type":39,"tag":61,"props":716,"children":717},{},[718],{"type":44,"value":719},"For complex medium\u002Flarge requests, use sub-agents where available; otherwise emulate the split as named workstreams. Suggested lanes: release and filing numbers, transcript\u002FQ&A, estimates and guidance, model\u002Fthesis impact, and source QA. Keep this skill as the lead: reconcile conflicts, source labels, assumptions, open items, final QA, and the user-facing answer.",{"type":39,"tag":47,"props":721,"children":723},{"id":722},"deterministic-contract",[724],{"type":44,"value":725},"Deterministic Contract",{"type":39,"tag":61,"props":727,"children":728},{},[729],{"type":44,"value":730},"Use only when requested or file\u002Fmodel inputs are supplied:",{"type":39,"tag":160,"props":732,"children":733},{},[734,743,752,761,770,779],{"type":39,"tag":164,"props":735,"children":736},{},[737],{"type":39,"tag":67,"props":738,"children":740},{"className":739},[],[741],{"type":44,"value":742},"scripts\u002Fvalidate_plan.py",{"type":39,"tag":164,"props":744,"children":745},{},[746],{"type":39,"tag":67,"props":747,"children":749},{"className":748},[],[750],{"type":44,"value":751},"scripts\u002Fvalidate_normalized_inputs.py",{"type":39,"tag":164,"props":753,"children":754},{},[755],{"type":39,"tag":67,"props":756,"children":758},{"className":757},[],[759],{"type":44,"value":760},"scripts\u002Frun_plan.py",{"type":39,"tag":164,"props":762,"children":763},{},[764],{"type":39,"tag":67,"props":765,"children":767},{"className":766},[],[768],{"type":44,"value":769},"scripts\u002Fapply_model_updates.py",{"type":39,"tag":164,"props":771,"children":772},{},[773],{"type":39,"tag":67,"props":774,"children":776},{"className":775},[],[777],{"type":44,"value":778},"scripts\u002Fmodel_diff.py",{"type":39,"tag":164,"props":780,"children":781},{},[782],{"type":39,"tag":67,"props":783,"children":785},{"className":784},[],[786],{"type":44,"value":787},"scripts\u002Fverify_tearsheet.py",{"type":39,"tag":61,"props":789,"children":790},{},[791],{"type":44,"value":792},"If workbook apply fails or is unsafe, deliver a driver update packet and explain the limitation. The bundled plan defaults to packet\u002Fdry-run mode and writes outside the skill tree.",{"type":39,"tag":47,"props":794,"children":796},{"id":795},"standardized-dashboard-handoff",[797],{"type":44,"value":798},"Standardized Dashboard Handoff",{"type":39,"tag":61,"props":800,"children":801},{},[802,804,809,811,816,818,824],{"type":44,"value":803},"Use ",{"type":39,"tag":67,"props":805,"children":807},{"className":806},[],[808],{"type":44,"value":301},{"type":44,"value":810}," only when the user explicitly selects the standardized dashboard, reusable dashboard-template, or structured payload-driven rendering path. This skill still owns the analysis and maps it into ",{"type":39,"tag":67,"props":812,"children":814},{"className":813},[],[815],{"type":44,"value":395},{"type":44,"value":817},"; prefer ",{"type":39,"tag":67,"props":819,"children":821},{"className":820},[],[822],{"type":44,"value":823},"layout: \"single_page\"",{"type":44,"value":825}," with sticky contents for full PM diligence dashboards unless the user explicitly asks for tabs. Ordinary standalone HTML deep dives use the flexible HTML guidance above rather than a fixed module inventory.",{"type":39,"tag":47,"props":827,"children":829},{"id":828},"public-equity-pm-judgment-layer",[830],{"type":44,"value":831},"Public Equity PM Judgment Layer",{"type":39,"tag":61,"props":833,"children":834},{},[835,837,843,845,851,852,858,859,865,866,872,873,879],{"type":44,"value":836},"For substantial post-print work, load ",{"type":39,"tag":67,"props":838,"children":840},{"className":839},[],[841],{"type":44,"value":842},"shared\u002Fpm-judgment-heuristics.md",{"type":44,"value":844}," before finalizing. Audience modes: ",{"type":39,"tag":67,"props":846,"children":848},{"className":847},[],[849],{"type":44,"value":850},"long_only_pm",{"type":44,"value":117},{"type":39,"tag":67,"props":853,"children":855},{"className":854},[],[856],{"type":44,"value":857},"long_short_hf",{"type":44,"value":117},{"type":39,"tag":67,"props":860,"children":862},{"className":861},[],[863],{"type":44,"value":864},"sell_side_research",{"type":44,"value":117},{"type":39,"tag":67,"props":867,"children":869},{"className":868},[],[870],{"type":44,"value":871},"etf_index_diligence",{"type":44,"value":117},{"type":39,"tag":67,"props":874,"children":876},{"className":875},[],[877],{"type":44,"value":878},"public_equity_diligence",{"type":44,"value":90},{"type":39,"tag":61,"props":881,"children":882},{},[883],{"type":44,"value":884},"Default PM question: did the quarter change the thesis, estimates, valuation support, or sizing?",{"type":39,"tag":61,"props":886,"children":887},{},[888],{"type":44,"value":889},"Required PM judgment:",{"type":39,"tag":160,"props":891,"children":892},{},[893,898,903,908],{"type":39,"tag":164,"props":894,"children":895},{},[896],{"type":44,"value":897},"Lead with thesis change, estimate revision direction, valuation support, and position action.",{"type":39,"tag":164,"props":899,"children":900},{},[901],{"type":44,"value":902},"Bridge headline versus clean result, guide delta, quality of beat\u002Fmiss, transcript evidence, management credibility, and next falsifier.",{"type":39,"tag":164,"props":904,"children":905},{},[906],{"type":44,"value":907},"Separate reported facts, management claims, consensus, market data, model output, assumptions, and PM judgment.",{"type":39,"tag":164,"props":909,"children":910},{},[911],{"type":44,"value":912},"For sell-side mode, add rating\u002Ftarget implications and risk-to-rating. For hedge fund mode, add add\u002Ftrim\u002Fcover triggers.",{"items":914,"total":1119},[915,936,959,976,992,1011,1030,1046,1062,1076,1088,1103],{"slug":916,"name":916,"fn":917,"description":918,"org":919,"tags":920,"stars":933,"repoUrl":934,"updatedAt":935},"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},[921,924,927,930],{"name":922,"slug":923,"type":15},"Documents","documents",{"name":925,"slug":926,"type":15},"Healthcare","healthcare",{"name":928,"slug":929,"type":15},"Insurance","insurance",{"name":931,"slug":932,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-08-02T05:48:07.395855",{"slug":937,"name":937,"fn":938,"description":939,"org":940,"tags":941,"stars":956,"repoUrl":957,"updatedAt":958},"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},[942,945,947,950,953],{"name":943,"slug":944,"type":15},".NET","dotnet",{"name":946,"slug":937,"type":15},"ASP.NET Core",{"name":948,"slug":949,"type":15},"Blazor","blazor",{"name":951,"slug":952,"type":15},"C#","csharp",{"name":954,"slug":955,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":960,"name":960,"fn":961,"description":962,"org":963,"tags":964,"stars":956,"repoUrl":957,"updatedAt":975},"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},[965,968,971,974],{"name":966,"slug":967,"type":15},"Apps SDK","apps-sdk",{"name":969,"slug":970,"type":15},"ChatGPT","chatgpt",{"name":972,"slug":973,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":977,"name":977,"fn":978,"description":979,"org":980,"tags":981,"stars":956,"repoUrl":957,"updatedAt":991},"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},[982,985,988],{"name":983,"slug":984,"type":15},"API Development","api-development",{"name":986,"slug":987,"type":15},"CLI","cli",{"name":989,"slug":990,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":993,"name":993,"fn":994,"description":995,"org":996,"tags":997,"stars":956,"repoUrl":957,"updatedAt":1010},"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},[998,1001,1004,1007],{"name":999,"slug":1000,"type":15},"Cloudflare","cloudflare",{"name":1002,"slug":1003,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":1005,"slug":1006,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":1008,"slug":1009,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":1012,"name":1012,"fn":1013,"description":1014,"org":1015,"tags":1016,"stars":956,"repoUrl":957,"updatedAt":1029},"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},[1017,1020,1023,1026],{"name":1018,"slug":1019,"type":15},"Productivity","productivity",{"name":1021,"slug":1022,"type":15},"Project Management","project-management",{"name":1024,"slug":1025,"type":15},"Strategy","strategy",{"name":1027,"slug":1028,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":1031,"name":1031,"fn":1032,"description":1033,"org":1034,"tags":1035,"stars":956,"repoUrl":957,"updatedAt":1045},"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},[1036,1039,1041,1044],{"name":1037,"slug":1038,"type":15},"Design","design",{"name":1040,"slug":1031,"type":15},"Figma",{"name":1042,"slug":1043,"type":15},"Frontend","frontend",{"name":972,"slug":973,"type":15},"2026-04-12T05:06:47.939943",{"slug":1047,"name":1047,"fn":1048,"description":1049,"org":1050,"tags":1051,"stars":956,"repoUrl":957,"updatedAt":1061},"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},[1052,1053,1056,1057,1058],{"name":1037,"slug":1038,"type":15},{"name":1054,"slug":1055,"type":15},"Design System","design-system",{"name":1040,"slug":1031,"type":15},{"name":1042,"slug":1043,"type":15},{"name":1059,"slug":1060,"type":15},"UI Components","ui-components","2026-05-10T05:59:52.971881",{"slug":1063,"name":1063,"fn":1064,"description":1065,"org":1066,"tags":1067,"stars":956,"repoUrl":957,"updatedAt":1075},"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},[1068,1069,1070,1073,1074],{"name":1037,"slug":1038,"type":15},{"name":1054,"slug":1055,"type":15},{"name":1071,"slug":1072,"type":15},"Documentation","documentation",{"name":1040,"slug":1031,"type":15},{"name":1042,"slug":1043,"type":15},"2026-05-16T06:07:47.821474",{"slug":1077,"name":1077,"fn":1078,"description":1079,"org":1080,"tags":1081,"stars":956,"repoUrl":957,"updatedAt":1087},"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},[1082,1083,1084,1085,1086],{"name":1037,"slug":1038,"type":15},{"name":1040,"slug":1031,"type":15},{"name":1042,"slug":1043,"type":15},{"name":1059,"slug":1060,"type":15},{"name":954,"slug":955,"type":15},"2026-05-16T06:07:40.583615",{"slug":1089,"name":1089,"fn":1090,"description":1091,"org":1092,"tags":1093,"stars":956,"repoUrl":957,"updatedAt":1102},"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},[1094,1097,1098,1101],{"name":1095,"slug":1096,"type":15},"Animation","animation",{"name":989,"slug":990,"type":15},{"name":1099,"slug":1100,"type":15},"Creative","creative",{"name":1037,"slug":1038,"type":15},"2026-05-02T05:31:48.48485",{"slug":1104,"name":1104,"fn":1105,"description":1106,"org":1107,"tags":1108,"stars":956,"repoUrl":957,"updatedAt":1118},"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},[1109,1110,1111,1114,1117],{"name":1099,"slug":1100,"type":15},{"name":1037,"slug":1038,"type":15},{"name":1112,"slug":1113,"type":15},"Image Generation","image-generation",{"name":1115,"slug":1116,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",578,{"items":1121,"total":1217},[1122,1139,1153,1165,1180,1193,1205],{"slug":1123,"name":1123,"fn":1124,"description":1125,"org":1126,"tags":1127,"stars":22,"repoUrl":23,"updatedAt":1138},"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},[1128,1131,1134,1137],{"name":1129,"slug":1130,"type":15},"Accessibility","accessibility",{"name":1132,"slug":1133,"type":15},"Charts","charts",{"name":1135,"slug":1136,"type":15},"Data Visualization","data-visualization",{"name":1037,"slug":1038,"type":15},"2026-06-30T19:00:57.102",{"slug":1140,"name":1140,"fn":1141,"description":1142,"org":1143,"tags":1144,"stars":22,"repoUrl":23,"updatedAt":1152},"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},[1145,1146,1149],{"name":1099,"slug":1100,"type":15},{"name":1147,"slug":1148,"type":15},"Editing","editing",{"name":1150,"slug":1151,"type":15},"Imaging","imaging","2026-08-28T15:09:11.185865",{"slug":1154,"name":1154,"fn":1155,"description":1156,"org":1157,"tags":1158,"stars":22,"repoUrl":23,"updatedAt":1164},"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},[1159,1160,1161],{"name":1099,"slug":1100,"type":15},{"name":1037,"slug":1038,"type":15},{"name":1162,"slug":1163,"type":15},"Graphics","graphics","2026-08-28T15:09:07.42507",{"slug":1166,"name":1166,"fn":1167,"description":1168,"org":1169,"tags":1170,"stars":22,"repoUrl":23,"updatedAt":1179},"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},[1171,1172,1173,1176],{"name":1099,"slug":1100,"type":15},{"name":1162,"slug":1163,"type":15},{"name":1174,"slug":1175,"type":15},"Marketing","marketing",{"name":1177,"slug":1178,"type":15},"Social Media","social-media","2026-08-28T15:10:07.282096",{"slug":1181,"name":1181,"fn":1182,"description":1183,"org":1184,"tags":1185,"stars":22,"repoUrl":23,"updatedAt":1192},"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},[1186,1187,1188,1189],{"name":1099,"slug":1100,"type":15},{"name":1037,"slug":1038,"type":15},{"name":1162,"slug":1163,"type":15},{"name":1190,"slug":1191,"type":15},"Templates","templates","2026-08-28T15:10:03.050113",{"slug":1194,"name":1194,"fn":1195,"description":1196,"org":1197,"tags":1198,"stars":22,"repoUrl":23,"updatedAt":1204},"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},[1199,1200,1201],{"name":1099,"slug":1100,"type":15},{"name":1147,"slug":1148,"type":15},{"name":1202,"slug":1203,"type":15},"Video","video","2026-08-28T15:09:07.765245",{"slug":1206,"name":1206,"fn":1207,"description":1208,"org":1209,"tags":1210,"stars":22,"repoUrl":23,"updatedAt":1216},"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},[1211,1212,1213],{"name":1099,"slug":1100,"type":15},{"name":1150,"slug":1151,"type":15},{"name":1214,"slug":1215,"type":15},"Photography","photography","2026-08-28T15:09:10.386974",499]