[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-idea-generation":3,"mdc--8qbpd1-key":33,"related-org-openai-idea-generation":1036,"related-repo-openai-idea-generation":1243},{"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},"idea-generation","triage public equity investment ideas","Use when triaging public-equity idea candidates. Do not use for final trade recommendations, pitches, memos, or models.",{"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},"Finance","finance","tag",{"name":17,"slug":18,"type":15},"Ideation","ideation",{"name":20,"slug":21,"type":15},"Equity Research","equity-research",4888,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-08-28T15:09:15.677488",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\u002Fidea-generation","---\nname: idea-generation\ndescription: Use when triaging public-equity idea candidates. Do not use for final trade recommendations, pitches, memos, or models.\n---\n\n# Idea Generation For Public Equity Investing\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- `Market Data & Estimates`\n- `Company Filings & IR`\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 a substantive idea screen, market map, watchlist review, or reusable\u002Fsource-heavy candidate set, the default resolves the presentation surface to a polished standalone HTML idea-triage report unless the user requests another surface, a quick\u002Fno-file answer, or workbook\u002Ftracker output. In interactive runs, ask only remaining material choices such as depth, audience\u002Fuse, or focus; in non-interactive runs, default to the HTML idea-triage report and `Full working analysis` and disclose 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\nTriage public-equity idea candidates and screen outputs into research-worthy longs, shorts, pairs, catalysts, relative-value ideas, watchlist items, and rejected false positives. This is a PM-style research-prioritization skill, not a final recommendation engine.\n\nA strong output explains why a security surfaced now, possible variant perception, what is priced in, what would make it investable, first rejection risk, and the next workflow.\n\nUse chat for quick triage. For a substantial reusable screen, market map, watchlist review, or source-heavy candidate set, produce a polished standalone HTML idea-triage report following `..\u002F..\u002Fshared\u002Fhtml-artifact-standard.md`; let the mandate and screening question determine the structure. Use `dashboard-builder` only when the user explicitly asks for a standardized dashboard, reusable dashboard template, or structured payload-driven render.\n\n## Operating Rules\n\n- Never present a screen result as a final recommendation.\n- Label outputs as idea candidates, watchlist items, deeper-research candidates, or rejected false positives.\n- Preserve user portfolios, watchlists, models, notes, and spreadsheets; add outputs rather than overwriting source work.\n- Use prompt\u002Fconnected\u002Fuser files first, primary sources next, market\u002Fconsensus data next, and web fallback only when current public data is needed.\n- Do not fabricate unavailable market data or metrics.\n- Use `crowded` only when supported by positioning, ownership, flow, short-interest, or comparably direct evidence. If the evidence is limited to price appreciation, narrative visibility, or simple valuation, use `expectations-heavy`, `valuation-gated`, or `crowding-risk candidate`.\n- Do not advance a candidate solely because the stock rallied after a thematic catalyst or management mentioned the theme. For an advanced name, show a source-backed link from the driver to orders, backlog, revenue, margins, or estimate revisions; otherwise label it `needs exposure attribution`.\n\n## Workflow\n\n1. **Assess context.** With no context, use liquid public-equity defaults and state assumptions. With partial context, infer mandate\u002Fstyle and label assumptions. With rich context, treat provided portfolios, screens, notes, files, or connected data as primary evidence.\n2. **Set mandate and universe.** Identify long-only, long\u002Fshort, market-neutral, event, credit, region, sector, cap size, liquidity, benchmark, horizon, and allowed instruments.\n3. **Normalize candidates.** Resolve tickers, ADRs, share classes, currencies, fiscal calendars, sectors, liquidity, benchmark membership, and portfolio\u002Fwatchlist overlap.\n4. **Screen by archetype and beneficiary pathway.** Use long, short, pair, relative value, catalyst, and watchlist archetypes rather than one generic rank. For thematic screens, map candidates by beneficiary pathway before ranking, such as electrical\u002Fpower distribution, construction, networking, cooling, grid\u002Fgeneration, or colocation\u002Freal estate.\n5. **Score if structured data exists.** Use `scripts\u002Fscore_ideas.py` only for user-provided candidate rows and scoring fields.\n6. **Apply PM triage.** Test denominator quality, estimate credibility, catalyst path, valuation support, risk compensation, verified positioning versus inferred expectations risk, liquidity, and false-positive risk.\n7. **Output priorities and routing.** Lead with a candidate funnel and route candidates to model update, earnings, pitch, thesis tracker, hedge, event, credit, macro, scenario, memo, or QC workflows as appropriate.\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: screen construction, source QC, variant view, catalyst path, risk flags, and prioritization. Keep this skill as the lead: reconcile conflicts, source labels, assumptions, open items, final QA, and the user-facing answer.\n\n\n## Deterministic Scoring Helper\n\n```bash\npython scripts\u002Fscore_ideas.py candidates.csv --output-dir output\n```\n\nThe helper materializes supplied scores into ranked support outputs and warnings. It does not create proprietary market data or replace PM judgment. If no numeric score fields are supplied, treat output as qualitative triage.\n\nFor standardized dashboard handoffs only, use `references\u002FDASHBOARD_PACK.md`. `idea-generation` owns candidate triage, screen interpretation, and workflow routing; `dashboard-builder` owns the shared shell\u002Frendering\u002FQA. Build a `public_equity_investing_dashboard.v1` payload as an internal renderer input, and keep JSON\u002FMarkdown\u002FCSV support files behind the HTML artifact unless explicitly requested.\n\n## Output Contract\n\nDefault output:\n\n- scope and assumptions;\n- methodology and data\u002Fsource caveats;\n- headline research-priority conclusion and candidate funnel;\n- beneficiary-pathway map when relevant to a thematic screen;\n- ranked idea table with exposure proof and expectations risk;\n- PM-style idea cards for highest-priority names;\n- rejected\u002Fdeprioritized false positives;\n- cross-idea themes and risk observations;\n- next research step for each important candidate;\n- downstream routing.\n\nRanking buckets: `A - immediate research candidate`, `B - watchlist \u002F needs trigger`, `C - screen flag only`, and `Reject`.\n\nFor thematic or source-heavy idea screens, express the funnel as `Advance to deeper work`, `Valuation \u002F expectations gated`, `Exposure not yet proven`, and `Deprioritized or reject`. Make clear that `Advance to deeper work` is a research-priority status, not an investment recommendation, approved position, or attractive entry point; an advanced candidate may still be valuation-gated or entry-gated. A candidate without a quantified or source-backed link to the theme stays in `Exposure not yet proven` and is labeled `needs exposure attribution`.\n\n## HTML Guidance\n\nFor a substantive HTML idea-triage report, load `..\u002F..\u002Fshared\u002Fhtml-artifact-standard.md` and apply these workflow-specific rules:\n\n- Lead with the research-priority conclusion and candidate funnel; make the funnel or an exposure-versus-expectations matrix the primary visual object.\n- Use three to five first-read tiles only when each has a distinct job, such as universe size, advance count, valuation-gated count, unproven-exposure count, or the most important evidence gap.\n- Keep methodology and evidence-posture commentary compact or place it below the candidate funnel when it would otherwise delay the primary research-prioritization visual.\n- Put the ranked candidate board near the top. For thematic screens, organize candidates by beneficiary pathway before or alongside rank.\n- Show `Exposure proof`, `Expectations risk`, `First rejection`, and `Next workflow` in the table or visible candidate summaries. Reserve longer idea cards for the highest-priority names.\n- Distinguish verified positioning from inferred crowding risk; do not make the headline or status label more certain than the evidence.\n- Keep citations traceable but readable: do not fragment years, ticker symbols, ranges, product names, or guidance values into separately linked tokens, and avoid an oversized citation run in the hero.\n- Visually inspect local HTML via local headless-browser screenshots, not the in-app Browser plugin, and iterate on legibility, hierarchy, clipping, citation rendering, and whitespace before delivery.\n\n## Reference Map\n\n- `references\u002Fsource-qc.md`: source hierarchy, stale data, citations, data caveats.\n- `references\u002Fworkflow.md`: full workflow and context adaptation.\n- `references\u002Fscreen-archetypes.md`: long, short, pair, catalyst, and watchlist archetypes.\n- `references\u002Fsector-overlays.md`: sector metrics and traps.\n- `references\u002Foutput-standards.md`: report and idea-card templates.\n- `references\u002Fdownstream-routing.md`: local handoff patterns.\n- `references\u002Fscoring-materializer.md`: deterministic scoring contract.\n\n## Public Equity PM Judgment Layer\n\nFor substantial screens or idea queues, 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\nEvery top idea must include `Actionability`, `Variant Wedge`, `Why Now`, `First Rejection`, `What Would Make It Investable`, `What Would Kill It`, and `Next Workflow`.\n\nRequired PM judgment:\n- Long-only: benchmark fit, active share, quality durability, downside versus benchmark, liquidity, and add\u002Ftrim path.\n- Long\u002Fshort hedge fund: catalyst path, shortability, borrow, gross\u002Fnet impact, factor crowding, and cover discipline.\n- Sell-side: rating-change potential, estimate revisions, target-price debate, client relevance, and risk-to-rating.\n- ETF\u002Findex: index methodology, constituent weight, rebalance effects, liquidity, passive-flow relevance, and factor exposure.\n- Public equity diligence: source pack completeness, thesis readiness, diligence queue, and next evidence needed.\n",{"data":34,"body":35},{"name":4,"description":6},{"type":36,"children":37},"root",[38,47,54,61,92,98,149,155,160,192,198,219,225,254,260,265,270,291,297,372,378,461,467,472,478,522,527,562,568,573,626,659,713,719,731,803,809,889,895,943,997,1002,1030],{"type":39,"tag":40,"props":41,"children":43},"element","h1",{"id":42},"idea-generation-for-public-equity-investing",[44],{"type":45,"value":46},"text","Idea Generation For Public Equity Investing",{"type":39,"tag":48,"props":49,"children":51},"h2",{"id":50},"skill-configuration",[52],{"type":45,"value":53},"Skill Configuration",{"type":39,"tag":55,"props":56,"children":58},"h3",{"id":57},"common-skill-instructions",[59],{"type":45,"value":60},"Common Skill Instructions",{"type":39,"tag":62,"props":63,"children":64},"p",{},[65,67,74,76,82,84,90],{"type":45,"value":66},"MANDATORY: Before searching connectors, retrieving evidence, or drafting output, read and apply the shared runtime contract in ",{"type":39,"tag":68,"props":69,"children":71},"code",{"className":70},[],[72],{"type":45,"value":73},"..\u002Fpublic-equity-investing\u002FSKILL.md## Cross-Skill Runtime Contract",{"type":45,"value":75},". Then check the router skill map and ",{"type":39,"tag":68,"props":77,"children":79},{"className":78},[],[80],{"type":45,"value":81},"..\u002F..\u002Fshared\u002Fplugin-routing-playbook.md",{"type":45,"value":83}," 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":68,"props":85,"children":87},{"className":86},[],[88],{"type":45,"value":89},"..\u002Fuser-context\u002FSKILL.md",{"type":45,"value":91},".",{"type":39,"tag":55,"props":93,"children":95},{"id":94},"source-resolution",[96],{"type":45,"value":97},"Source Resolution",{"type":39,"tag":62,"props":99,"children":100},{},[101,103,109,111,117,119,125,126,132,133,139,141,147],{"type":45,"value":102},"Load ",{"type":39,"tag":68,"props":104,"children":106},{"className":105},[],[107],{"type":45,"value":108},"..\u002F..\u002Fshared\u002Fworkflow-source-resolution.md",{"type":45,"value":110},". Resolve only the categories needed for this workflow: ",{"type":39,"tag":68,"props":112,"children":114},{"className":113},[],[115],{"type":45,"value":116},"company_filings_ir",{"type":45,"value":118},", ",{"type":39,"tag":68,"props":120,"children":122},{"className":121},[],[123],{"type":45,"value":124},"earnings_transcripts_presentations",{"type":45,"value":118},{"type":39,"tag":68,"props":127,"children":129},{"className":128},[],[130],{"type":45,"value":131},"internal_research",{"type":45,"value":118},{"type":39,"tag":68,"props":134,"children":136},{"className":135},[],[137],{"type":45,"value":138},"portfolio_models_trackers",{"type":45,"value":140},", and ",{"type":39,"tag":68,"props":142,"children":144},{"className":143},[],[145],{"type":45,"value":146},"market_data_estimates",{"type":45,"value":148},". Use the shared runtime contract to map each attempted category to an available app, connector, file, export, or user-provided input.",{"type":39,"tag":48,"props":150,"children":152},{"id":151},"relevant-dependency-categories",[153],{"type":45,"value":154},"Relevant Dependency Categories",{"type":39,"tag":62,"props":156,"children":157},{},[158],{"type":45,"value":159},"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":161,"props":162,"children":163},"ul",{},[164,174,183],{"type":39,"tag":165,"props":166,"children":167},"li",{},[168],{"type":39,"tag":68,"props":169,"children":171},{"className":170},[],[172],{"type":45,"value":173},"Market Data & Estimates",{"type":39,"tag":165,"props":175,"children":176},{},[177],{"type":39,"tag":68,"props":178,"children":180},{"className":179},[],[181],{"type":45,"value":182},"Company Filings & IR",{"type":39,"tag":165,"props":184,"children":185},{},[186],{"type":39,"tag":68,"props":187,"children":189},{"className":188},[],[190],{"type":45,"value":191},"Internal Research",{"type":39,"tag":48,"props":193,"children":195},{"id":194},"internal-support",[196],{"type":45,"value":197},"Internal Support",{"type":39,"tag":62,"props":199,"children":200},{},[201,203,209,211,217],{"type":45,"value":202},"When this workflow needs rendering, evidence\u002Fdata preparation, style, or sector context, route support through the visible ",{"type":39,"tag":68,"props":204,"children":206},{"className":205},[],[207],{"type":45,"value":208},"public-equity-investing",{"type":45,"value":210}," router and its bundled internal playbooks. Route workbook or model QA through the visible ",{"type":39,"tag":68,"props":212,"children":214},{"className":213},[],[215],{"type":45,"value":216},"model-audit-tieout",{"type":45,"value":218}," workflow.",{"type":39,"tag":48,"props":220,"children":222},{"id":221},"deliverable-intake",[223],{"type":45,"value":224},"Deliverable Intake",{"type":39,"tag":62,"props":226,"children":227},{},[228,230,236,238,244,246,252],{"type":45,"value":229},"Before source gathering or analysis for a new substantive hero deliverable, load ",{"type":39,"tag":68,"props":231,"children":233},{"className":232},[],[234],{"type":45,"value":235},"..\u002F..\u002Fshared\u002Fdeliverable-intake-policy.md",{"type":45,"value":237}," and use its adaptive ",{"type":39,"tag":68,"props":239,"children":241},{"className":240},[],[242],{"type":45,"value":243},"request_user_input",{"type":45,"value":245}," preflight for materially unresolved format, depth, audience\u002Fuse, or focus choices. For a substantive idea screen, market map, watchlist review, or reusable\u002Fsource-heavy candidate set, the default resolves the presentation surface to a polished standalone HTML idea-triage report unless the user requests another surface, a quick\u002Fno-file answer, or workbook\u002Ftracker output. In interactive runs, ask only remaining material choices such as depth, audience\u002Fuse, or focus; in non-interactive runs, default to the HTML idea-triage report and ",{"type":39,"tag":68,"props":247,"children":249},{"className":248},[],[250],{"type":45,"value":251},"Full working analysis",{"type":45,"value":253}," and disclose 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":39,"tag":48,"props":255,"children":257},{"id":256},"purpose",[258],{"type":45,"value":259},"Purpose",{"type":39,"tag":62,"props":261,"children":262},{},[263],{"type":45,"value":264},"Triage public-equity idea candidates and screen outputs into research-worthy longs, shorts, pairs, catalysts, relative-value ideas, watchlist items, and rejected false positives. This is a PM-style research-prioritization skill, not a final recommendation engine.",{"type":39,"tag":62,"props":266,"children":267},{},[268],{"type":45,"value":269},"A strong output explains why a security surfaced now, possible variant perception, what is priced in, what would make it investable, first rejection risk, and the next workflow.",{"type":39,"tag":62,"props":271,"children":272},{},[273,275,281,283,289],{"type":45,"value":274},"Use chat for quick triage. For a substantial reusable screen, market map, watchlist review, or source-heavy candidate set, produce a polished standalone HTML idea-triage report following ",{"type":39,"tag":68,"props":276,"children":278},{"className":277},[],[279],{"type":45,"value":280},"..\u002F..\u002Fshared\u002Fhtml-artifact-standard.md",{"type":45,"value":282},"; let the mandate and screening question determine the structure. Use ",{"type":39,"tag":68,"props":284,"children":286},{"className":285},[],[287],{"type":45,"value":288},"dashboard-builder",{"type":45,"value":290}," only when the user explicitly asks for a standardized dashboard, reusable dashboard template, or structured payload-driven render.",{"type":39,"tag":48,"props":292,"children":294},{"id":293},"operating-rules",[295],{"type":45,"value":296},"Operating Rules",{"type":39,"tag":161,"props":298,"children":299},{},[300,305,310,315,320,325,360],{"type":39,"tag":165,"props":301,"children":302},{},[303],{"type":45,"value":304},"Never present a screen result as a final recommendation.",{"type":39,"tag":165,"props":306,"children":307},{},[308],{"type":45,"value":309},"Label outputs as idea candidates, watchlist items, deeper-research candidates, or rejected false positives.",{"type":39,"tag":165,"props":311,"children":312},{},[313],{"type":45,"value":314},"Preserve user portfolios, watchlists, models, notes, and spreadsheets; add outputs rather than overwriting source work.",{"type":39,"tag":165,"props":316,"children":317},{},[318],{"type":45,"value":319},"Use prompt\u002Fconnected\u002Fuser files first, primary sources next, market\u002Fconsensus data next, and web fallback only when current public data is needed.",{"type":39,"tag":165,"props":321,"children":322},{},[323],{"type":45,"value":324},"Do not fabricate unavailable market data or metrics.",{"type":39,"tag":165,"props":326,"children":327},{},[328,330,336,338,344,345,351,353,359],{"type":45,"value":329},"Use ",{"type":39,"tag":68,"props":331,"children":333},{"className":332},[],[334],{"type":45,"value":335},"crowded",{"type":45,"value":337}," only when supported by positioning, ownership, flow, short-interest, or comparably direct evidence. If the evidence is limited to price appreciation, narrative visibility, or simple valuation, use ",{"type":39,"tag":68,"props":339,"children":341},{"className":340},[],[342],{"type":45,"value":343},"expectations-heavy",{"type":45,"value":118},{"type":39,"tag":68,"props":346,"children":348},{"className":347},[],[349],{"type":45,"value":350},"valuation-gated",{"type":45,"value":352},", or ",{"type":39,"tag":68,"props":354,"children":356},{"className":355},[],[357],{"type":45,"value":358},"crowding-risk candidate",{"type":45,"value":91},{"type":39,"tag":165,"props":361,"children":362},{},[363,365,371],{"type":45,"value":364},"Do not advance a candidate solely because the stock rallied after a thematic catalyst or management mentioned the theme. For an advanced name, show a source-backed link from the driver to orders, backlog, revenue, margins, or estimate revisions; otherwise label it ",{"type":39,"tag":68,"props":366,"children":368},{"className":367},[],[369],{"type":45,"value":370},"needs exposure attribution",{"type":45,"value":91},{"type":39,"tag":48,"props":373,"children":375},{"id":374},"workflow",[376],{"type":45,"value":377},"Workflow",{"type":39,"tag":379,"props":380,"children":381},"ol",{},[382,393,403,413,423,441,451],{"type":39,"tag":165,"props":383,"children":384},{},[385,391],{"type":39,"tag":386,"props":387,"children":388},"strong",{},[389],{"type":45,"value":390},"Assess context.",{"type":45,"value":392}," With no context, use liquid public-equity defaults and state assumptions. With partial context, infer mandate\u002Fstyle and label assumptions. With rich context, treat provided portfolios, screens, notes, files, or connected data as primary evidence.",{"type":39,"tag":165,"props":394,"children":395},{},[396,401],{"type":39,"tag":386,"props":397,"children":398},{},[399],{"type":45,"value":400},"Set mandate and universe.",{"type":45,"value":402}," Identify long-only, long\u002Fshort, market-neutral, event, credit, region, sector, cap size, liquidity, benchmark, horizon, and allowed instruments.",{"type":39,"tag":165,"props":404,"children":405},{},[406,411],{"type":39,"tag":386,"props":407,"children":408},{},[409],{"type":45,"value":410},"Normalize candidates.",{"type":45,"value":412}," Resolve tickers, ADRs, share classes, currencies, fiscal calendars, sectors, liquidity, benchmark membership, and portfolio\u002Fwatchlist overlap.",{"type":39,"tag":165,"props":414,"children":415},{},[416,421],{"type":39,"tag":386,"props":417,"children":418},{},[419],{"type":45,"value":420},"Screen by archetype and beneficiary pathway.",{"type":45,"value":422}," Use long, short, pair, relative value, catalyst, and watchlist archetypes rather than one generic rank. For thematic screens, map candidates by beneficiary pathway before ranking, such as electrical\u002Fpower distribution, construction, networking, cooling, grid\u002Fgeneration, or colocation\u002Freal estate.",{"type":39,"tag":165,"props":424,"children":425},{},[426,431,433,439],{"type":39,"tag":386,"props":427,"children":428},{},[429],{"type":45,"value":430},"Score if structured data exists.",{"type":45,"value":432}," Use ",{"type":39,"tag":68,"props":434,"children":436},{"className":435},[],[437],{"type":45,"value":438},"scripts\u002Fscore_ideas.py",{"type":45,"value":440}," only for user-provided candidate rows and scoring fields.",{"type":39,"tag":165,"props":442,"children":443},{},[444,449],{"type":39,"tag":386,"props":445,"children":446},{},[447],{"type":45,"value":448},"Apply PM triage.",{"type":45,"value":450}," Test denominator quality, estimate credibility, catalyst path, valuation support, risk compensation, verified positioning versus inferred expectations risk, liquidity, and false-positive risk.",{"type":39,"tag":165,"props":452,"children":453},{},[454,459],{"type":39,"tag":386,"props":455,"children":456},{},[457],{"type":45,"value":458},"Output priorities and routing.",{"type":45,"value":460}," Lead with a candidate funnel and route candidates to model update, earnings, pitch, thesis tracker, hedge, event, credit, macro, scenario, memo, or QC workflows as appropriate.",{"type":39,"tag":48,"props":462,"children":464},{"id":463},"sub-agent-decomposition",[465],{"type":45,"value":466},"Sub-agent decomposition",{"type":39,"tag":62,"props":468,"children":469},{},[470],{"type":45,"value":471},"For complex medium\u002Flarge requests, use sub-agents where available; otherwise emulate the split as named workstreams. Suggested lanes: screen construction, source QC, variant view, catalyst path, risk flags, and prioritization. Keep this skill as the lead: reconcile conflicts, source labels, assumptions, open items, final QA, and the user-facing answer.",{"type":39,"tag":48,"props":473,"children":475},{"id":474},"deterministic-scoring-helper",[476],{"type":45,"value":477},"Deterministic Scoring Helper",{"type":39,"tag":479,"props":480,"children":485},"pre",{"className":481,"code":482,"language":483,"meta":484,"style":484},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","python scripts\u002Fscore_ideas.py candidates.csv --output-dir output\n","bash","",[486],{"type":39,"tag":68,"props":487,"children":488},{"__ignoreMap":484},[489],{"type":39,"tag":490,"props":491,"children":494},"span",{"class":492,"line":493},"line",1,[495,501,507,512,517],{"type":39,"tag":490,"props":496,"children":498},{"style":497},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[499],{"type":45,"value":500},"python",{"type":39,"tag":490,"props":502,"children":504},{"style":503},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[505],{"type":45,"value":506}," scripts\u002Fscore_ideas.py",{"type":39,"tag":490,"props":508,"children":509},{"style":503},[510],{"type":45,"value":511}," candidates.csv",{"type":39,"tag":490,"props":513,"children":514},{"style":503},[515],{"type":45,"value":516}," --output-dir",{"type":39,"tag":490,"props":518,"children":519},{"style":503},[520],{"type":45,"value":521}," output\n",{"type":39,"tag":62,"props":523,"children":524},{},[525],{"type":45,"value":526},"The helper materializes supplied scores into ranked support outputs and warnings. It does not create proprietary market data or replace PM judgment. If no numeric score fields are supplied, treat output as qualitative triage.",{"type":39,"tag":62,"props":528,"children":529},{},[530,532,538,540,545,547,552,554,560],{"type":45,"value":531},"For standardized dashboard handoffs only, use ",{"type":39,"tag":68,"props":533,"children":535},{"className":534},[],[536],{"type":45,"value":537},"references\u002FDASHBOARD_PACK.md",{"type":45,"value":539},". ",{"type":39,"tag":68,"props":541,"children":543},{"className":542},[],[544],{"type":45,"value":4},{"type":45,"value":546}," owns candidate triage, screen interpretation, and workflow routing; ",{"type":39,"tag":68,"props":548,"children":550},{"className":549},[],[551],{"type":45,"value":288},{"type":45,"value":553}," owns the shared shell\u002Frendering\u002FQA. Build a ",{"type":39,"tag":68,"props":555,"children":557},{"className":556},[],[558],{"type":45,"value":559},"public_equity_investing_dashboard.v1",{"type":45,"value":561}," payload as an internal renderer input, and keep JSON\u002FMarkdown\u002FCSV support files behind the HTML artifact unless explicitly requested.",{"type":39,"tag":48,"props":563,"children":565},{"id":564},"output-contract",[566],{"type":45,"value":567},"Output Contract",{"type":39,"tag":62,"props":569,"children":570},{},[571],{"type":45,"value":572},"Default output:",{"type":39,"tag":161,"props":574,"children":575},{},[576,581,586,591,596,601,606,611,616,621],{"type":39,"tag":165,"props":577,"children":578},{},[579],{"type":45,"value":580},"scope and assumptions;",{"type":39,"tag":165,"props":582,"children":583},{},[584],{"type":45,"value":585},"methodology and data\u002Fsource caveats;",{"type":39,"tag":165,"props":587,"children":588},{},[589],{"type":45,"value":590},"headline research-priority conclusion and candidate funnel;",{"type":39,"tag":165,"props":592,"children":593},{},[594],{"type":45,"value":595},"beneficiary-pathway map when relevant to a thematic screen;",{"type":39,"tag":165,"props":597,"children":598},{},[599],{"type":45,"value":600},"ranked idea table with exposure proof and expectations risk;",{"type":39,"tag":165,"props":602,"children":603},{},[604],{"type":45,"value":605},"PM-style idea cards for highest-priority names;",{"type":39,"tag":165,"props":607,"children":608},{},[609],{"type":45,"value":610},"rejected\u002Fdeprioritized false positives;",{"type":39,"tag":165,"props":612,"children":613},{},[614],{"type":45,"value":615},"cross-idea themes and risk observations;",{"type":39,"tag":165,"props":617,"children":618},{},[619],{"type":45,"value":620},"next research step for each important candidate;",{"type":39,"tag":165,"props":622,"children":623},{},[624],{"type":45,"value":625},"downstream routing.",{"type":39,"tag":62,"props":627,"children":628},{},[629,631,637,638,644,645,651,652,658],{"type":45,"value":630},"Ranking buckets: ",{"type":39,"tag":68,"props":632,"children":634},{"className":633},[],[635],{"type":45,"value":636},"A - immediate research candidate",{"type":45,"value":118},{"type":39,"tag":68,"props":639,"children":641},{"className":640},[],[642],{"type":45,"value":643},"B - watchlist \u002F needs trigger",{"type":45,"value":118},{"type":39,"tag":68,"props":646,"children":648},{"className":647},[],[649],{"type":45,"value":650},"C - screen flag only",{"type":45,"value":140},{"type":39,"tag":68,"props":653,"children":655},{"className":654},[],[656],{"type":45,"value":657},"Reject",{"type":45,"value":91},{"type":39,"tag":62,"props":660,"children":661},{},[662,664,670,671,677,678,684,685,691,693,698,700,705,707,712],{"type":45,"value":663},"For thematic or source-heavy idea screens, express the funnel as ",{"type":39,"tag":68,"props":665,"children":667},{"className":666},[],[668],{"type":45,"value":669},"Advance to deeper work",{"type":45,"value":118},{"type":39,"tag":68,"props":672,"children":674},{"className":673},[],[675],{"type":45,"value":676},"Valuation \u002F expectations gated",{"type":45,"value":118},{"type":39,"tag":68,"props":679,"children":681},{"className":680},[],[682],{"type":45,"value":683},"Exposure not yet proven",{"type":45,"value":140},{"type":39,"tag":68,"props":686,"children":688},{"className":687},[],[689],{"type":45,"value":690},"Deprioritized or reject",{"type":45,"value":692},". Make clear that ",{"type":39,"tag":68,"props":694,"children":696},{"className":695},[],[697],{"type":45,"value":669},{"type":45,"value":699}," is a research-priority status, not an investment recommendation, approved position, or attractive entry point; an advanced candidate may still be valuation-gated or entry-gated. A candidate without a quantified or source-backed link to the theme stays in ",{"type":39,"tag":68,"props":701,"children":703},{"className":702},[],[704],{"type":45,"value":683},{"type":45,"value":706}," and is labeled ",{"type":39,"tag":68,"props":708,"children":710},{"className":709},[],[711],{"type":45,"value":370},{"type":45,"value":91},{"type":39,"tag":48,"props":714,"children":716},{"id":715},"html-guidance",[717],{"type":45,"value":718},"HTML Guidance",{"type":39,"tag":62,"props":720,"children":721},{},[722,724,729],{"type":45,"value":723},"For a substantive HTML idea-triage report, load ",{"type":39,"tag":68,"props":725,"children":727},{"className":726},[],[728],{"type":45,"value":280},{"type":45,"value":730}," and apply these workflow-specific rules:",{"type":39,"tag":161,"props":732,"children":733},{},[734,739,744,749,754,788,793,798],{"type":39,"tag":165,"props":735,"children":736},{},[737],{"type":45,"value":738},"Lead with the research-priority conclusion and candidate funnel; make the funnel or an exposure-versus-expectations matrix the primary visual object.",{"type":39,"tag":165,"props":740,"children":741},{},[742],{"type":45,"value":743},"Use three to five first-read tiles only when each has a distinct job, such as universe size, advance count, valuation-gated count, unproven-exposure count, or the most important evidence gap.",{"type":39,"tag":165,"props":745,"children":746},{},[747],{"type":45,"value":748},"Keep methodology and evidence-posture commentary compact or place it below the candidate funnel when it would otherwise delay the primary research-prioritization visual.",{"type":39,"tag":165,"props":750,"children":751},{},[752],{"type":45,"value":753},"Put the ranked candidate board near the top. For thematic screens, organize candidates by beneficiary pathway before or alongside rank.",{"type":39,"tag":165,"props":755,"children":756},{},[757,759,765,766,772,773,779,780,786],{"type":45,"value":758},"Show ",{"type":39,"tag":68,"props":760,"children":762},{"className":761},[],[763],{"type":45,"value":764},"Exposure proof",{"type":45,"value":118},{"type":39,"tag":68,"props":767,"children":769},{"className":768},[],[770],{"type":45,"value":771},"Expectations risk",{"type":45,"value":118},{"type":39,"tag":68,"props":774,"children":776},{"className":775},[],[777],{"type":45,"value":778},"First rejection",{"type":45,"value":140},{"type":39,"tag":68,"props":781,"children":783},{"className":782},[],[784],{"type":45,"value":785},"Next workflow",{"type":45,"value":787}," in the table or visible candidate summaries. Reserve longer idea cards for the highest-priority names.",{"type":39,"tag":165,"props":789,"children":790},{},[791],{"type":45,"value":792},"Distinguish verified positioning from inferred crowding risk; do not make the headline or status label more certain than the evidence.",{"type":39,"tag":165,"props":794,"children":795},{},[796],{"type":45,"value":797},"Keep citations traceable but readable: do not fragment years, ticker symbols, ranges, product names, or guidance values into separately linked tokens, and avoid an oversized citation run in the hero.",{"type":39,"tag":165,"props":799,"children":800},{},[801],{"type":45,"value":802},"Visually inspect local HTML via local headless-browser screenshots, not the in-app Browser plugin, and iterate on legibility, hierarchy, clipping, citation rendering, and whitespace before delivery.",{"type":39,"tag":48,"props":804,"children":806},{"id":805},"reference-map",[807],{"type":45,"value":808},"Reference Map",{"type":39,"tag":161,"props":810,"children":811},{},[812,823,834,845,856,867,878],{"type":39,"tag":165,"props":813,"children":814},{},[815,821],{"type":39,"tag":68,"props":816,"children":818},{"className":817},[],[819],{"type":45,"value":820},"references\u002Fsource-qc.md",{"type":45,"value":822},": source hierarchy, stale data, citations, data caveats.",{"type":39,"tag":165,"props":824,"children":825},{},[826,832],{"type":39,"tag":68,"props":827,"children":829},{"className":828},[],[830],{"type":45,"value":831},"references\u002Fworkflow.md",{"type":45,"value":833},": full workflow and context adaptation.",{"type":39,"tag":165,"props":835,"children":836},{},[837,843],{"type":39,"tag":68,"props":838,"children":840},{"className":839},[],[841],{"type":45,"value":842},"references\u002Fscreen-archetypes.md",{"type":45,"value":844},": long, short, pair, catalyst, and watchlist archetypes.",{"type":39,"tag":165,"props":846,"children":847},{},[848,854],{"type":39,"tag":68,"props":849,"children":851},{"className":850},[],[852],{"type":45,"value":853},"references\u002Fsector-overlays.md",{"type":45,"value":855},": sector metrics and traps.",{"type":39,"tag":165,"props":857,"children":858},{},[859,865],{"type":39,"tag":68,"props":860,"children":862},{"className":861},[],[863],{"type":45,"value":864},"references\u002Foutput-standards.md",{"type":45,"value":866},": report and idea-card templates.",{"type":39,"tag":165,"props":868,"children":869},{},[870,876],{"type":39,"tag":68,"props":871,"children":873},{"className":872},[],[874],{"type":45,"value":875},"references\u002Fdownstream-routing.md",{"type":45,"value":877},": local handoff patterns.",{"type":39,"tag":165,"props":879,"children":880},{},[881,887],{"type":39,"tag":68,"props":882,"children":884},{"className":883},[],[885],{"type":45,"value":886},"references\u002Fscoring-materializer.md",{"type":45,"value":888},": deterministic scoring contract.",{"type":39,"tag":48,"props":890,"children":892},{"id":891},"public-equity-pm-judgment-layer",[893],{"type":45,"value":894},"Public Equity PM Judgment Layer",{"type":39,"tag":62,"props":896,"children":897},{},[898,900,906,908,914,915,921,922,928,929,935,936,942],{"type":45,"value":899},"For substantial screens or idea queues, load ",{"type":39,"tag":68,"props":901,"children":903},{"className":902},[],[904],{"type":45,"value":905},"shared\u002Fpm-judgment-heuristics.md",{"type":45,"value":907}," before finalizing. Audience modes: ",{"type":39,"tag":68,"props":909,"children":911},{"className":910},[],[912],{"type":45,"value":913},"long_only_pm",{"type":45,"value":118},{"type":39,"tag":68,"props":916,"children":918},{"className":917},[],[919],{"type":45,"value":920},"long_short_hf",{"type":45,"value":118},{"type":39,"tag":68,"props":923,"children":925},{"className":924},[],[926],{"type":45,"value":927},"sell_side_research",{"type":45,"value":118},{"type":39,"tag":68,"props":930,"children":932},{"className":931},[],[933],{"type":45,"value":934},"etf_index_diligence",{"type":45,"value":118},{"type":39,"tag":68,"props":937,"children":939},{"className":938},[],[940],{"type":45,"value":941},"public_equity_diligence",{"type":45,"value":91},{"type":39,"tag":62,"props":944,"children":945},{},[946,948,954,955,961,962,968,969,975,976,982,983,989,990,996],{"type":45,"value":947},"Every top idea must include ",{"type":39,"tag":68,"props":949,"children":951},{"className":950},[],[952],{"type":45,"value":953},"Actionability",{"type":45,"value":118},{"type":39,"tag":68,"props":956,"children":958},{"className":957},[],[959],{"type":45,"value":960},"Variant Wedge",{"type":45,"value":118},{"type":39,"tag":68,"props":963,"children":965},{"className":964},[],[966],{"type":45,"value":967},"Why Now",{"type":45,"value":118},{"type":39,"tag":68,"props":970,"children":972},{"className":971},[],[973],{"type":45,"value":974},"First Rejection",{"type":45,"value":118},{"type":39,"tag":68,"props":977,"children":979},{"className":978},[],[980],{"type":45,"value":981},"What Would Make It Investable",{"type":45,"value":118},{"type":39,"tag":68,"props":984,"children":986},{"className":985},[],[987],{"type":45,"value":988},"What Would Kill It",{"type":45,"value":140},{"type":39,"tag":68,"props":991,"children":993},{"className":992},[],[994],{"type":45,"value":995},"Next Workflow",{"type":45,"value":91},{"type":39,"tag":62,"props":998,"children":999},{},[1000],{"type":45,"value":1001},"Required PM judgment:",{"type":39,"tag":161,"props":1003,"children":1004},{},[1005,1010,1015,1020,1025],{"type":39,"tag":165,"props":1006,"children":1007},{},[1008],{"type":45,"value":1009},"Long-only: benchmark fit, active share, quality durability, downside versus benchmark, liquidity, and add\u002Ftrim path.",{"type":39,"tag":165,"props":1011,"children":1012},{},[1013],{"type":45,"value":1014},"Long\u002Fshort hedge fund: catalyst path, shortability, borrow, gross\u002Fnet impact, factor crowding, and cover discipline.",{"type":39,"tag":165,"props":1016,"children":1017},{},[1018],{"type":45,"value":1019},"Sell-side: rating-change potential, estimate revisions, target-price debate, client relevance, and risk-to-rating.",{"type":39,"tag":165,"props":1021,"children":1022},{},[1023],{"type":45,"value":1024},"ETF\u002Findex: index methodology, constituent weight, rebalance effects, liquidity, passive-flow relevance, and factor exposure.",{"type":39,"tag":165,"props":1026,"children":1027},{},[1028],{"type":45,"value":1029},"Public equity diligence: source pack completeness, thesis readiness, diligence queue, and next evidence needed.",{"type":39,"tag":1031,"props":1032,"children":1033},"style",{},[1034],{"type":45,"value":1035},"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":1037,"total":1242},[1038,1059,1082,1099,1115,1134,1153,1169,1185,1199,1211,1226],{"slug":1039,"name":1039,"fn":1040,"description":1041,"org":1042,"tags":1043,"stars":1056,"repoUrl":1057,"updatedAt":1058},"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},[1044,1047,1050,1053],{"name":1045,"slug":1046,"type":15},"Documents","documents",{"name":1048,"slug":1049,"type":15},"Healthcare","healthcare",{"name":1051,"slug":1052,"type":15},"Insurance","insurance",{"name":1054,"slug":1055,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-08-02T05:48:07.395855",{"slug":1060,"name":1060,"fn":1061,"description":1062,"org":1063,"tags":1064,"stars":1079,"repoUrl":1080,"updatedAt":1081},"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},[1065,1068,1070,1073,1076],{"name":1066,"slug":1067,"type":15},".NET","dotnet",{"name":1069,"slug":1060,"type":15},"ASP.NET Core",{"name":1071,"slug":1072,"type":15},"Blazor","blazor",{"name":1074,"slug":1075,"type":15},"C#","csharp",{"name":1077,"slug":1078,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":1083,"name":1083,"fn":1084,"description":1085,"org":1086,"tags":1087,"stars":1079,"repoUrl":1080,"updatedAt":1098},"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},[1088,1091,1094,1097],{"name":1089,"slug":1090,"type":15},"Apps SDK","apps-sdk",{"name":1092,"slug":1093,"type":15},"ChatGPT","chatgpt",{"name":1095,"slug":1096,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":1100,"name":1100,"fn":1101,"description":1102,"org":1103,"tags":1104,"stars":1079,"repoUrl":1080,"updatedAt":1114},"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},[1105,1108,1111],{"name":1106,"slug":1107,"type":15},"API Development","api-development",{"name":1109,"slug":1110,"type":15},"CLI","cli",{"name":1112,"slug":1113,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":1116,"name":1116,"fn":1117,"description":1118,"org":1119,"tags":1120,"stars":1079,"repoUrl":1080,"updatedAt":1133},"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},[1121,1124,1127,1130],{"name":1122,"slug":1123,"type":15},"Cloudflare","cloudflare",{"name":1125,"slug":1126,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":1128,"slug":1129,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":1131,"slug":1132,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":1135,"name":1135,"fn":1136,"description":1137,"org":1138,"tags":1139,"stars":1079,"repoUrl":1080,"updatedAt":1152},"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},[1140,1143,1146,1149],{"name":1141,"slug":1142,"type":15},"Productivity","productivity",{"name":1144,"slug":1145,"type":15},"Project Management","project-management",{"name":1147,"slug":1148,"type":15},"Strategy","strategy",{"name":1150,"slug":1151,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":1154,"name":1154,"fn":1155,"description":1156,"org":1157,"tags":1158,"stars":1079,"repoUrl":1080,"updatedAt":1168},"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},[1159,1162,1164,1167],{"name":1160,"slug":1161,"type":15},"Design","design",{"name":1163,"slug":1154,"type":15},"Figma",{"name":1165,"slug":1166,"type":15},"Frontend","frontend",{"name":1095,"slug":1096,"type":15},"2026-04-12T05:06:47.939943",{"slug":1170,"name":1170,"fn":1171,"description":1172,"org":1173,"tags":1174,"stars":1079,"repoUrl":1080,"updatedAt":1184},"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},[1175,1176,1179,1180,1181],{"name":1160,"slug":1161,"type":15},{"name":1177,"slug":1178,"type":15},"Design System","design-system",{"name":1163,"slug":1154,"type":15},{"name":1165,"slug":1166,"type":15},{"name":1182,"slug":1183,"type":15},"UI Components","ui-components","2026-05-10T05:59:52.971881",{"slug":1186,"name":1186,"fn":1187,"description":1188,"org":1189,"tags":1190,"stars":1079,"repoUrl":1080,"updatedAt":1198},"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},[1191,1192,1193,1196,1197],{"name":1160,"slug":1161,"type":15},{"name":1177,"slug":1178,"type":15},{"name":1194,"slug":1195,"type":15},"Documentation","documentation",{"name":1163,"slug":1154,"type":15},{"name":1165,"slug":1166,"type":15},"2026-05-16T06:07:47.821474",{"slug":1200,"name":1200,"fn":1201,"description":1202,"org":1203,"tags":1204,"stars":1079,"repoUrl":1080,"updatedAt":1210},"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},[1205,1206,1207,1208,1209],{"name":1160,"slug":1161,"type":15},{"name":1163,"slug":1154,"type":15},{"name":1165,"slug":1166,"type":15},{"name":1182,"slug":1183,"type":15},{"name":1077,"slug":1078,"type":15},"2026-05-16T06:07:40.583615",{"slug":1212,"name":1212,"fn":1213,"description":1214,"org":1215,"tags":1216,"stars":1079,"repoUrl":1080,"updatedAt":1225},"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},[1217,1220,1221,1224],{"name":1218,"slug":1219,"type":15},"Animation","animation",{"name":1112,"slug":1113,"type":15},{"name":1222,"slug":1223,"type":15},"Creative","creative",{"name":1160,"slug":1161,"type":15},"2026-05-02T05:31:48.48485",{"slug":1227,"name":1227,"fn":1228,"description":1229,"org":1230,"tags":1231,"stars":1079,"repoUrl":1080,"updatedAt":1241},"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},[1232,1233,1234,1237,1240],{"name":1222,"slug":1223,"type":15},{"name":1160,"slug":1161,"type":15},{"name":1235,"slug":1236,"type":15},"Image Generation","image-generation",{"name":1238,"slug":1239,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",578,{"items":1244,"total":1340},[1245,1262,1276,1288,1303,1316,1328],{"slug":1246,"name":1246,"fn":1247,"description":1248,"org":1249,"tags":1250,"stars":22,"repoUrl":23,"updatedAt":1261},"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},[1251,1254,1257,1260],{"name":1252,"slug":1253,"type":15},"Accessibility","accessibility",{"name":1255,"slug":1256,"type":15},"Charts","charts",{"name":1258,"slug":1259,"type":15},"Data Visualization","data-visualization",{"name":1160,"slug":1161,"type":15},"2026-06-30T19:00:57.102",{"slug":1263,"name":1263,"fn":1264,"description":1265,"org":1266,"tags":1267,"stars":22,"repoUrl":23,"updatedAt":1275},"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},[1268,1269,1272],{"name":1222,"slug":1223,"type":15},{"name":1270,"slug":1271,"type":15},"Editing","editing",{"name":1273,"slug":1274,"type":15},"Imaging","imaging","2026-08-28T15:09:11.185865",{"slug":1277,"name":1277,"fn":1278,"description":1279,"org":1280,"tags":1281,"stars":22,"repoUrl":23,"updatedAt":1287},"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},[1282,1283,1284],{"name":1222,"slug":1223,"type":15},{"name":1160,"slug":1161,"type":15},{"name":1285,"slug":1286,"type":15},"Graphics","graphics","2026-08-28T15:09:07.42507",{"slug":1289,"name":1289,"fn":1290,"description":1291,"org":1292,"tags":1293,"stars":22,"repoUrl":23,"updatedAt":1302},"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},[1294,1295,1296,1299],{"name":1222,"slug":1223,"type":15},{"name":1285,"slug":1286,"type":15},{"name":1297,"slug":1298,"type":15},"Marketing","marketing",{"name":1300,"slug":1301,"type":15},"Social Media","social-media","2026-08-28T15:10:07.282096",{"slug":1304,"name":1304,"fn":1305,"description":1306,"org":1307,"tags":1308,"stars":22,"repoUrl":23,"updatedAt":1315},"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},[1309,1310,1311,1312],{"name":1222,"slug":1223,"type":15},{"name":1160,"slug":1161,"type":15},{"name":1285,"slug":1286,"type":15},{"name":1313,"slug":1314,"type":15},"Templates","templates","2026-08-28T15:10:03.050113",{"slug":1317,"name":1317,"fn":1318,"description":1319,"org":1320,"tags":1321,"stars":22,"repoUrl":23,"updatedAt":1327},"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},[1322,1323,1324],{"name":1222,"slug":1223,"type":15},{"name":1270,"slug":1271,"type":15},{"name":1325,"slug":1326,"type":15},"Video","video","2026-08-28T15:09:07.765245",{"slug":1329,"name":1329,"fn":1330,"description":1331,"org":1332,"tags":1333,"stars":22,"repoUrl":23,"updatedAt":1339},"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},[1334,1335,1336],{"name":1222,"slug":1223,"type":15},{"name":1273,"slug":1274,"type":15},{"name":1337,"slug":1338,"type":15},"Photography","photography","2026-08-28T15:09:10.386974",499]