[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71HKAJ5VBATE3Q76R3CT2W0":3,"skill-same:01M71HKAJ5VBATE3Q76R3CT2W0":134},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":27,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":66,"commitSha":67,"skillDirectory":68,"forksCount":69,"repositoryHtmlUrl":70,"repositoryHomepageUrl":71,"ownerHtmlUrl":72,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":73,"install":74,"resources":87},"01M71HKAJ5VBATE3Q76R3CT2W0","research-finance",null,"Use when managing the money for an internal R&D program or portfolio — building a multi-period program budget with the F&A (indirect) split, tracking burn rate and runway against value-inflection milestones, or routing R&D cost items to a capitalize-vs-expense determination. Every budget output surfaces its assumptions block; capitalize-vs-expense is decision-support only and routes to a named finance owner — it never books an entry or decides accounting treatment. Distinct from finance\u002Ffinancial-analysis (corporate DCF, close, valuation) and research\u002Fgrants (funding discovery — this manages money already won).","marshadgani\u002FArshad.AI","marshadgani","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F275367399?v=4","01M71G2BP4YMZ4AX5YY0QBHAZH","01M71G2BPPHHFRMHQAKJTZPGK4",1,"MIT","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fresearch-finance\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000040","财务","PROFESSION","适用职业",[28,29,30,5,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"finance","research finance","research","program","when","milestones","funding","books","decision-support","only","never","rd-budget","research-ops","financial-analysis","burn-rate","decision","expense","analysis","code","2026-11-10 10:12:30",false,"---\nname: research-finance\ndescription: Use when managing the money for an internal R&D program or portfolio — building a multi-period program budget with the F&A (indirect) split, tracking burn rate and runway against value-inflection milestones, or routing R&D cost items to a capitalize-vs-expense determination. Every budget output surfaces its assumptions block; capitalize-vs-expense is decision-support only and routes to a named finance owner — it never books an entry or decides accounting treatment. Distinct from finance\u002Ffinancial-analysis (corporate DCF, close, valuation) and research\u002Fgrants (funding discovery — this manages money already won).\nversion: 2.9.0\nauthor: claude-code-skills\nlicense: MIT\ntags: [research-ops, research-finance, rd-budget, burn-rate, runway, fa-rate, capitalize-vs-expense, portfolio]\ncompatible_tools: [claude-code, codex-cli, cursor, antigravity, opencode, gemini-cli]\n---\n\n# research-finance\n\nFinancial management of internal R&D programs and portfolios: program budgeting with F&A, burn\u002Frunway tracking, and capitalize-vs-expense routing. Every number ships with its **assumptions block**, and accounting-treatment calls **route to a named finance owner** — this skill never books an entry.\n\n## Purpose\n\nR&D finance partners, program controllers, and operations leads manage money that has already been allocated or raised — not the corporate close, not the next funding round, not finding a grant. This skill structures three recurring decisions:\n\nThree deterministic tools:\n\n1. `program_budget_planner.py` — Builds a multi-period budget from work-package line items, applies the F&A (indirect) rate to an MTDC-style eligible base, and rolls up direct \u002F F&A \u002F fully-loaded cost per period with an explicit assumptions block.\n2. `burn_runway_tracker.py` — Computes average + trailing burn, runway in periods\u002Fmonths, and whether each value-inflection milestone is reachable before cash runs out. Flags accelerating burn and below-threshold runway.\n3. `capex_vs_opex_router.py` — Scores each R&D cost item against the IAS 38 development-phase criteria (or flags US GAAP ASC 730 expense-as-incurred) and routes it to **CAPITALIZE-CANDIDATE \u002F EXPENSE \u002F FINANCE-OWNER-REVIEW** with a named owner. Never auto-decides.\n\n## When to use\n\nInvoke this skill when:\n\n- You are building or revising an R&D program budget and need the F&A split made explicit.\n- A program's runway is in question and you need a milestone-vs-cash read.\n- Finance asks whether a development cost can be capitalized and you need a defensible first routing.\n- You are preparing a portfolio review and need per-program burn consistency.\n\n**Do NOT use this skill to**: run corporate DCF \u002F valuation \u002F close (use `finance\u002Ffinancial-analysis`), discover or position grants (use `research\u002Fgrants`), or make the final accounting determination (that is the controller's + auditor's call — this tool only routes).\n\n## Workflow\n\n1. **Lay out the program** — Fill `assets\u002Frd_program_budget_template.md` with work-package lines, categories, and per-period amounts.\n2. **Build the budget** — Run `program_budget_planner.py --input program.json --profile {pharma-rd|biotech|medtech|deep-tech|software-rd|university-lab} --fa-rate \u003Cnegotiated rate>`. Read direct \u002F F&A \u002F fully-loaded rollups + assumptions.\n3. **Track burn & runway** — Run `burn_runway_tracker.py --input ledger.json --threshold-months 6`. Read runway + milestone verdicts + flags.\n4. **Route accounting treatment** — Run `capex_vs_opex_router.py --input costs.json --standard {ifrs|usgaap}`. Read the per-item routing; send CAPITALIZE-CANDIDATE and FINANCE-OWNER-REVIEW items to the named owner.\n5. **Assemble the review** — Combine into a program-finance packet. Every number carries its assumptions; treatment calls carry a named owner.\n\n## Scripts\n\n| Script | Purpose | Profiles |\n|---|---|---|\n| `scripts\u002Fprogram_budget_planner.py` | Multi-period budget + F&A split + assumptions | pharma-rd, biotech, medtech, deep-tech, software-rd, university-lab |\n| `scripts\u002Fburn_runway_tracker.py` | Burn, runway, milestone-vs-cash alignment | n\u002Fa (ledger-driven) |\n| `scripts\u002Fcapex_vs_opex_router.py` | IAS 38 \u002F ASC 730 routing to named finance owner | pharma-rd, biotech, medtech, deep-tech, software-rd, university-lab |\n\nAll three: stdlib-only, `--help`, `--sample`, `--output {human,json}`.\n\n## Onboarding & customization\n\nRun the onboarding questionnaire **once before you start** — it captures your defaults so every tool in this skill is pre-configured. Customization is the point: the answers actually change tool behavior.\n\n```bash\npython3 scripts\u002Fonboard.py            # interactive (also: --defaults, --set key=value, --reset)\npython3 scripts\u002Fonboard.py --show     # see the questions + current effective config\n```\n\nAnswers are saved to `~\u002F.config\u002Fresearch-ops\u002Fresearch-finance.json` (global) or `.\u002F.research-ops\u002Fresearch-finance.json` (`--scope project`) and are read automatically by `config_loader.py`. They set the default R&D-area **profile**, the default **F&A rate**, the **runway alert threshold**, the **accounting standard**, and the named **finance owner** printed on capitalize-vs-expense routing. CLI flags always override saved config; `RESEARCH_OPS_NO_CONFIG=1` ignores it.\n\n**The five questions:** R&D area · F&A rate · runway threshold · accounting standard · finance owner.\n\n## Optimize with autoresearch (opt-in)\n\nThis skill ships an **isolated, opt-in** bridge to `engineering\u002Fautoresearch-agent`. Only when you ask to \"optimize\" \u002F \"extend runway\" \u002F \"run a loop\" does an autoresearch experiment iteratively improve a program plan against this skill's runway metric. `scripts\u002Far_evaluator.py` is the ground-truth evaluator; it prints `runway_months: \u003Cfloat>` (higher is better).\n\n```bash\n\u002Far:setup --domain custom --name extend-runway \\\n  --target ledger.json \\\n  --eval \"python3 ar_evaluator.py --target ledger.json\" \\\n  --metric runway_months --direction higher\n\u002Far:loop custom\u002Fextend-runway\n```\n\nIsolated: no hard dependency — autoresearch runs only on demand, and the loop edits `ledger.json`, never the evaluator.\n\n## References\n\n- `references\u002Frd_program_finance_canon.md` — IAS 38 (research vs development); ASC 730 + ASC 985-20; Uniform Guidance 2 CFR 200 (F&A); FASB\u002FIFRS capitalization criteria; NICRA basics.\n- `references\u002Fburn_and_portfolio.md` — Cooper stage-gate; rNPV \u002F real-options for R&D; risk-adjusted portfolio ROI; burn-rate \u002F runway frameworks; milestone-based budgeting.\n- `references\u002Findirect_rate_modeling.md` — F&A pool composition (facilities + administration); MTDC base; de minimis 10%; fringe\u002Foverhead loading; CAS primer.\n\n## Assumptions\n\n- The F&A rate is the most error-prone input. The planner applies whatever rate you pass; it warns you to confirm it is a negotiated NICRA, not a guess.\n- Burn\u002Frunway uses the trailing (recent-weighted) burn as the forward run-rate and assumes flat forward spend unless your ledger encodes a ramp.\n- The capex router asserts criteria from your input; asserting \"technical feasibility\" does not make it true — the named finance owner and auditor validate it.\n- Profiles annotate context (e.g., \"most drug R&D is expensed\") but do not change the accounting test.\n\n## Anti-patterns\n\n- **Stating a budget number without its assumptions.** F&A rate, escalation, and base must travel with the number.\n- **Auto-deciding capitalize-vs-expense.** This tool routes; the controller (and auditor where required) decides.\n- **Using lifetime-average burn for runway.** Recent burn is the honest forward run-rate; averages hide a slowdown or a ramp.\n- **Applying F&A to the full base.** Capital equipment, large subaward portions, and certain categories are MTDC-exempt.\n- **Confusing this with corporate finance.** Valuation, close, and fundraising live in `finance\u002F`.\n\n## Distinct from\n\n| Sibling \u002F neighbor | Scope | Difference |\n|---|---|---|\n| `finance\u002Ffinancial-analysis` | Corporate DCF, ratios, close, rolling forecast, SaaS metrics | That is **company-level**; this is **R&D-program-level** |\n| `research\u002Fgrants` | NIH funding discovery + positioning | That **finds funding**; this **manages money already won** |\n| `clinical-research` (sibling) | Study design + feasibility + budget gate-check | That **scopes** the study; this **funds + tracks** the program |\n| `ra-qm-team` | Regulatory\u002FQM submission | Unrelated — no financial scope |\n\n## Quick examples\n\n```bash\npython3 scripts\u002Fprogram_budget_planner.py --sample\npython3 scripts\u002Fprogram_budget_planner.py --input program.json --profile university-lab --fa-rate 0.585\npython3 scripts\u002Fburn_runway_tracker.py --sample --output json\npython3 scripts\u002Fcapex_vs_opex_router.py --sample --standard ifrs\n```\n\nThe sample budget excludes the sequencer (capital equipment) and CRO subaward from the F&A base; the capex router routes exploratory screening to EXPENSE, a fully-criteria'd pilot line to CAPITALIZE-CANDIDATE, and a partial-criteria software build to FINANCE-OWNER-REVIEW.\n\n## Forcing-question library (Matt Pocock grill discipline)\n\nWalked one at a time by `\u002Fcs:grill-research-ops` or the orchestrator. Recommended answer + canon citation per question. Never bundled.\n\n1. **\"Is this spend in the research phase or the development phase — and can you evidence technical feasibility?\"**\n   Recommended: research = expense; development = capitalize-candidate only with feasibility evidence, routed to a named finance owner.\n   Canon: IAS 38.54-57; ASC 730.\n\n2. **\"What F&A \u002F indirect rate are you applying, and is it your negotiated NICRA, a de minimis 10%, or an assumption?\"**\n   Recommended: use the negotiated rate; if assumed, flag it explicitly.\n   Canon: 2 CFR 200 (Uniform Guidance); NICRA basics.\n\n3. **\"What's runway in months at current burn, and does it clear the next value-inflection milestone?\"**\n   Recommended: runway must cover the milestone plus a buffer; surface the gap.\n   Canon: Cooper stage-gate; SaaS\u002Fstartup efficiency frameworks (a16z, Bessemer).\n\n4. **\"Is portfolio ROI risk-adjusted (rNPV \u002F probability-of-success weighted) or raw NPV?\"**\n   Recommended: risk-adjusted; raw NPV overstates R&D value.\n   Canon: rNPV drug-development valuation; real-options literature.\n\n5. **\"Who is the named finance \u002F controller owner who signs the capitalize-vs-expense treatment?\"**\n   Recommended: name them — this tool recommends, it never books the entry.\n   Canon: ASC 730 \u002F IAS 38 governance; auditor sign-off requirements.\n\nWalk depth-first. Lock 1-2 before opening 3-5. After all are answered, invoke `program_budget_planner.py` → `burn_runway_tracker.py` → `capex_vs_opex_router.py`.\n","# research-finance\n\nFinancial management of internal R&D programs and portfolios: program budgeting with F&A, burn\u002Frunway tracking, and capitalize-vs-expense routing. Every number ships with its **assumptions block**, and accounting-treatment calls **route to a named finance owner** — this skill never books an entry.\n\n## Purpose\n\nR&D finance partners, program controllers, and operations leads manage money that has already been allocated or raised — not the corporate close, not the next funding round, not finding a grant. This skill structures three recurring decisions:\n\nThree deterministic tools:\n\n1. `program_budget_planner.py` — Builds a multi-period budget from work-package line items, applies the F&A (indirect) rate to an MTDC-style eligible base, and rolls up direct \u002F F&A \u002F fully-loaded cost per period with an explicit assumptions block.\n2. `burn_runway_tracker.py` — Computes average + trailing burn, runway in periods\u002Fmonths, and whether each value-inflection milestone is reachable before cash runs out. Flags accelerating burn and below-threshold runway.\n3. `capex_vs_opex_router.py` — Scores each R&D cost item against the IAS 38 development-phase criteria (or flags US GAAP ASC 730 expense-as-incurred) and routes it to **CAPITALIZE-CANDIDATE \u002F EXPENSE \u002F FINANCE-OWNER-REVIEW** with a named owner. Never auto-decides.\n\n## When to use\n\nInvoke this skill when:\n\n- You are building or revising an R&D program budget and need the F&A split made explicit.\n- A program's runway is in question and you need a milestone-vs-cash read.\n- Finance asks whether a development cost can be capitalized and you need a defensible first routing.\n- You are preparing a portfolio review and need per-program burn consistency.\n\n**Do NOT use this skill to**: run corporate DCF \u002F valuation \u002F close (use `finance\u002Ffinancial-analysis`), discover or position grants (use `research\u002Fgrants`), or make the final accounting determination (that is the controller's + auditor's call — this tool only routes).\n\n## Workflow\n\n1. **Lay out the program** — Fill `assets\u002Frd_program_budget_template.md` with work-package lines, categories, and per-period amounts.\n2. **Build the budget** — Run `program_budget_planner.py --input program.json --profile {pharma-rd|biotech|medtech|deep-tech|software-rd|university-lab} --fa-rate \u003Cnegotiated rate>`. Read direct \u002F F&A \u002F fully-loaded rollups + assumptions.\n3. **Track burn & runway** — Run `burn_runway_tracker.py --input ledger.json --threshold-months 6`. Read runway + milestone verdicts + flags.\n4. **Route accounting treatment** — Run `capex_vs_opex_router.py --input costs.json --standard {ifrs|usgaap}`. Read the per-item routing; send CAPITALIZE-CANDIDATE and FINANCE-OWNER-REVIEW items to the named owner.\n5. **Assemble the review** — Combine into a program-finance packet. Every number carries its assumptions; treatment calls carry a named owner.\n\n## Scripts\n\n| Script | Purpose | Profiles |\n|---|---|---|\n| `scripts\u002Fprogram_budget_planner.py` | Multi-period budget + F&A split + assumptions | pharma-rd, biotech, medtech, deep-tech, software-rd, university-lab |\n| `scripts\u002Fburn_runway_tracker.py` | Burn, runway, milestone-vs-cash alignment | n\u002Fa (ledger-driven) |\n| `scripts\u002Fcapex_vs_opex_router.py` | IAS 38 \u002F ASC 730 routing to named finance owner | pharma-rd, biotech, medtech, deep-tech, software-rd, university-lab |\n\nAll three: stdlib-only, `--help`, `--sample`, `--output {human,json}`.\n\n## Onboarding & customization\n\nRun the onboarding questionnaire **once before you start** — it captures your defaults so every tool in this skill is pre-configured. Customization is the point: the answers actually change tool behavior.\n\n```bash\npython3 scripts\u002Fonboard.py            # interactive (also: --defaults, --set key=value, --reset)\npython3 scripts\u002Fonboard.py --show     # see the questions + current effective config\n```\n\nAnswers are saved to `~\u002F.config\u002Fresearch-ops\u002Fresearch-finance.json` (global) or `.\u002F.research-ops\u002Fresearch-finance.json` (`--scope project`) and are read automatically by `config_loader.py`. They set the default R&D-area **profile**, the default **F&A rate**, the **runway alert threshold**, the **accounting standard**, and the named **finance owner** printed on capitalize-vs-expense routing. CLI flags always override saved config; `RESEARCH_OPS_NO_CONFIG=1` ignores it.\n\n**The five questions:** R&D area · F&A rate · runway threshold · accounting standard · finance owner.\n\n## Optimize with autoresearch (opt-in)\n\nThis skill ships an **isolated, opt-in** bridge to `engineering\u002Fautoresearch-agent`. Only when you ask to \"optimize\" \u002F \"extend runway\" \u002F \"run a loop\" does an autoresearch experiment iteratively improve a program plan against this skill's runway metric. `scripts\u002Far_evaluator.py` is the ground-truth evaluator; it prints `runway_months: \u003Cfloat>` (higher is better).\n\n```bash\n\u002Far:setup --domain custom --name extend-runway \\\n  --target ledger.json \\\n  --eval \"python3 ar_evaluator.py --target ledger.json\" \\\n  --metric runway_months --direction higher\n\u002Far:loop custom\u002Fextend-runway\n```\n\nIsolated: no hard dependency — autoresearch runs only on demand, and the loop edits `ledger.json`, never the evaluator.\n\n## References\n\n- `references\u002Frd_program_finance_canon.md` — IAS 38 (research vs development); ASC 730 + ASC 985-20; Uniform Guidance 2 CFR 200 (F&A); FASB\u002FIFRS capitalization criteria; NICRA basics.\n- `references\u002Fburn_and_portfolio.md` — Cooper stage-gate; rNPV \u002F real-options for R&D; risk-adjusted portfolio ROI; burn-rate \u002F runway frameworks; milestone-based budgeting.\n- `references\u002Findirect_rate_modeling.md` — F&A pool composition (facilities + administration); MTDC base; de minimis 10%; fringe\u002Foverhead loading; CAS primer.\n\n## Assumptions\n\n- The F&A rate is the most error-prone input. The planner applies whatever rate you pass; it warns you to confirm it is a negotiated NICRA, not a guess.\n- Burn\u002Frunway uses the trailing (recent-weighted) burn as the forward run-rate and assumes flat forward spend unless your ledger encodes a ramp.\n- The capex router asserts criteria from your input; asserting \"technical feasibility\" does not make it true — the named finance owner and auditor validate it.\n- Profiles annotate context (e.g., \"most drug R&D is expensed\") but do not change the accounting test.\n\n## Anti-patterns\n\n- **Stating a budget number without its assumptions.** F&A rate, escalation, and base must travel with the number.\n- **Auto-deciding capitalize-vs-expense.** This tool routes; the controller (and auditor where required) decides.\n- **Using lifetime-average burn for runway.** Recent burn is the honest forward run-rate; averages hide a slowdown or a ramp.\n- **Applying F&A to the full base.** Capital equipment, large subaward portions, and certain categories are MTDC-exempt.\n- **Confusing this with corporate finance.** Valuation, close, and fundraising live in `finance\u002F`.\n\n## Distinct from\n\n| Sibling \u002F neighbor | Scope | Difference |\n|---|---|---|\n| `finance\u002Ffinancial-analysis` | Corporate DCF, ratios, close, rolling forecast, SaaS metrics | That is **company-level**; this is **R&D-program-level** |\n| `research\u002Fgrants` | NIH funding discovery + positioning | That **finds funding**; this **manages money already won** |\n| `clinical-research` (sibling) | Study design + feasibility + budget gate-check | That **scopes** the study; this **funds + tracks** the program |\n| `ra-qm-team` | Regulatory\u002FQM submission | Unrelated — no financial scope |\n\n## Quick examples\n\n```bash\npython3 scripts\u002Fprogram_budget_planner.py --sample\npython3 scripts\u002Fprogram_budget_planner.py --input program.json --profile university-lab --fa-rate 0.585\npython3 scripts\u002Fburn_runway_tracker.py --sample --output json\npython3 scripts\u002Fcapex_vs_opex_router.py --sample --standard ifrs\n```\n\nThe sample budget excludes the sequencer (capital equipment) and CRO subaward from the F&A base; the capex router routes exploratory screening to EXPENSE, a fully-criteria'd pilot line to CAPITALIZE-CANDIDATE, and a partial-criteria software build to FINANCE-OWNER-REVIEW.\n\n## Forcing-question library (Matt Pocock grill discipline)\n\nWalked one at a time by `\u002Fcs:grill-research-ops` or the orchestrator. Recommended answer + canon citation per question. Never bundled.\n\n1. **\"Is this spend in the research phase or the development phase — and can you evidence technical feasibility?\"**\n   Recommended: research = expense; development = capitalize-candidate only with feasibility evidence, routed to a named finance owner.\n   Canon: IAS 38.54-57; ASC 730.\n\n2. **\"What F&A \u002F indirect rate are you applying, and is it your negotiated NICRA, a de minimis 10%, or an assumption?\"**\n   Recommended: use the negotiated rate; if assumed, flag it explicitly.\n   Canon: 2 CFR 200 (Uniform Guidance); NICRA basics.\n\n3. **\"What's runway in months at current burn, and does it clear the next value-inflection milestone?\"**\n   Recommended: runway must cover the milestone plus a buffer; surface the gap.\n   Canon: Cooper stage-gate; SaaS\u002Fstartup efficiency frameworks (a16z, Bessemer).\n\n4. **\"Is portfolio ROI risk-adjusted (rNPV \u002F probability-of-success weighted) or raw NPV?\"**\n   Recommended: risk-adjusted; raw NPV overstates R&D value.\n   Canon: rNPV drug-development valuation; real-options literature.\n\n5. **\"Who is the named finance \u002F controller owner who signs the capitalize-vs-expense treatment?\"**\n   Recommended: name them — this tool recommends, it never books the entry.\n   Canon: ASC 730 \u002F IAS 38 governance; auditor sign-off requirements.\n\nWalk depth-first. Lock 1-2 before opening 3-5. After all are answered, invoke `program_budget_planner.py` → `burn_runway_tracker.py` → `capex_vs_opex_router.py`.\n",{"name":5,"tags":52,"author":57,"license":14,"version":58,"description":7,"compatible_tools":59},[40,5,39,42,53,54,55,56],"runway","fa-rate","capitalize-vs-expense","portfolio","claude-code-skills","2.9.0",[60,61,62,63,64,65],"claude-code","codex-cli","cursor","antigravity","opencode","gemini-cli","claude\u002Fai-personal-assistant-main","fb33f7f5b3a206eb019c788e3c48e91c02ccb1f9",".claude\u002Fskills\u002Fclaude-skills\u002Fresearch-finance",0,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI","https:\u002F\u002Farshad-ai-seven.vercel.app","https:\u002F\u002Fgithub.com\u002Fmarshadgani","2026-11-02 00:51:35",{"source":8,"skillName":5,"commands":75,"prompt":85,"zipAvailable":86},[76,79,82],{"tool":77,"command":78},"npx","npx skills add marshadgani\u002FArshad.AI --skill research-finance",{"tool":80,"command":81},"bunx","bunx skills add marshadgani\u002FArshad.AI --skill research-finance",{"tool":83,"command":84},"pnpm","pnpm dlx skills add marshadgani\u002FArshad.AI --skill research-finance","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fresearch-finance\u002FSKILL.md",true,[88,94,100,104,108,114,118,122,126,130],{"path":89,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":92,"sourceHtmlUrl":93},"assets\u002Frd_program_budget_template.md","ASSET","资产文件",1792,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fresearch-finance\u002Fassets\u002Frd_program_budget_template.md",{"path":95,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fburn_and_portfolio.md","REFERENCE","参考文档",2776,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fresearch-finance\u002Freferences\u002Fburn_and_portfolio.md",{"path":101,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Findirect_rate_modeling.md",2459,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fresearch-finance\u002Freferences\u002Findirect_rate_modeling.md",{"path":105,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Frd_program_finance_canon.md",2833,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fresearch-finance\u002Freferences\u002Frd_program_finance_canon.md",{"path":109,"resourceType":110,"resourceTypeDesc":111,"sizeBytes":112,"sourceHtmlUrl":113},"scripts\u002Far_evaluator.py","SCRIPT","脚本",2468,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fresearch-finance\u002Fscripts\u002Far_evaluator.py",{"path":115,"resourceType":110,"resourceTypeDesc":111,"sizeBytes":116,"sourceHtmlUrl":117},"scripts\u002Fburn_runway_tracker.py",6312,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fresearch-finance\u002Fscripts\u002Fburn_runway_tracker.py",{"path":119,"resourceType":110,"resourceTypeDesc":111,"sizeBytes":120,"sourceHtmlUrl":121},"scripts\u002Fcapex_vs_opex_router.py",7658,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fresearch-finance\u002Fscripts\u002Fcapex_vs_opex_router.py",{"path":123,"resourceType":110,"resourceTypeDesc":111,"sizeBytes":124,"sourceHtmlUrl":125},"scripts\u002Fconfig_loader.py",3912,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fresearch-finance\u002Fscripts\u002Fconfig_loader.py",{"path":127,"resourceType":110,"resourceTypeDesc":111,"sizeBytes":128,"sourceHtmlUrl":129},"scripts\u002Fonboard.py",4267,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fresearch-finance\u002Fscripts\u002Fonboard.py",{"path":131,"resourceType":110,"resourceTypeDesc":111,"sizeBytes":132,"sourceHtmlUrl":133},"scripts\u002Fprogram_budget_planner.py",7185,"https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fclaude-skills\u002Fresearch-finance\u002Fscripts\u002Fprogram_budget_planner.py",[135,168,194,223,253,277],{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":139,"licenseFileUrl":140,"sourceHtmlUrl":141,"categories":142,"keywords":149,"publishedAt":167},"01M71MVWH15PQRS9KT3J24D7WV","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[143,146],{"categoryNo":144,"categoryName":145,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":147,"categoryName":148,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166],"webapp","testing","webapp testing","for","applications","local","frontend","debugging","toolkit","logs","browser","with","playwright","web","behavior","ui","screenshots","2026-11-10 10:56:23",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":139,"licenseFileUrl":172,"sourceHtmlUrl":173,"categories":174,"keywords":176,"publishedAt":167},"01M71MVMAZ1J606SGA4JPHRDAZ","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fweb-artifacts-builder\u002FSKILL.md",[175],{"categoryNo":147,"categoryName":148,"taxonomyType":20,"taxonomyTypeDesc":21},[177,178,179,163,180,181,182,153,183,184,156,185,186,187,188,189,190,191,192,193],"builder","artifacts builder","artifacts","web artifacts builder","single-file","css","Tailwind","ui components","single","use","file","components","react","multi","state","routing","state management",{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":198,"sourceHtmlUrl":199,"categories":200,"keywords":207,"publishedAt":167},"01M71MSTFAEYT9J9GA587SP3RB","ui-styling","Create beautiful, accessible user interfaces with shadcn\u002Fui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user interfaces, implementing design systems, creating responsive layouts, adding accessible components (dialogs, dropdowns, forms, tables), customizing themes and colors, implementing dark mode, generating visual designs and posters, or establishing consistent styling patterns across applications.","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fui-ux-pro-max\u002Fui-styling\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fui-ux-pro-max\u002Fui-styling\u002FSKILL.md",[201,204],{"categoryNo":202,"categoryName":203,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":205,"categoryName":206,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000032","设计师",[208,209,165,182,183,210,211,212,213,214,215,216,32,188,217,218,219,220,221,222],"ui styling","styling","mode","canvas","implementing","design","themes","utility","design systems","across","create","component","layout","forms","patterns",{"skillNo":224,"name":213,"nameZh":6,"description":225,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":226,"categories":227,"keywords":236,"publishedAt":167},"01M71MSM72HXKQRCY5D45WYPNP","Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini, Atlas Cloud, or MuAPI AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social\u002Fads\u002Fweb\u002Fprint), icon design (15 styles, SVG, Gemini 3.1 Pro), social photos (HTML→screenshot, multi-platform). Actions: design logo, create CIP, generate mockups, build slides, design banner, generate icon, create social photos, social media images, brand identity, design system. Platforms: Facebook, Twitter, LinkedIn, YouTube, Instagram, Pinterest, TikTok, Threads, Google Ads.","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fui-ux-pro-max\u002Fdesign\u002FSKILL.md",[228,231,232,235],{"categoryNo":229,"categoryName":230,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":202,"categoryName":203,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":233,"categoryName":234,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":205,"categoryName":206,"taxonomyType":25,"taxonomyTypeDesc":26},[213,237,238,239,208,240,241,242,243,218,244,245,246,247,248,249,250,251,165,252],"Media","tiktok","actions","logo","logo generation","chart","multi-platform","ads","youtube","generate","presentations","google","atlas cloud","screenshot","muapi","identity",{"skillNo":254,"name":255,"nameZh":6,"description":256,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":257,"categories":258,"keywords":261,"publishedAt":167},"01M71MSH9T7S227MN2YSYB2EP5","design-system","Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing\u002Ftypography scales, component specs, strategic slide creation. Use for design tokens, systematic design, brand-compliant presentations.","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fui-ux-pro-max\u002Fdesign-system\u002FSKILL.md",[259,260],{"categoryNo":202,"categoryName":203,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":205,"categoryName":206,"taxonomyType":25,"taxonomyTypeDesc":26},[213,262,263,182,264,265,266,267,219,247,268,269,270,271,272,273,274,153,275,276],"design system","system","css variables","creation","Variables","architecture","systematic","token","spacing","layer","typography","brand","three","tokens","slide generation",{"skillNo":278,"name":279,"nameZh":6,"description":280,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":281,"categories":282,"keywords":285,"publishedAt":167},"01M71MSCFZ1HFMNBDMAFXDZV92","banner-design","Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with optional generated or supplied visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter\u002FX, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold typography, photo-based, illustrated, geometric, retro, glassmorphism, 3D, neon, duotone, editorial, collage.","https:\u002F\u002Fgithub.com\u002Fmarshadgani\u002FArshad.AI\u002Fblob\u002Fclaude\u002Fai-personal-assistant-main\u002F.claude\u002Fskills\u002Fui-ux-pro-max\u002Fbanner-design\u002FSKILL.md",[283,284],{"categoryNo":202,"categoryName":203,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":205,"categoryName":206,"taxonomyType":25,"taxonomyTypeDesc":26},[213,286,287,237,288,289,290,239,291,292,293,294,295,296,218,244,245,246,297,298],"banner","banner design","3D","direction","neon","Art","social","generated","hero","dimensions","display","options","website"]