agentsclimarketplace

Finance

Skill coco-research/coco/systems/superintelligence/finance

Meet Coco. A superintelligent agent framework powered by an advisory board of 389 world-class minds. Scale your AI assistant into a complete engineering department with 142 skills, 277 commands, and persistent state. Universal compatibility. Local privacy. Free and open source.

Install
npx -y skills add coco-research/coco --skill finance

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.

SKILL.md

2.4 KB, as published. Nobody here has run it

Finance Super Intelligence Team

Rijul's finance brain trust and decision partner. Named personas across 7 cells: valuation/corporate finance, investing, accounting/FP&A, macro, fintech, behavioral, and capital markets/M&A/private. Markets/quant/derivatives are reserved for the Trading team. Built local-first (LM Studio) and validator-gated. Invoked by /SI-Fin commands.

39 native personas (0 cross-listed) across 7 cells. Real public figures rendered as illustrative composites — see superintelligence/DISCLAIMER.md. Built local-first + Claude-research, validator-gated (real cited URLs, no fabrication).

Cells

CellPersonasFocus
valuation-corporate-finance6Valuation, corporate finance, intrinsic value, capital structure.
investing-capital-allocation7Value / discretionary investing and capital allocation.
accounting-fpa-reporting4Forensic accounting, financial reporting, and FP&A practice.
macro-economics7Macro economists and policy / markets framing.
fintech-payments5Fintech, payments, banking-as-a-service, fintech investing.
behavioral-decision-science6Behavioral finance and decision-making under uncertainty.
capital-markets-ma-private4IPOs, M&A, private equity / VC finance, distress and restructuring.

Command surface

  • Orchestrate (smart panel): /SI-Fin-Orchestrate "<prompt>" → picks 16-32 personas + approval gate
  • Action verbs: /SI-Fin-Decide · -Tradeoff · -Pre-Mortem · -Review · -Stress-Test · -Plan · -Design · -Analyse · -Vote · -Debug · -Defend · -Roast · -Post-Mortem · -Re-Analyse · -Full-Cycle
  • Identity: /SI-Fin-Ask <slug> "<q>" · -Huddle <cell> "<topic>" · -Meeting "<prompt>" · -Read <slug>
  • Roster/maintenance: /SI-Fin-Recruit · -Refresh · -VoiceCheck · -Verify

Cross-team

For multi-domain decisions, the top-level /SI-Orchestrate (+ /SI-<Verb>) routes ACROSS teams via superintelligence/scripts/meta_select.py (local nomic-embed). This team auto-joins that panel.

Source of truth

registry.json (generated from persona frontmatter) + cells/*.md + roster.json. Regenerate: python3 finance/scripts/build_registry.py && python3 finance/scripts/build_cells.py.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.