Private Company Research
Deep research framework for pre-IPO / private companies (Ant Group, SpaceX, Stripe...
Install
npx skills add HKUDS/Vibe-Trading --skill private-company-research -g -a claude-code -y- Repository
- HKUDS/Vibe-Trading37.4k
- Category
- Writing
- Updated
- 3d ago
- License
- MIT
- Context cost
- Mediumabout 3,000 tokens
- Runs scripts
- No, instructions only
What it does
Deep research framework for pre-IPO / private companies (Ant Group, SpaceX, Stripe, ByteDance...). Six analyst lenses, business model, financial forensics, competitive landscape, risk & governance, tech & IP, alternative-data signals, run in parallel via run_swarm, then cross-validated for signal consistency before any verdict. Built around the core challenge of private-company work: information is scarce, so every data point carries a confidence label (high / medium / low), inference is shown separately from fact, and 'I don't know' is a valid output. Outputs a fair-value range, exit-path analysis, and an information-gap map. Use for any unlisted company where you need to judge what the business is actually worth.
Private-Company Research: Multi-Lens Deep Framework
Deep research on an unlisted company (e.g. Ant Group, ByteDance, SpaceX, Stripe).
Ultimate goal: under information scarcity, recover the company's true value, not the market valuation, but what the business is actually worth.
Framework Characteristics
Private vs public research: no standardized financials (multi-source patchwork + cross-validation); few valuation anchors (funding rounds, comparables, scenarios); large information asymmetry ("jigsaw" research); uncertain exit path (IPO / M&A / secondary).
AI Research Bias Self-Check (core premise)
Private companies are where AI bias is worst. Watch for:
- False conservatism, with little data, AI gives conservative/vague conclusions, but scarce data ≠ bad company.
- False precision, to fill the template, AI disguises "reasonable guess" as "sourced analysis".
- Comparables trap, forcing a public-comp overlay inherits public-market logic and misses private-specific value.
- Survivorship bias, what's searchable online is mostly company-propagated good news.
Counter: prefer leaving blanks ("I don't know") over filling tables with speculation to fake certainty; label every data point with confidence (🟢high/🟡medium/🔴low); separate verifiable fact from inference; when information is extremely scarce, switch to "first-principles mode" and answer only: ① what real problem does this business solve? ② why this team? ③ ceiling if it succeeds / how it dies if it fails? ④ the key validation node at this stage?
Invert the asymmetry: the market knows little about private companies → pricing is inefficient → that's exactly where alpha may live.
Execution
Six lenses, best run in parallel (via run_swarm, one worker per lens; or sequentially via web_search):
