Write a publication-grade 8-part deep-dive series on a single company (~120k words total): cognitive reset / moat / profit engine / hidden assets / era variable (e.g. AI) / financials Buffett-style / management / valuation+redlines. The core IP is NOT writing but REVISING — a strict fact-check check
thesis-tracker
An AI skill for Claude Code, Cursor, Codex and other AI agents, from HKUDS/Vibe-Trading. Scored by fixed code checks, no AI.
CCode 60/100Builder 0/10
Buy-side discipline system. For each holding, maintain a written investment thesis — core thesis in 5 sentences, falsifiable assumptions, red lines, valuation anchors — and re-check it each quarter against new earnings/events. Scores thesis health 1-10 from assumption breakage and red-line triggers, and recommends hold / add / trim / exit. Use it right after buying a stock (to write the thesis) and every earnings season (to check it). Bridges the research→buy→monitor gap that most investors skip.
Install
npx skills add HKUDS/Vibe-Trading --skill thesis-tracker
Where do I paste this?
Open a terminal in your project folder, paste the command and press Enter. It needs Node.js on your computer.
Run it in your project. The skills CLI asks which agents to install it for (Claude Code, Cursor, Codex and more); add -g to install it for your user instead.
No terminal? Copy SKILL.md and give it to your AI as instructions.
SKILL.md
A skill is instructions and scripts your agent will follow, so read it before you install it. Its text loads here from GitHub; you can also read it on GitHub.
More skills from HKUDS/Vibe-Trading
Supply-chain bottleneck arbitrage. Given a super-trend (AI infra, energy transition, defense, semiconductor reshoring, space economy), decompose its physical supply chain down to Layer 2/3 choke points (optics, lasers, InP/SOI substrates, IC substrates, probe cards, specialty fiberglass...) and surf
Diagnose failed or underperforming backtests, locate the root cause, and fix the issue
Create, modify, and optimize quantitative trading strategies, then backtest and evaluate them.
A short self-bias checklist to run at the START of any investment research task (stock screen / sector study / company deep-dive). Four biases that systematically warp AI research — leader-bias (only big caps), English-bias (miss JP/KR/TW players), narrative-bias (chase concept labels), confirmation
Map research needs to gateway-backed tools. The runtime gateway owns source routing, bounded acquisition and caching; preserve credentials and source provenance.
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
Strategy Development Manager: convert academic papers and research reports into validated factors and strategies with automated backtesting, persistent storage, and decay monitoring.