Have an AI agent run a structured valuation checklist before giving an opinion on a stock.
Cross-check a company's announcements, financial reports, and analyst research before analysis.
Build pessimistic, neutral, and optimistic valuation scenarios for a stock or sector.
Get a proposed position-sizing plan along with conditions that would invalidate the thesis.
| ncuzlyang/dangforge | 0petru/sentimo | 0xblackash/cve-2026-46333 | |
|---|---|---|---|
| Stars | 17 | 17 | 17 |
| Language | — | Python | C |
| Setup difficulty | easy | moderate | moderate |
| Complexity | — | 3/5 | 4/5 |
| Audience | pm founder | developer | researcher |
Figures from each repo's GitHub metadata at analysis time.
Requires an AI agent capable of reading a GitHub repository, such as Claude Code or Codex, or the separately hosted MuseAI service.
DangForge is not a piece of software you run directly. It is a written skill, a structured set of instructions in Chinese, meant to be handed to an AI agent like Claude Code, Codex, or Cursor Agent so the agent follows a consistent process when analyzing a stock. It is based on a value investing framework attributed to someone referred to as MR Dang. The idea behind it is simple: instead of letting an AI write a smooth sounding but shallow summary about a stock, the skill forces the agent through a fixed checklist before it gives an opinion. That checklist includes pulling the latest data, cross checking company announcements, financial reports, and analyst research against each other, examining the underlying business model, breaking down what drives profit, calculating both a simple valuation and a forward looking price to earnings ratio, building pessimistic, neutral, and optimistic scenarios, estimating expected dividend yield and cash flow, and finally proposing a position sizing plan along with specific conditions that would prove the original thesis wrong. To use it, someone working with an AI agent that can read GitHub repositories simply shares the repository link and asks the agent to install and use the skill, then asks it to analyze a specific stock by name or ticker. The README also points to a separate hosted service called MuseAI as an easier option for people who do not want to set up their own agent environment, since it can read the repository and run the same analysis process directly. The project includes an explicit disclaimer that it is meant only for education, research, and learning about investment analysis methodology, and that it does not constitute investment advice, a securities recommendation, or any promise of returns.
A Chinese-language AI agent skill that walks an AI through a structured value-investing checklist before analyzing a stock.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly pm founder.
This repo across BitVibe Labs
Verify against the repo before relying on details.