awesome-investor-agent-skills
llms.txt0 starsChanged 10 days agoCC0-1.0View on GitHub
Web-first catalog and one portable agent skill for investor research: filings, public market data, portfolio maths, and leakage-safe backtesting. Research and simulation only — never personalized investment advice. Audience: researchers and builders mapping public financial tooling into a source-backed agent workflow, plus agents asked to shortlist investor or quant tooling. Not for anyone looking for trade signals or capital allocation. No package install and no build step. The catalog is README.md; the weekly research loop is described there and run…
- Reads credentials
In this repository2 other files it gives its agents.
- AGENTS.mdAGENTS.md
- investor-researchSkill
The file
We split this llms.txt into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
No package install and no build step.
- Distinctive: line 16
Run the harvester yourself (it only proposes):
- Distinctive: line 42
No secrets, private positions, account data, or wallet material.
≈ “Common” is an estimate: at least 1 in 5 of the 3,806 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
# Awesome Investor Agent Skills
> Web-first catalog and one portable agent skill for investor research: filings, public market data, portfolio maths, and leakage-safe backtesting. Research and simulation only — never personalized investment advice.
Audience: researchers and builders mapping public financial tooling into a source-backed agent workflow, plus agents asked to shortlist investor or quant tooling. Not for anyone looking for trade signals or capital allocation.
## How to use
No package install and no build step. The catalog is `README.md`; the weekly research loop is described there and run by `.github/workflows/weekly-harvest.yml`.
Health checks, the same ones CI runs:
node scripts/validate-catalog.mjs
node --test "scripts/*.test.mjs"
Run the harvester yourself (it only proposes):
GITHUB_TOKEN=... node scripts/harvest.mjs
To use the skill, copy the folder into a skills directory your agent reads (for example `.agents/skills/` in a project):
git clone https://github.com/Agentic-Income/awesome-investor-agent-skills
cp -r awesome-investor-agent-skills/skills/investor-research <your-project>/.agents/skills/
## Key files
- `README.md` — the catalog: curated table, weekly research loop, contribution standard, research method.
- `skills/investor-research/SKILL.md` — the skill: inputs, rules, and the required output shape, ending in a human approval gate.
- `data/repos.json` — reviewed entries, each carrying category, asset class, execution risk, privacy risk, why included, what it is not for, and a review date.
- `data/sources.json` — the search sources the weekly harvester watches. Edit this to change what is monitored.
- `scripts/harvest.mjs` — opens a pull request with a report; it never adds an entry on its own.
- `reports/` — dated harvest reports.
- `docs/paths/` — path docs for crypto investing, general investor research, OSS terminal work, risk and custody, and trading systems.
- `AGENTS.md` — repo classification, health commands, and agent rules.
## Scope and exclusions
- Research, memo, backtest, and simulation outputs only. No live trading, no capital movement, no wallet actions.
- Execution-adjacent projects are labeled as such; keep their use to public data and simulation.
- Licence traps are named up front. Never copy code from AGPL, GPL, unlicensed, or custom-licence projects into another repository.
- A human reviewer decides what enters `data/repos.json`. Harvest output is a proposal, and SPDX detection is a hint, not a judgement.
- No secrets, private positions, account data, or wallet material.
- Nothing here is investment, legal, tax, accounting, or compliance advice, and inclusion is not an endorsement.
- Content is dedicated to the public domain under CC0 1.0.
## Links
- [README](./README.md)
- [AGENTS.md](./AGENTS.md)
- [Organization profile](https://github.com/Agentic-Income)
- [Sibling catalog: awesome-wealth-agent-skills](https://github.com/Agentic-Income/awesome-wealth-agent-skills)
- [Sibling catalog: awesome-agentic-income](https://github.com/Agentic-Income/awesome-agentic-income)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

