awesome-investor-agent-skills
AGENTS.md0 starsChanged 10 days agoCC0-1.0View on GitHub
This repo is part of the FrankX / Starlight / Arcanea agent estate. Summarize changed files, validation run, source gaps, risks, and follow-up.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 33,315 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository2 other files it gives its agents.
- llms.txtllms.txt
- investor-researchSkill
The file
We split this AGENTS.md into the rules it gives an agent
9 rules. About 1 is common, 7 are distinctive, and 1 is very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈7
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
Default health command: node scripts/validate-catalog.mjs (portable, runs in CI).
- Distinctive: line 15
Read this file before making changes.
- Distinctive: line 17
Keep edits scoped to public-safe investor research catalogs, paths, docs, and skills.
- Distinctive: line 18
Prefer primary sources and active projects.
- Common: line 19
Avoid private paths, private strategy, account data, wallet material, seed phrases, API keys, and unsourced rankings.
- Distinctive: line 20
Do not make financial, investment, legal, tax, accounting, securities, or compliance claims.
- Distinctive: line 22
Treat trading bots and crypto tools as research and simulation references unless a human explicitly approves a separate private execution …
- Distinctive: line 23
Run the health command before handoff when feasible.
- Distinctive: line 25
Never copy code from AGPL, GPL, unlicensed or custom-licence projects into another repository.
≈ “Common” is an estimate: at least 1 in 5 of the 42,283 AGENTS.md 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
Repository Instructions
This repo is part of the FrankX / Starlight / Arcanea agent estate.
Classification
- Repo:
awesome-investor-agent-skills - Class: content-or-program, public-safe research catalog
- Default health command:
node scripts/validate-catalog.mjs(portable, runs in CI);./scripts/validate-catalog.ps1remains for Windows - Tests:
node --test "scripts/*.test.mjs"(offline) - Remote target:
https://github.com/Agentic-Income/awesome-investor-agent-skills
Agent Rules
- Read this file before making changes.
- Preserve existing user work and unrelated dirty files.
- Keep edits scoped to public-safe investor research catalogs, paths, docs, and skills.
- Prefer primary sources and active projects.
- Avoid private paths, private strategy, account data, wallet material, seed phrases, API keys, and unsourced rankings.
- Do not make financial, investment, legal, tax, accounting, securities, or compliance claims.
- Label execution-adjacent projects clearly.
- Treat trading bots and crypto tools as research and simulation references unless a human explicitly approves a separate private execution design.
- Run the health command before handoff when feasible.
- The weekly harvest only proposes. Never edit
data/repos.jsonfrom harvest output without reading each candidate's LICENSE and README; SPDX detection is a hint, and keyword-based execution risk is a default, not a judgement. - Never copy code from AGPL, GPL, unlicensed or custom-licence projects into another repository.
Handoff
Summarize changed files, validation run, source gaps, risks, and follow-up.
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.

