agentleFS
Sign inStart free
MicrosoftKnown publishermicrosoft/PilotSwarm/examples/agent-packages/finance-research-lab/skills/finance-research-standards/SKILL.md

finance-research-standards

Skill14 starsChanged 8 months agoMITView on GitHub

Evidence, timestamp, numerical, and communication standards for stock and finance research.

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Put an explicit as-of date and timezone on current-data work.

    line 8
  2. Distinctive:

    Prefer primary sources: regulator filings, issuer releases, exchange notices, court records, and official economic data.

    line 9
  3. Distinctive:

    Treat search results and aggregators as leads.

    line 11
  4. Distinctive:

    Use tools for material arithmetic and show formulas or assumptions.

    line 17
  5. Distinctive:

    Never invent missing data, citations, consensus estimates, or probabilities.

    line 19
  6. Distinctive:

    Use conditional language for forecasts and disclose stale, unavailable, or inaccessible sources.

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Finance Research Standards

  1. Put an explicit as-of date and timezone on current-data work.
  2. Prefer primary sources: regulator filings, issuer releases, exchange notices, court records, and official economic data.
  3. Treat search results and aggregators as leads; open the underlying source before relying on a material claim.
  4. Preserve currency, units, fiscal period, filing date, price timestamp, and whether a value is reported, adjusted, estimated, or calculated.
  5. Separate fact, management claim, estimate, inference, and scenario.
  6. Use tools for material arithmetic and show formulas or assumptions.
  7. Seek disconfirming evidence and state what would change the conclusion.
  8. Never invent missing data, citations, consensus estimates, or probabilities.
  9. Use conditional language for forecasts and disclose stale, unavailable, or inaccessible sources.
  10. Provide research rather than personalized investment, tax, accounting, or legal advice.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free