agentleFS
Sign inStart free
iblaiiblai/financial-services-agents/skills/factset/SKILL.md

factset

Skill15 starsChanged 5 months agoMITView on GitHub

FactSet financial data and research platform; lets an agent retrieve equity fundamentals, earnings estimates, sell-side research, sector classifications, and benchmark data for investment analysis and reporting.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Run custom security screening on fundamental or estimate criteria

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

FactSet

What it is

FactSet is an integrated financial data and analytics platform used by buy-side and sell-side professionals for fundamental equity research, portfolio analytics, and risk management. It aggregates data from thousands of global sources including company financials, consensus estimates, broker research, ownership data, and index constituents. In this segment, FactSet serves the client advisory, portfolio analysis, and risk assessment agents as a primary data backbone.

When to use this skill

  • Retrieve equity fundamentals: revenue, EPS, P/E, EV/EBITDA, debt/equity, dividend yield
  • Pull consensus earnings estimates and earnings calendar entries by ticker
  • Access sell-side research reports, analyst ratings, and price targets
  • Retrieve GICS sector and industry classification for portfolio construction or attribution
  • Pull benchmark index constituents and weights for tracking error or active share analysis
  • Run custom security screening on fundamental or estimate criteria

Credentials

This skill authenticates using env vars declared in metadata above. Set them in ~/.openclaw/.env (see .env.example at the config root). Required variables:

  • FACTSET_API_KEY - FactSet API key (username-serial format, e.g. USERNAME-SERIAL)
  • FACTSET_API_SECRET - FactSet API secret / password
  • FACTSET_BASE_URL - API base URL (e.g. https://api.factset.com/content)

Key operations

  • POST /factset-fundamentals/v2/fundamentals — retrieve fundamental data for a list of securities
  • POST /factset-estimates/v2/consensus-estimates — pull consensus EPS/revenue estimates by period
  • POST /factset-estimates/v2/rolling-estimates — retrieve rolling 12-month estimate series
  • GET /factset-prices/v1/prices — fetch historical or current price data
  • POST /factset-security-research/v1/research — retrieve research reports by security or analyst
  • POST /factset-benchmarks/v1/constituents — pull index constituent weights and returns

Notes

  • FactSet API uses HTTP Basic Auth with the API key as username and secret as password; some endpoints additionally require an OAuth2 bearer token
  • Rate limits vary by endpoint tier; core data endpoints allow ~10 requests/second; analytics endpoints may be lower
  • FactSet environment URLs: production uses api.factset.com; a developer sandbox is available at api-sandbox.factset.com
  • Data entitlements are enforced at the API layer — a 403 on a specific dataset indicates a missing content subscription, not an auth failure

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