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

bloomberg-terminal

Skill15 starsChanged 5 months agoMITView on GitHub

Bloomberg's financial data platform; lets an agent fetch real-time and historical price data, volatility surfaces, rates curves, credit spreads, and sell-side research via the Bloomberg API.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Test connectivity with blpapi Python SDK SessionOptions before issuing data requests

    line 37
  2. Distinctive:

    All data retrieved via Bloomberg is subject to Bloomberg's redistribution restrictions — do not write raw output to unauthenticated …

    line 38

≈ “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

Bloomberg Terminal

What it is

Bloomberg Terminal (accessed programmatically via the Bloomberg API / BPIPE or the Bloomberg Data License) is the primary market data and research platform for capital markets professionals. It provides real-time pricing, historical time series, volatility surfaces, rates curves, credit spreads, earnings data, and sell-side research notes across all asset classes.

When to use this skill

  • Retrieve real-time or historical prices, bid/ask spreads, or total return data for equities, fixed income, FX, or commodities
  • Pull interest rate curves, volatility surfaces, or credit spread term structures for risk or scenario analysis
  • Access sell-side research notes, sector primers, or earnings estimates by ticker
  • Fetch corporate action data, dividend schedules, or index constituent weights
  • Support stress scenario construction with cross-asset market data inputs
  • Troubleshoot Bloomberg Terminal connectivity or BPIPE API issues for staff

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:

  • BLOOMBERG_API_HOST - Bloomberg API server hostname or IP (e.g. localhost for BPIPE)
  • BLOOMBERG_API_PORT - BPIPE service port (default 8194)
  • BLOOMBERG_DATA_LICENSE_KEY - Data License credential for server-side B-PIPE or DL access

Key operations

  • ReferenceDataRequest — snapshot field values for one or more securities (price, rating, fundamentals)
  • HistoricalDataRequest — time-series data for a security and field over a date range
  • IntradayTickRequest / IntradayBarRequest — intraday tick or OHLCV bar data
  • FieldSearchRequest — discover available Bloomberg fields by mnemonic or keyword
  • Bloomberg Data License bulk extract — overnight delivery of large datasets (constituents, index weights)

Notes

  • BPIPE requires a Bloomberg Terminal or server-side license; an active B-PIPE session must be running on the host
  • Data License (DL) is the server-side bulk delivery product — different from BPIPE; separate entitlements apply
  • Bloomberg enforces concurrent session limits per license; avoid spawning parallel request threads without connection pooling
  • Test connectivity with blpapi Python SDK SessionOptions before issuing data requests
  • All data retrieved via Bloomberg is subject to Bloomberg's redistribution restrictions — do not write raw output to unauthenticated endpoints

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