agentleFS
d-wweid-wwei/openclaw-financial-services/skills/fsi-lseg-cmd-analyze-bond-rv/SKILL.md

fsi-lseg-cmd-analyze-bond-rv

Skill16 starsChanged 9 months agoApache-2.0View on GitHub

Analyze a bond's relative value vs yield curves and credit spreads with scenario stress testing — usage: /analyze-bond-rv <ISIN, RIC, or CUSIP> [vs benchmark]

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 3 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask the user for:

    line 21
  2. Very specific:

    Call bond_price with the identifier(s).

    line 28
  3. Distinctive:

    If benchmark provided, price that too.

    line 32
  4. Very specific:

    Call interest_rate_curve (list then calculate) for the bond's currency.

    line 36
  5. Very specific:

    Call credit_curve (search by country/issuerType, then calculate).

    line 42
  6. Very specific:

    Call yieldbook_scenario with parallel rate shifts: -100bp, -50bp, 0bp, +50bp, +100bp.

    line 48
  7. Distinctive:

    If benchmark provided, include side-by-side comparison.

    line 56

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Analyze Bond Relative Value

This command uses LSEG bond pricing, yield curves, credit curves, and scenario analysis tools. See CONNECTORS.md for available tools.

Perform relative value analysis on one or more bonds by combining pricing analytics, yield curve context, credit spread decomposition, and rate shock scenarios.

See the bond-relative-value skill for domain knowledge on spread frameworks and rich/cheap assessment.

Workflow

1. Gather Bond Identifiers

Ask the user for:

  • Bond identifier(s) — ISIN, RIC, or CUSIP (required)
  • Optional benchmark bond for comparison
  • Valuation date (optional, defaults to today)

2. Price the Bond(s)

Call bond_price with the identifier(s).

Extract: clean/dirty price, yield, duration, convexity, DV01, currency.

If benchmark provided, price that too.

3. Get the Risk-Free Yield Curve

Call interest_rate_curve (list then calculate) for the bond's currency.

Interpolate at the bond's maturity to compute G-spread.

4. Get the Credit Spread Curve

Call credit_curve (search by country/issuerType, then calculate).

Compute residual spread = bond G-spread minus credit curve spread at matching maturity. Positive residual = cheap; negative = rich.

5. Run Scenario Analysis

Call yieldbook_scenario with parallel rate shifts: -100bp, -50bp, 0bp, +50bp, +100bp.

Extract price change and P&L under each scenario.

6. Synthesize the Report

Present: bond summary table, spread decomposition (G-spread, credit spread, residual), scenario P&L table, and rich/cheap assessment.

If benchmark provided, include side-by-side comparison.

Output Format

Lead with the rich/cheap assessment and supporting evidence. Follow with spread decomposition and scenario tables.

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.