agentleFS
d-wweid-wwei/openclaw-financial-services/skills/fsi-lseg-cmd-review-fi-portfolio/SKILL.md

fsi-lseg-cmd-review-fi-portfolio

Skill16 starsChanged 9 months agoApache-2.0View on GitHub

Review a fixed income portfolio with pricing, reference data, cashflows, and scenario analysis — usage: /review-fi-portfolio <ISIN1,ISIN2,...> [scenario e.g. +100bp]

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 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.

  • 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 all identifiers.

    line 29
  3. Very specific:

    Call yieldbook_bond_reference for each bond.

    line 37
  4. Very specific:

    Call yieldbook_scenario with rate shifts: -200bp, -100bp, -50bp, 0bp, +50bp, +100bp, +200bp.

    line 51
  5. Very specific:

    Call interest_rate_curve for the portfolio's primary currency.

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Review Fixed Income Portfolio

This command uses LSEG bond pricing, YieldBook analytics, and yield curve tools. See CONNECTORS.md for available tools.

Produce a consolidated fixed income portfolio risk and return report by pricing all holdings, enriching with reference data, projecting cashflows, and stress testing under rate scenarios.

See the fixed-income-portfolio skill for domain knowledge on portfolio analytics and scenario analysis.

Workflow

1. Gather Portfolio Holdings

Ask the user for:

  • Bond identifiers (required) — comma-separated ISINs, CUSIPs, or RICs
  • Position sizes/weights (optional — if not provided, assume equal weight)
  • Specific scenario to test (optional — e.g., "+100bp", defaults to standard grid)
  • Valuation date (optional, defaults to today)

2. Price All Bonds

Call bond_price with all identifiers.

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

Aggregate portfolio-level: weighted yield, weighted duration, total DV01, total market value.

3. Enrich with Reference Data

Call yieldbook_bond_reference for each bond.

Extract: security type, sector, ratings, coupon type, call features, issuer, country.

Build composition breakdowns: by sector, rating, maturity bucket, currency.

4. Project Cashflows

Call yieldbook_cashflow for each bond.

Aggregate into quarterly cashflow waterfall. Flag periods with concentrated maturities.

5. Run Scenario Analysis

Call yieldbook_scenario with rate shifts: -200bp, -100bp, -50bp, 0bp, +50bp, +100bp, +200bp.

Identify which bonds contribute most to upside and downside risk.

6. Curve Context

Call interest_rate_curve for the portfolio's primary currency.

Compute spread to curve for each bond. Assess curve environment.

7. Synthesize the Report

Present: portfolio summary metrics, composition breakdowns, cashflow waterfall, scenario P&L table with risk contributors, and curve exposure.

Output Format

Lead with the portfolio summary metrics, then detail composition, cashflows, and risk analysis in sections.

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.