What does this skill do, and when should you use it?
This skill supports rates strategy analysis using LSEG MCP tools to price interest-rate swaps across multiple tenors. It overlays swap rates with government yields to calculate swap spreads and uses inflation breakevens to decompose nominal rates into real rates. It calculates 2s10s, 5s30s, and 2s5s10s butterfly metrics, then produces curve-trade recommendations with DV01-neutral sizing, carry, roll-down, targets, and stop-loss levels. It is suited to structured fixed-income research, with outputs requiring professional review.
It first lists swap templates for a target currency through ir_swap, then prices standard tenors such as 2Y, 5Y, 7Y, 10Y, 20Y, and 30Y to obtain par swap rates and DV01. It uses interest_rate_curve to retrieve government yields and calculate swap spreads, and inflation_curve to retrieve inflation breakevens and calculate real rates. Historical and macro context can be added with tscc_historical_pricing_summaries and qa_macroeconomic. The final output contains a swap-curve table, curve metrics, real-rate decomposition, and structured curve-trade recommendations.
- A rates strategist needs to compare swap rates across tenors and classify the curve shape.
- A fixed-income trader needs swap spreads versus government yields for relative-value analysis.
- A macro researcher needs to decompose nominal swap rates into inflation breakevens and real rates.
- A rates desk is evaluating 2s10s, 5s30s, or butterfly trade structures.
- A cross-market analyst is comparing swap curves across currencies.
How do you install this skill?
- The skill generates trade recommendations without requiring explicit risk limits, suitability review, user confirmation, or compliance review; outputs must not be treated as executable trading instructions.
- The LSEG MCP may require a subscription/API credentials and depends on an overseas service; verify institutional authorization, mainland-China reachability, data timestamps, and missing-data handling first.
- No safe degradation path is defined for tool failures, partial results, currency/index mismatches, or failed DV01, carry, and roll-down calculations.
- Network access
- MCP Server
LSEG MCP tools
In Cowork, open Settings → Plugins → Add plugin, paste https://github.com/anthropics/financial-services, and select the relevant content from the marketplace list. Alternatively, upload a zip of plugins/partner-built/lseg/. The source does not provide a standalone installation command for this individual skill.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/anthropics/financial-services.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/plugins/partner-built/lseg/skills/swap-curve-strategy" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- Analyze the USD swap curve across 2Y, 5Y, 10Y, and 30Y; calculate swap spreads, real rates, curve metrics, and propose DV01-neutral trades.
After installation and configuration of an available LSEG MCP connection, use a prompt such as: “Analyze the USD swap curve across 2Y, 5Y, 10Y, and 30Y; calculate swap spreads, real rates, curve metrics, and propose DV01-neutral trades.” MCP access may require a provider subscription or API key.
What are this skill's strengths and limitations?
- Covers swap pricing, government curves, inflation curves, historical data, and macro context in one workflow.
- Explicitly defines calculations for curve slopes, butterflies, swap spreads, and real rates.
- The trade output includes DV01-neutral sizing, carry, roll-down, targets, and stop-loss parameters.
- Supports comparison of swap rates across currencies.
- Requires access to LSEG MCP tools and any associated data entitlements.
- The source provides no test suite, sample output, or detailed data-quality documentation.
- It specifies an analysis and recommendation format but cannot establish suitability for a particular portfolio or market.
- The README states that the repository does not provide investment advice and that outputs require qualified professional review.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Swap Curve Strategy Analyst this page ✓ Anthropic · Official | 42 · Not recommended | ★ 40k | 1mo ago | Apache-2.0 |
| Macro & Rates Monitor ✓ Anthropic · Official | 45 · Not recommended | ★ 40k | 1mo ago | Apache-2.0 |
| FX Carry Trade Analyst ✓ Anthropic · Official | 40 · Not recommended | ★ 40k | 1mo ago | Apache-2.0 |
| Bond Futures Basis Analyzer ✓ Anthropic · Official | 46 · Use with care | ★ 40k | 1mo ago | Apache-2.0 |
| Bond Relative Value Analyst ✓ Anthropic · Official | 41 · Not recommended | ★ 40k | 1mo ago | Apache-2.0 |
How did FollowSkills review this skill?
The skill requests market-data and pricing-tool calls and produces analysis; it contains no write, transaction-execution, or credential-theft behavior. The README requires human review and says outputs do not execute trades. However, least-privilege boundaries, sensitive-data flows, user confirmation, provider retention, failure recovery, and rollback are unspecified, so points are deducted.
The two-phase tool workflow is broadly coherent and includes structured output templates. It does not specify tool schemas, authentication or availability prerequisites, missing-data behavior, abnormal-input handling, or diagnosable error feedback; static evidence does not justify a higher score.
The audience and scenarios cover swap-curve, swap-spread, real-rate, and curve-trade analysis, with reasonably clear outputs. Currency/index coverage, non-fit boundaries, fallback behavior, and semantic trigger exclusions are missing, as is Chinese-language support. Core functionality depends on an LSEG MCP service that may require subscription and may be difficult to reach from mainland China, so points are deducted.
The name, description, workflow, and output templates are readable; repository context provides an Apache-2.0 license, pinned revision, and basic CI validation. The skill lacks specific installation and dependency notes, parameter conventions, examples, FAQs, known limitations, changelog/versioning, and explicit maintenance ownership, so points are deducted.
The workflow covers curve construction, government-curve overlays, inflation decomposition, curve metrics, and trade recommendations, with tables that could be directly used as an analyst draft. Correctness of data mapping, DV01-neutral sizing, carry/roll-down, and breakeven calculations is not demonstrated, and static review cannot verify representative outputs; the score therefore remains at the static ceiling.
The pinned revision, Apache license, and repository CI for plugin validation and secret scanning provide limited auditability. There is no skill-specific test suite, sample execution evidence, third-party corroboration, or independent reproduction, so only limited credit is justified.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →