What does this skill do, and when should you use it?
This skill evaluates foreign-exchange carry trade opportunities by weighing interest-rate carry against currency and volatility risk. It uses MCP tools to retrieve spot rates, forwards, yield curves, implied volatility surfaces, and historical pricing data. It calculates annualized carry and carry-to-vol ratios, then combines skew and historical context into a carry profile. It is intended for research and analyst work, not trade execution or investment advice.
It calls fx_spot_price for current spot quotes; fx_forward_price and fx_forward_curve for forward points, outright rates, and the full tenor structure; interest_rate_curve for the rate differential driving carry; fx_vol_surface for ATM volatility, risk reversals, and butterflies; and tscc_historical_pricing_summaries for historical ranges, trends, and realized-volatility context. It calculates annualized carry and carry-to-vol ratios by tenor, then produces a Carry Profile, Vol Surface Summary, and trade recommendations containing direction, tenor, carry, ratio, skew signal, risks, and conviction.
- An FX strategist compares forward curves across currency pairs to identify the strongest risk-adjusted carry tenor.
- A macro researcher tests whether a rate differential compensates for implied volatility and spot risk.
- A trading team reviews ATM volatility, risk reversals, and butterflies before considering a carry position.
- An investment researcher uses one year of historical spot data and the 52-week range to assess directional context.
- A risk team uses carry-to-vol ratios and rising-volatility signals to challenge proposed carry trades.
How do you install this skill?
- This is a static document review; no MCP call or calculation was executed, so the score is not evidence of tool availability or result correctness.
- LSEG data tools may require a subscription, API credentials, and reachable network access; mainland-China deployment should verify connectivity, compliance, and data licensing.
- “Entry recommendation” and “position sizing guidance” may be interpreted as investment advice; add risk limits, user confirmation, suitability review, and human sign-off.
- The skill should specify tool parameters and schemas, source timestamps, missing-data handling, formulas, failure messages, and historical-data and volatility conventions.
- MCP Server
LSEG MCP tools
In Cowork, open Settings → Plugins → Add plugin, paste https://github.com/anthropics/financial-services, and select the relevant plugin or vertical from the marketplace list. Alternatively, upload a zip of plugins/partner-built/lseg/. The README does not document 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 "$tmp/plugins/partner-built/lseg/skills/fx-carry-trade" ~/.claude/skills/
rm -rf "$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 EUR/USD 1M, 3M, 6M, and 1Y carry trades using spot, forward curves, rate differentials, volatility surfaces, and one year of historical pricing. Report carry-to-vol ratios, risk signals, and recommendations.
After installation and configuration of the available LSEG MCP tools, use a prompt such as: "Analyze EUR/USD 1M, 3M, 6M, and 1Y carry trades using spot, forward curves, rate differentials, volatility surfaces, and one year of historical pricing. Report carry-to-vol ratios, risk signals, and recommendations."
What are this skill's strengths and limitations?
- Covers spot, forwards, full forward curves, rate curves, volatility surfaces, and historical prices.
- Defines annualized carry and carry-to-vol as central comparison metrics.
- Includes risk reversals, butterflies, historical trends, and rising volatility in the synthesis.
- Specifies structured tables and recommendation fields for the output.
- It depends on MCP market-data tools, whose access may require a provider subscription or API key.
- The SKILL.md provides no test suite, data-quality checks, or explicit position-sizing formula.
- Outputs require professional review; the README says the repository is not investment advice and does not execute trades.
- The documented scope is FX carry analysis, not other asset classes or end-to-end execution.
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 |
|---|---|---|---|---|
| FX Carry Trade Analyst this page ✓ Anthropic · Official | 40 · Not recommended | ★ 40k | 1mo ago | Apache-2.0 |
| Swap Curve Strategy Analyst ✓ Anthropic · Official | 42 · Not recommended | ★ 40k | 1mo ago | Apache-2.0 |
| Bond Futures Basis Analyzer ✓ Anthropic · Official | 46 · Use with care | ★ 40k | 1mo ago | Apache-2.0 |
| Reconciliation Break Tracer ✓ Anthropic · Official | 53 · Use with care | ★ 40k | 1mo ago | Apache-2.0 |
| Month-End Variance Commentary ✓ Anthropic · Official | 42 · Not recommended | ★ 40k | 1mo ago | Apache-2.0 |
How did FollowSkills review this skill?
The skill describes reading FX market data and producing analysis, with no stated writes, trade execution, or other external side effects, so its apparent permission scope is limited. It does not require user confirmation, disclose data flows or sensitive-data handling, provide rollback, or specify source/timestamp attribution, and it does not clearly enforce human review for investment recommendations; points are deducted for these omissions.
The workflow and tool chain are broadly consistent, and the output fields are specified. However, there are no tool parameters, response schemas, availability assumptions, abnormal-input handling, or diagnosable failure messages, and key calculation conventions are incomplete. With no execution evidence in the static review, the score remains below the static ceiling of 10.
The target scenario, audience, and principal inputs are reasonably clear. Boundaries, exclusion triggers, input formats, and fallbacks for missing data are not defined; Chinese-language support is not addressed; and the core function depends on LSEG MCP services that may require overseas network access and a subscription, so points are deducted.
The document is readable and layered into principles, tools, workflow, and output templates. Repository context supplies an Apache-2.0 license, contribution process, and basic CI governance evidence. The skill itself lacks versioning, changelog, named maintenance responsibility, installation/dependency notes, examples, FAQs, and known-limitations disclosure, so points are deducted.
The tables and recommendation fields could serve as a usable analysis draft, and the workflow covers spot, forwards, volatility, and historical context. There are no tool-call examples, fully specified formula conventions, data-quality checks, or execution verification; substantial professional review remains necessary, and the static ceiling is 7.
The skill provides an auditable sequence and identifies the required data types, while repository CI includes plugin validation and secret scanning. There is no committed test suite covering this skill's key paths, third-party execution evidence, representative fixtures, or independent corroboration, so only limited static verifiability is supported.
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 →