Llmquant Rates Fx Agent Skill
Router skill for LLMQuant rates and FX workflows. Use when the user needs yield curve, duration, central-bank divergence, FX carry, real-rate, dollar, or cross-currency analysis.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/LLMQuant/skills --skill llmquant-rates-fxThe instruction itself
4 sections, as written by the authorLLMQuant Rates FX
This category routes rates and foreign-exchange workflows for curve analysis, central-bank divergence, and FX carry.
Routing Rules
- Identify currencies, countries, curve points, instrument proxy, horizon, and decision type.
- Select the closest workflow below.
- Open only that workflow and any referenced local resources.
- Use LLMQuant Data for yield curves, policy rates, inflation, growth, FX prices, carry, volatility, credit, commodities, and macro context.
- Report observation dates, price timestamps, policy dates, curve tenors, stale notices, and missing inputs.
Workflow Index
| User intent | Workflow |
|---|---|
| Analyze yield curve shape, duration exposure, and curve trades. | workflows/yield-curve-trade-lens.md |
| Compare central-bank paths and macro divergence across countries. | workflows/central-bank-divergence.md |
| Build an FX carry, momentum, valuation, and risk dashboard. | workflows/fx-carry-dashboard.md |
LLMQuant Data Contract
Prefer LLMQuant Data when available. The workflows may need these data capabilities:
- Retrieve nominal and real yield curves, policy rates, inflation expectations, rate histories, and term-premium context.
- Retrieve FX spot history, carry, forward points, rate differentials, volatility, positioning, and trade-weighted dollar context.
- Retrieve central-bank meeting calendars, policy communication, macro indicators, commodities, credit, and risk sentiment.
- Retrieve portfolio duration, currency exposures, ETF look-through, and hedging instruments when available.
Fallback:
- If forward points, real rates, or positioning are unavailable, state the missing inputs and use spot/rate-differential evidence only.
- Do not infer live FX carry or curve trades without timestamped rate and FX data.
Other skills for the same job
different authors, same section of the catalogue
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
How to use it
Take llmquant/llmquant-rates-fx from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.