Skip to content

feat(rates-fx): add rate-scenario-analysis workflow - #7

Open
liyc-sys wants to merge 1 commit into
LLMQuant:masterfrom
liyc-sys:feat/rates-fx-rate-scenario-analysis
Open

feat(rates-fx): add rate-scenario-analysis workflow#7
liyc-sys wants to merge 1 commit into
LLMQuant:masterfrom
liyc-sys:feat/rates-fx-rate-scenario-analysis

Conversation

@liyc-sys

Copy link
Copy Markdown

Summary

Adds a rate-scenario-analysis workflow to llmquant-rates-fx. The existing workflows analyze the current curve (yield-curve-trade-lens) and cross-country policy paths (central-bank-divergence); this workflow covers the complementary task of building explicit rate scenarios — parallel shifts, steepeners/flatteners, policy or inflation repricing — anchored to historical shift magnitudes, tracing each scenario across tenors, and mapping the impact onto rate-sensitive exposures with duration evidence. It answers "what happens to my curve view and holdings if rates move like X", which no current workflow addresses.

Type of change

  • New category skill (skills/llmquant-<category>/)
  • New workflow (workflows/<name>.md)
  • Fix to an existing skill / workflow
  • Script or asset change
  • Docs / README only

Affected categories

llmquant-rates-fx

Contract checklist

  • Category folder is named llmquant-*.
  • Root SKILL.md exists and routes to the workflow.
  • Workflow file added or updated under workflows/.
  • input_data_source: LLMQuant Data is present in the router frontmatter.
  • Required data capabilities are described in natural language (not exact MCP tool names).
  • Missing or future data capabilities are explicitly named.
  • Freshness rules are explicit (dates, filing periods, observation dates, stale notices).
  • Fallback behavior is explicit for missing, unsupported, or stale data.
  • Guardrails prevent invented data and unsupported conclusions.
  • Output format is structured (Answer, Evidence, Risks/Caveats, Data Used).
  • README tables updated if a category or major workflow was added, removed, or renamed.

Evidence grounding

All external facts (yield curves and shift history, policy rates and market-implied paths, inflation and macro indicators, ETF/instrument duration and holdings, cross-asset context) route through LLMQuant Data. The workflow requires reporting curve observation dates, tenor sets, policy-path dates, and holdings dates, and falls back to scenario curve paths without instrument-level impact — with the missing exposure inputs named — when duration or holdings data is unavailable. Guardrails forbid presenting scenarios as forecasts, estimating instrument impact without duration data, and using magnitudes detached from historical shifts without a stress-case label.

Linked issues

None.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant