agentsclimarketplace

Strategy translate

Skill lucaswychan/quant-paper-agent/.agents/skills/strategy-translate

A Claude Code plugin that turns a quantitative-finance arxiv paper into a production-ready event-driven strategy

Install
npx -y skills add lucaswychan/quant-paper-agent --skill strategy-translate

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Translate a user-accepted quantitative replication into a framework-specific event-driven strategy and equivalence tests. Use only after a replication benchmark is complete and explicitly accepted, and when a schema-valid framework contract defines events, strategy callbacks, orders, fills, positions, contract metadata, risk limits, and clock semantics. Produces research or paper-trading code by default; live deployment requires separate operational review.

SKILL.md

3.1 KB, as published. Nobody here has run it

Strategy translate

Translate a validated research implementation; do not claim that generated code is production-ready or authorize live trading.

Preconditions

Require all of the following:

  • replications/<run-id>/outputs/benchmark.md exists.
  • The user has explicitly accepted that benchmark and selected a target framework.
  • A framework contract exists at frameworks/<framework-id>/spec.json.
  • scripts/check_spec.py frameworks/<framework-id>/spec.json passes.
  • The vectorized run and its data manifest are unchanged since acceptance.

If any condition fails, stop and report the missing contract or decision.

Read references/framework_spec.md before validating or authoring a framework specification.

Workflow

  1. Record the accepted benchmark hash and framework ID in strategy/review.json.
  2. Map the approved timing contract explicitly: observation, signal, decision, order submission, fill, position update, P&L recognition, and rebalance schedule.
  3. Translate stateful operations into framework state: rolling buffers, last prices, pending orders, fills, positions, capital, and contract metadata.
  4. Keep signal logic, portfolio intent, execution, sizing, and risk checks in separate units.
  5. Use size_contracts only as a conservative single-position conversion utility. Portfolio margin, existing exposure, reserved capital, limits, fees, and framework-specific risk remain separate mandatory checks.
  6. Generate under:
papers/<paper-id>/replications/<run-id>/strategy/<framework-id>/
├── strategy.py
├── sizing.py
├── review.json
└── tests/
    ├── test_equivalence.py
    ├── test_sizing.py
    └── test_event_ordering.py

Required validation

  • Replay a representative multi-day window through both vectorized and event-driven implementations.
  • Compare signals, target positions, filled positions, turnover, costs, daily P&L, and ending NAV within declared tolerances.
  • Test partial fills, rejected orders, duplicate/out-of-order bars, missing bars, session boundaries, contract rolls where applicable, and restart/state restoration.
  • Test portfolio-level limits and margin through the actual framework risk API.
  • Run in simulation or paper-trading mode before any operational handoff.

Rules

  • Do not translate from an unapproved or changed benchmark.
  • Do not infer missing framework APIs from examples.
  • Do not equate a one-day smoke test with behavioral equivalence.
  • Do not label code production-ready solely because unit tests pass.
  • Live deployment, credentials, exchange connectivity, and operational authorization are outside this skill.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.