Instructions file CodexOpenCode
Instructions for xingwudao/open-xquant, covering agents.md and naming policy.
Instructions file CodexOpenCode
Instructions for xingwudao/open-xquant, covering agents.md and naming policy.
Instructions file
Instructions for xingwudao/open-xquant, covering claude.md, project overview, project structure, bug fixing and cross-file sync.
Skill Claude CodeCodex
Use when open-xquant artifacts must be checked for version/run/final traceability before comparison, report review, migration, or final selection.
Skill Claude CodeCodex
Compile an open-xquant strategy spec preview and audit that material SPEC execution semantics are preserved in compiledplan.json before backtests.
Skill Claude CodeCodex
Audit strategyideabrief.json and the brainstorm conversation before strategyspec.yaml construction begins.
Skill Claude CodeCodex
Audit strategyspec.yaml field provenance before backtests.
Skill Claude CodeCodex
Author workspace-local open-xquant custom components from componentrequest.json, with tests, manifest hashing, catalog refresh, and no global SDK mutation.
Skill Claude CodeCodex
Guide a user through the open-xquant pre-spec strategy idea workflow and produce strategyideabrief.json before any strategyspec.yaml work begins.
Skill Claude CodeCodex
Use when report chart assets, figures, visual evidence, plotting scripts, or notebook-like assets are required for an open-xquant experiment report.
Skill Claude CodeCodex
Configure and reason about open-xquant trading rules, exits, risk holds, and rebalance limits; use when the user asks for stop loss, take profit, drawdown guards, holding limits, or rule components.
Skill Claude CodeCodex
Build open-xquant strategyspec.yaml files from audited strategy idea briefs for multi-Agent systems; stops after deterministic validation and writes a builder phase result for downstream orchestration.
Skill Claude CodeCodex
Define open-xquant strategy universes and explain survivorship/PIT constraints; use when users choose symbols, indexes, dynamic filters, or tradable pools.
Skill Claude CodeCodex
Compare two completed open-xquant experiment runs.
Skill Claude CodeCodex
Use when comparing open-xquant runs or strategy versions, especially when distinguishing within-version reproducibility from cross-version strategy evidence.
Skill Claude CodeCodex
Configure open-xquant execution timing, fees, slippage, lot size, fill price mode, and broker assumptions; use when users discuss trading costs or order execution.
Skill Claude CodeCodex
Route open-xquant component creation requests after checking the registry; use when users ask for a new Indicator, Signal, Rule, or PortfolioOptimizer.
Skill Claude CodeCodex
Create a new open-xquant Indicator with tests and registry wiring; use after create-component confirms no existing indicator satisfies the request.
Skill Claude CodeCodex
Create a new open-xquant PortfolioOptimizer with weight-invariant tests and registry wiring; use after create-component confirms no existing optimizer satisfies the allocation request.
Skill Claude CodeCodex
Create a new open-xquant Rule with portfolio-state tests and registry wiring; use after create-component confirms no existing rule satisfies the requested risk or exit behavior.
Skill Claude CodeCodex
Create a new open-xquant Signal with deterministic output-domain tests and registry wiring; use after create-component confirms no existing signal satisfies the request.
Skill Claude CodeCodex
Evaluate cross-sectional factors with IC, Rank IC, ICIR, decay, and turnover in open-xquant; use for stock selection and multi-asset ranking factors.
Skill Claude CodeCodex
Route open-xquant factor evaluation tasks to cross-sectional or time-series workflows; use when users ask whether a factor predicts returns.
Skill Claude CodeCodex
Evaluate time-series factors with hit rate, decay curve, profit/loss ratio, cash-period behavior, and tearsheets in open-xquant; use for timing or rotation signals.
Skill Claude CodeCodex
Inspect, download, and validate open-xquant market, macro, and financial data; use before backtests, factor studies, or any task that depends on local parquet data.