skills.rest
xingwudao
xingwudaoCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

audit-strategy-spec

Audit strategy_spec.yaml field provenance and component catalog alignment before backtest execution.

116|38|Updated Feb 26, 2026
Search Tags:#assumption-checking#component-catalog#reproducible-research#quant-research#strategy-audit#backtest-validation#spec-provenance
One-click install
npx skills add https://github.com/xingwudao/open-xquant --skill audit-strategy-spec
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: audit-strategy-spec
Source: https://github.com/xingwudao/open-xquant/tree/main/agent/skills/audit-strategy-spec
Command: npx skills add https://github.com/xingwudao/open-xquant --skill audit-strategy-spec

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

When building quantitative trading strategies via AI agents, unvetted, unconfirmed assumptions in strategy_spec.yaml can lead to invalid, non-reproducible backtest results that waste research compute and produce false positive strategy performance claims.

Core Features & Use Cases

  • Field Provenance Classification: Traces conversation history to classify all material spec fields as confirmed, default, unconfirmed, or agent-added, ensuring no unapproved assumptions slip through.
  • Component Catalog Validation: Audits all strategy components against the registered component catalog to catch non-canonical decompositions, unregistered custom components, or deviations from standard recipes.
  • Backtest Gating: Blocks formal backtest execution until all unconfirmed, default, or agent-added fields are explicitly confirmed by the user, preventing wasted compute on invalid strategy specs. Use Case: A quant researcher using an AI agent to build a momentum strategy can use this skill to verify that all indicator parameters, execution assumptions, and component choices are explicitly approved before running a backtest, avoiding false performance results from unvetted assumptions.

Quick Start

Use the audit-strategy-spec skill to review your strategy_spec.yaml and raw conversation history to identify any unconfirmed assumptions or component provenance issues before running a backtest.

Frequently Asked Questions about audit-strategy-spec

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I validate strategy spec assumptions before running a backtest?▼

Validating strategy spec assumptions before backtesting requires auditing field provenance to classify spec fields as confirmed, default, unconfirmed, or agent-added. This process blocks formal backtest execution until all material fields are explicitly confirmed by the user, preventing wasted compute on invalid specs.

What is strategy spec field provenance in quantitative research?▼

Strategy spec field provenance in quantitative research traces conversation history to classify all material spec fields as confirmed, default, unconfirmed, or agent-added. This classification ensures no unapproved assumptions slip through into formal backtesting experiments, maintaining reproducible research integrity.

How do I check my strategy components against the registered component catalog?▼

Checking strategy components against the registered component catalog involves auditing all strategy components to catch non-canonical decompositions, unregistered custom components, or deviations from standard recipes. This validation enforces component provenance checks to ensure alignment before backtest execution.

Does audit-strategy-spec block backtests with unapproved assumptions?▼

Audit-strategy-spec blocks formal backtest execution until all unconfirmed, default, or agent-added fields are explicitly confirmed by the user. This backtest gating mechanism prevents wasted compute on invalid strategy specs generated from AI agent-driven quantitative research workflows.

Why do my backtest results show false performance from unvetted assumptions?▼

Backtest results show false performance from unvetted assumptions because unconfirmed parameters in strategy_spec.yaml files lead to invalid, non-reproducible outcomes. Auditing strategy specification field provenance prevents these unapproved assumptions from entering formal backtesting experiments.

Related Skills

Explore More Finance & Accounting Skills→
pax-kpax-k
6

claude-history-ingest

Ingest Claude conversation history into Obsidian wiki pages with frontmatter and provenance.

Community
Intermediate
adennngadennng
33

attempt-evaluation

Automate SignalAgent strategy evaluation with parameter search and backtesting.

Community
Intermediate
xingwudaoxingwudao
116

build-strategy-spec

Convert strategy ideas into validated strategy_spec.yaml files using canonical recipes.

Community
Advanced
xingwudaoxingwudao
116

audit-runtime-semantics

Audit compiled quant strategy runtime plans against original specifications.

Community
Advanced