ai-regression-testing

Choose staged contract tests that catch partial AI-generated fixes across models, data, risk, execution ownership, and CLI/Windows parity.

Opciones de instalación

De forma predeterminada está seleccionado el prompt que primero revisa el origen. Puedes cambiar a un comando directo o descargar una copia local.

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Un comando directo omite el prompt de revisión. Revisa el origen antes de ejecutarlo.

npx skills add https://github.com/strmt7/simple_ai_trading --skill ai-regression-testing

El comando permanece en una sola línea. Desplázate horizontalmente para revisarlo antes de copiarlo.

¿Prefieres una copia local? Descarga los archivos que SkillsMP tiene disponibles ahora.

Lee SKILL.md y los archivos complementarios que muestra SkillsMP antes de decidir si quieres instalarlo.

Explorador de archivos

2 archivos

SKILL.md

Instrucciones de origen · Vista previa de solo lectura

Use the pinned external CocoIndex Code MCP workflow for broad repository routing, then prove exact candidates with rg and direct file reads.

Bound repository context reads and semantic-search output without weakening source, test, or evidence verification.

Containerization rules for this repo — pinned base image, non-root user, read-only FS, explicit volumes for config and data.

name	ai-regression-testing
description	Choose staged contract tests that catch partial AI-generated fixes across models, data, risk, execution ownership, and CLI/Windows parity.
metadata	{"origin":"adapted from ZMB-UZH/omero-docker-extended at 246110b1045cfd4ca318b4e870b5a38d213399b6; ECC v2.0.0 reviewed"}

Use this skill when an agent changes behavior that can look correct on one path while breaking a paired path or safety boundary.

Reproduce the exact defect or violated contract with the smallest test.
Exercise both success and failure branches, including timeout, malformed input, partial exchange response, interruption, and restart when relevant.
Run paired boundaries touched by the change: CLI/Windows, spot/futures, long/short, CPU/accelerator, fresh/reconnect, model/AI-disabled, train/reload, and simulated/live-testnet.
Validate artifacts and hashes separately from in-memory results.
Run the complete suite only at a promotion, integration, or release boundary unless the blast radius requires it earlier.

No network access in unit tests.
No order may bypass ownership, reconciliation, rate-limit, liquidity, loss, or stale-data gates.
Generated CLI/Windows parity must fail when a command, option, choice, or control mapping drifts.
Financial tests must reject non-finite values, leakage, impossible accounting, missing provenance, and fabricated or hand-edited evidence.
A passing smoke test never substitutes for model validation or risk evidence.