菜单
Choose staged contract tests that catch partial AI-generated fixes across models, data, risk, execution ownership, and CLI/Windows parity.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| 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 b27dbe990703d64d13e540c40cf4e122954c664d"} |
Use this skill when an agent changes behavior that can look correct on one path while breaking a paired path or safety boundary.
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.
Keep concise user docs and machine-readable model evidence synchronized with real behavior without losing provenance or caveats.
Apply four anti-error coding principles plus this repository's stricter financial-evidence, safety, and single-session rules.
Research the existing implementation, tests, primary technical sources, and financial rationale before adding trading code or dependencies.
Audit financial, data, model, and dependency claims for primary-source quality, dates, provenance, and reproducibility before implementation or publication.
