メニュー
Research the existing implementation, tests, primary technical sources, and financial rationale before adding trading code or dependencies.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
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.
Choose staged contract tests that catch partial AI-generated fixes across models, data, risk, execution ownership, and CLI/Windows parity.
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.
Audit financial, data, model, and dependency claims for primary-source quality, dates, provenance, and reproducibility before implementation or publication.
| name | search-first |
| description | Research the existing implementation, tests, primary technical sources, and financial rationale before adding trading code or dependencies. |
| metadata | {"origin":"adapted from ZMB-UZH/omero-docker-extended at b27dbe990703d64d13e540c40cf4e122954c664d"} |
Use this skill before new model logic, exchange behavior, risk controls, dependencies, data pipelines, workflows, or broad refactors.
README.md, the nearest src/simple_ai_trading/ module, and its tests.rg for exact questions. Use cocoindex-code-search first only for
genuinely broad semantic routing.