メニュー
Perform a deep test of the codebase, validating functional smoke tests, claim verification, drift checks, license headers, and placeholder checks. Trigger whenever the user asks to run deep tests, check code health, or perform strict verification.
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
| name | deep-test |
| description | Perform a deep test of the codebase, validating functional smoke tests, claim verification, drift checks, license headers, and placeholder checks. Trigger whenever the user asks to run deep tests, check code health, or perform strict verification. |
This skill performs a thorough and strict verification of the codebase to guarantee that changes are clean, functional, matches Conventions, contains proper license headers, and does not leak template placeholders.
Ensure you have the required runtimes and node dependencies installed:
npm install before running tests if dependencies are updated.Run the automated deep test script via npm:
npm run deep-test
The script automatically tests:
node test/run-tests.mjsnode install.mjs verify . --strictnode install.mjs drift . --strict --git (falls back to --strict without --git if git is not available)templates/.If any of the checks fail, print the failures verbatim and address them before declaring success.
ai/guide/MODULE_MAP.md) and labeled as [inferred].AGENTS.md and conventions in ai/guide/CONVENTIONS.md.Bootstrap the ai/ knowledge layer for a repo that has none — draft the MODULE_MAP, diagrams, and guide docs as [inferred] for a human to audit, touching no source code. Use when the maps are still placeholders or the user asks to cold-start, bootstrap, or onboard a repository.
Bootstrap the ai/ knowledge layer for a repo that has none — draft the MODULE_MAP, diagrams, and guide docs as [inferred] for a human to audit, touching no source code. Use when the maps are still placeholders or the user asks to cold-start, bootstrap, or onboard a repository.
Deep, judgement-based adversarial code audit — hunts for stale cross-references, unescaped interpolation, platform gaps, generated-file ownership conflicts, and cross-module consistency rot that no mechanical check can catch. Read-only; writes a dated findings report.
Kit-maintainer diagnostic (LOCAL-ONLY, not distributed) that audits the README and docs/ for staleness against the repo's real command/skill/CLI roster, stamped tree, and cross-doc consistency. Read-only; produces a severity-ranked findings report.
Run verification and drift checks on the AI knowledge-base to identify missing documentation or stale references.
Deep-mine the source code to discover implemented features; writes ai/analysis/FEATURE_CATALOG.md.