菜单
Run only the E2E test suite (no full 705-test unit battery). Two modes — Docker-sandboxed (scripts/run-e2e.sh) or direct pytest (tests/e2e/).
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
Scaffold a new AI backend that implements AIBackend.analyze() — add file under src/aigate/backends/, register in BACKEND_MAP, wire unit tests. Use when adding support for a new AI model / provider.
Cut a new PyPI release — bump version in pyproject.toml, run scripts/publish.sh, tag, and hand off the final `uv publish` step to the user.
Check any package for supply chain attacks before installing. Use when: pip install, npm install, yarn add, pnpm add, cargo add, gem install, composer require, flutter pub add, go get, dotnet add package. Also use when someone suggests installing a package or dependency. ALWAYS run this before installing anything — no exceptions.
Scan a lockfile or requirements file for supply chain attacks. Use when: reviewing requirements.txt, package-lock.json, Cargo.lock, Gemfile.lock, composer.lock, pubspec.lock, go.sum, yarn.lock, pnpm-lock.yaml. Also use when auditing project dependencies or onboarding to a new codebase. ALWAYS run this when you see a lockfile or dependency manifest.
Analyze a package with aigate CLI (static pre-filter + optional AI analysis). Usage: /check-package <name> [version] [ecosystem]
Run lint, format check, and all tests to verify code quality before committing.
| name | e2e |
| description | Run only the E2E test suite (no full 705-test unit battery). Two modes — Docker-sandboxed (scripts/run-e2e.sh) or direct pytest (tests/e2e/). |
Use this when you want fast signal on E2E changes without running the full pytest tests/ suite.
cd "$CLAUDE_PROJECT_DIR"
./scripts/run-e2e.sh
Builds synthetic malicious packages, spins up docker compose, runs the suite inside a network-isolated container, and cleans up. Slower but matches CI.
cd "$CLAUDE_PROJECT_DIR"
.venv/bin/python -m pytest tests/e2e/ -v
No Docker, no network isolation — only use when iterating on a specific E2E test and you've already verified Mode 1 works.
Report: passed/failed counts, any failures with file:line, and total wall time. If Mode 1 fails but Mode 2 passes, that usually points at network isolation or fixture-build bugs — flag it explicitly.