菜单
Use when AI-generated or AI-modified changes need a Code Health gate before commit, handoff, or pull request.
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
Use when installing the CodeScene MCP Server binary or package, registering it in an AI assistant, or copying agent guidance files into a repository.
Write an end-to-end integration test for the CodeScene MCP Server, covering file structure, backend abstraction, MCPClient usage, test registration, and verification.
Run the end-to-end integration test suite for the CodeScene MCP Server. Use when you need to verify that all MCP tools work correctly against the real CLI and server infrastructure.
Update the embedded CodeScene CLI to a new version, including downloading new binaries, computing SHA-256 checksums, and updating all pinned hashes in cli-checksums.sha256 and Dockerfile.
Use when the user wants to view, set, or troubleshoot CodeScene MCP configuration such as access tokens, on-prem URLs, default projects, or SSL certificates.
Scaffold a new MCP tool for the CodeScene MCP Server following the project's established patterns for directory structure, dependency injection, decorators, testing, and registration.
| name | safeguarding-ai-generated-code |
| description | Use when AI-generated or AI-modified changes need a Code Health gate before commit, handoff, or pull request. |
Use Code Health safeguards before declaring AI-touched code ready. The goal is to catch maintainability regressions early and prevent agents from normalizing technical debt.
Do not use this skill for broad refactoring discovery or project-level prioritization.
code_health_review: Review each AI-modified file immediately after the change.pre_commit_code_health_safeguard: Check staged or modified files before commit.analyze_change_set: Check a branch or PR-style change set against a base ref.code_health_review on that file.pre_commit_code_health_safeguard before commit-oriented recommendations as a broader gate across staged or modified files.analyze_change_set before PR-oriented recommendations as a final branch-level gate.code_health_review and keep iterating until the issue is removed or the user explicitly accepts the risk.