菜单
run a comprehensive linting suite (MegaLinter style). Trigger when asked to check code quality, security, or style across multiple languages.
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 asked to create, improve, review, migrate, sync, or validate repository context files for coding agents, including AGENTS.md, CLAUDE.md, CODEX.md, GEMINI.md, .cursorrules, or .github/copilot-instructions.md. Trigger on close synonyms and paraphrases such as "agent instructions", "coding agent setup", "AI-friendly repo", or "Copilot/Codex/Claude instructions".
Use when asked to create, improve, review, migrate, sync, or validate repository context files for coding agents, including AGENTS.md, CLAUDE.md, CODEX.md, GEMINI.md, .cursorrules, or .github/copilot-instructions.md. Trigger on close synonyms and paraphrases such as "agent instructions", "coding agent setup", "AI-friendly repo", or "Copilot/Codex/Claude instructions".
Use when writing, revising, or reviewing TSDoc comments for TypeScript APIs, IntelliSense hover text, exported functions, classes, interfaces, type aliases, generic helpers, parameter docs, examples, deprecation notices, defaults, thrown errors, release tags, TypeDoc or API Extractor output, or documentation lint feedback.
Audit GitHub Actions workflow efficiency and recommend fixes to reduce CI minutes and costs.
Use when Neurotoxic test commands, CI test jobs, or runner-owned suites need diagnosis or optimization: slow/flaky/hanging/OOMing runs, runtime regressions, worker tuning, sharding, fixture duplication, suite topology, `pnpm run test`, `pnpm run test:all`, node:test, Vitest, Playwright, perf, or locale coverage.
Audit GitHub Actions workflow efficiency and recommend fixes to reduce CI minutes and costs.
| name | mega-lint-snapshot |
| description | run a comprehensive linting suite (MegaLinter style). Trigger when asked to check code quality, security, or style across multiple languages. |
Generate a detailed quality report for the repository, covering linting, security, and formatting.
Run the bundled script to generate the report.
.claude/skills/mega-lint-snapshot/scripts/run-mega-lint.sh
To apply fixes (where available):
.claude/skills/mega-lint-snapshot/scripts/run-mega-lint.sh --fix
Execute the Script
The script runs configured linters defined in .claude/skills/mega-lint-snapshot/assets/mega-lint.config.json.
Analyze the Report
Fix Issues
--fix works, commit the changes.Input: "Check the codebase for any linting errors."
Action:
Run .claude/skills/mega-lint-snapshot/scripts/run-mega-lint.sh.
Output:
[INFO] Starting MegaLinter Snapshot...
[INFO] Running ESLint... [PASS]
[ERROR] Running Gitleaks... [FAIL]
- hardcoded_secret in src/utils/api.ts:20
[INFO] Running Prettier... [PASS]
"Found a hardcoded secret in api.ts. Please remove it."
Skill sync: compatible with React 19.2.6 / Vite 8.0.10 / Tailwind 4.2.4 baseline as of 2026-05-20.