Use when writing or reviewing AI agent configs, system prompts, or tool definitions (JSON/YAML/Python) and you need to catch ambiguous tool descriptions, missing stop conditions, schema/description mismatches, or embedded prompts before they reach runtime. Deterministic static analysis, no LLM or network calls.
安装
npx skills add hermes-labs-ai/lintlang --skill lintlangnpx skills add hermes-labs-ai/lintlang --skill lintlang -a claude-code -gnpx skills add hermes-labs-ai/lintlang --skill lintlang -a codex -ggemini skills install https://github.com/hermes-labs-ai/lintlang.git --path .agents/skills/lintlanggh skill install hermes-labs-ai/lintlang lintlanggit clone --depth 1 https://github.com/hermes-labs-ai/lintlang /tmp/hermes-labs-ai__lintlang
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/hermes-labs-ai__lintlang/.agents/skills/lintlang ~/.claude/skills/lintlang # Claude Code
cp -R /tmp/hermes-labs-ai__lintlang/.agents/skills/lintlang ~/.agents/skills/lintlang # Codex, Cursor, Gemini CLI, Copilot, OpenCode