Audit a named AI agent config, system prompt, tool-definition or instruction file (YAML, JSON, Markdown, text, or Python) with the released LintLang CLI, on request. Use when the user asks to audit, lint, scan or review such a file for ambiguous tool descriptions, missing stop conditions, schema/description mismatches, or prompts embedded in Python, and names the file.
安装
npx skills add hermes-labs-ai/lintlang --skill lintlang-auditnpx skills add hermes-labs-ai/lintlang --skill lintlang-audit -a claude-code -gnpx skills add hermes-labs-ai/lintlang --skill lintlang-audit -a codex -ggemini skills install https://github.com/hermes-labs-ai/lintlang.git --path integrations/claude-code/skills/lintlang-auditgh skill install hermes-labs-ai/lintlang lintlang-auditgit 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/integrations/claude-code/skills/lintlang-audit ~/.claude/skills/lintlang-audit # Claude Code
cp -R /tmp/hermes-labs-ai__lintlang/integrations/claude-code/skills/lintlang-audit ~/.agents/skills/lintlang-audit # Codex, Cursor, Gemini CLI, Copilot, OpenCode