The Agent Skills Directory

[SAFE]: The skill's primary function is the automated maintenance of documentation. It uses a Python script (scripts/maintain_skills_readme.py) to discover repositories and validate their README.md structure against a predefined schema.
[SAFE]: File access is restricted to reading and writing README.md files and reading project manifests (like package.json or Cargo.toml) for environment detection. This is consistent with its stated purpose.
[SAFE]: The skill includes explicit guardrails in SKILL.md that prevent it from editing source code, manifests, or performing git operations (commit/push), ensuring it remains focused on documentation.
[SAFE]: Although the script parses shell-like command strings (e.g., npx skills add) found within markdown files, it does so for syntax validation purposes only and does not execute these commands.
[SAFE]: All external references and URLs target trusted or well-known services (such as Vercel's GitHub repositories and official documentation sites).

maintain-skills-readme