The Agent Skills Directory

[SAFE]: The skill is a documentation-only resource consisting of a SKILL.md file and a GLOSSARY.md file. It describes principles like predictability, information hierarchy, and information pruning.\n- [SAFE]: The disable-model-invocation: true flag in the frontmatter correctly scopes the skill as a user-invoked documentation piece, preventing the agent from triggering it autonomously.\n- [SAFE]: All links and references are internal (local .md files). There are no external URLs, remote scripts, or package dependencies found in the content.\n- [SAFE]: No sensitive data access, exfiltration patterns, or obfuscation techniques were detected. The skill focuses entirely on natural language instructions for skill development best practices.

writing-great-skills