The Agent Skills Directory

[SAFE]: The skill is composed entirely of markdown instructions for the AI agent on how to structure documentation. It does not perform any file system operations, network requests, or command executions. No code or script files are included with the skill.
[INDIRECT_PROMPT_INJECTION]: The skill defines principles for processing and rewriting documentation (which may originate from untrusted sources). While this establishes an ingestion point for external data, the skill does not grant the agent any dangerous capabilities—such as shell execution, network exfiltration, or privileged file access—that could be abused by malicious instructions embedded in that data. The scope is strictly limited to stylistic and structural documentation choices.

write-docs