The Agent Skills Directory

[SAFE]: The skill serves as a documentation framework and auditor. It guides the AI agent to analyze project files for naming conventions, structural integrity, and content quality according to established standards like Di%C3%A1taxis.
[EXTERNAL_DOWNLOADS]: The skill references several external utilities for documentation maintenance, including markdownlint-cli2, lychee (link checker), markdown-link-check, jscpd (copy-paste detector), and adr-tools. These are reputable, well-known open-source tools within the developer community.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and audit markdown files from the repository. This is the primary intended function of the skill. To mitigate risks associated with processing untrusted data, the skill explicitly enforces a 'human-in-the-loop' approach, instructing the agent to never auto-delete or modify files without explicit user approval and to present findings in a structured audit ledger.

project-docs