The Agent Skills Directory

[SAFE]: The skill's primary function is to establish and validate a documentation structure (specs, decisions, conventions) within a project's repository. The provided guidelines and reference files are purely instructional and contain no malicious patterns.
[COMMAND_EXECUTION]: The skill includes Node.js validation scripts that perform read-only structural checks on local Markdown files. These scripts utilize standard Node.js modules (fs, path) to verify links and naming conventions. They do not perform network requests or execute arbitrary commands from untrusted sources.
[SAFE]: The skill defines a process for the agent to ingest and analyze local documentation. Ingestion points include the loadDocs function in docs.mjs which reads all Markdown files in the docs directory. While no explicit boundary markers or sanitization are applied to the file content itself in the provided code, the skill's logic is restricted to structural linting and does not grant the agent capabilities to execute content or access sensitive system data.

living-project-documentation