The Agent Skills Directory

[SAFE]: The skill performs local repository analysis using standard command-line tools like git and wc to map directory structures and project history.
[SAFE]: It does not initiate network connections, download external resources, or execute remote code.
[SAFE]: The skill follows security best practices by explicitly delegating commit actions to the user rather than performing them automatically.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from repository files to generate documentation. This is an inherent part of the skill's discovery function.
Ingestion points: Processes README.md, Makefile, package.json, go.mod, pyproject.toml, and other repository configuration files (SKILL.md).
Boundary markers: None identified.
Capability inventory: Limited to read-only git operations and writing markdown files (AGENTS.md, CLAUDE.md).
Sanitization: None identified; output is formatted as markdown documentation.

repo-context