The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes local Python scripts (validate-yaml.py and search-yaml.py) to validate documentation manifests and search for specific document statuses. These scripts are referenced as part of the environment's internal toolset for the CodeStable ecosystem.
[DATA_EXPOSURE]: The skill accesses project source code, existing documentation in the docs/ directory, and internal configuration files like .codestable/attention.md. These actions are necessary for its primary function of generating documentation based on the current state of the repository.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests untrusted data from source code comments and existing documentation. However, it mitigates this by using structured YAML frontmatter and specific Markdown templates, and by providing a workflow that requires human checkpoints for reviewing drafts before publication.
[REMOTE_CODE_EXECUTION]: No remote code execution or unauthorized external downloads were detected. All scripts executed are local to the development environment.

cs-docs