The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script using the command uv run --with pyyaml python scripts/slop_score.py. The content of this script is not included in the skill files, which prevents verification of its safety or behavior.
[EXTERNAL_DOWNLOADS]: The execution of the uv command involves downloading and installing the pyyaml package from the Python Package Index (PyPI). This is a well-known official registry, and the download is documented as a standard functional requirement.
[COMMAND_EXECUTION]: The skill utilizes shell utilities such as cat and grep to read configuration files (e.g., .scribe/style-profile.yaml) and perform vocabulary searches within documentation files.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and remediate existing documentation and code docstrings, which creates a potential surface for indirect prompt injection if the source material contains malicious instructions. * Ingestion points: Reads local Markdown files and code docstrings for remediation. * Boundary markers: Includes a human-in-the-loop confirmation step ("Proceed? [Y/n/edit]") and instructions to preserve original intent. * Capability inventory: Shell execution (uv, cat, grep) and file system read access. * Sanitization: There are no explicit instructions to sanitize or escape input text to prevent the model from following instructions embedded within the processed documentation.

doc-generator