The Agent Skills Directory

[PROMPT_INJECTION]: The skill generates documentation by analyzing source code and files, which creates an indirect prompt injection surface. • Ingestion points: The skill reads source files, docstrings, and OpenAPI specifications to identify documentation needs (SKILL.md). • Boundary markers: The instructions lack explicit delimiters or warnings for the agent to ignore instructions that might be embedded within the code being analyzed. • Capability inventory: The skill utilizes python -m doctest, pytest, tsc, and npx to execute and validate code examples found in documentation (SKILL.md). • Sanitization: Content from analyzed files is not explicitly sanitized before being processed in the documentation workflow.
[COMMAND_EXECUTION]: The skill core workflow includes executing validation tools such as pytest, doctest, tsc, and npx @redocly/cli to verify documentation quality.
[EXTERNAL_DOWNLOADS]: Reference files provide instructions and commands for installing documentation-related tools and libraries from established registries like NPM and PyPI.

code-documenter