The Agent Skills Directory

[SAFE]: No malicious patterns, unauthorized network access, or hardcoded credentials were found in the skill files.
[NO_CODE]: The skill consists exclusively of Markdown-based instructions and reference materials. No executable scripts (Python, JavaScript, shell) or configuration files that could trigger autonomous execution are present.
[PROMPT_INJECTION]: The skill defines processes for reading and analyzing project source code and documentation, which constitutes an indirect prompt injection surface.
Ingestion points: The skill ingests untrusted source material as described in references/generate.md, references/index.md, references/teacher.md, and references/tutorials.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided within the documentation workflows.
Capability inventory: The agent has access to Write, Read, Grep, Glob, and Task (delegation) tools as coordinated in all reference files.
Sanitization: No sanitization of ingested content is performed before it is used for analysis or passed to subagents.

documentation-production