The Agent Skills Directory

[SAFE]: The skill is strictly limited to text processing and markdown generation. It does not perform network communication, execute shell commands, or access sensitive system configuration files like credentials or SSH keys.
[PROMPT_INJECTION]: The skill identifies a potential indirect prompt injection surface by reading external repository files to generate context for documentation.
Ingestion points: The skill reads AGENTS.md, architecture-rules.md, and various markdown files within the docs/ directory.
Boundary markers: There are no explicit instructions or delimiters provided to differentiate between control instructions and data content within the ingested files.
Capability inventory: The agent is authorized to create and edit project documentation files (e.g., README.md, docs/*.md).
Sanitization: No sanitization or validation of the ingested file content is specified in the skill instructions.

code-docs-writer