The Agent Skills Directory

[SAFE]: The skill is purely instructional and defines a workflow for documentation management. It does not invoke shell commands, perform network requests, or utilize external code execution patterns.
[INDIRECT_PROMPT_INJECTION]: The skill processes natural language requirements and architectural documentation from multiple external files, creating a surface for potential indirect prompt injection.
Ingestion points: The agent is instructed to read CLAUDE.md and README.md files from multiple child repository directories.
Boundary markers: The instructions do not define specific delimiters or security headers to separate untrusted file content from the agent's core instructions.
Capability inventory: The skill's capabilities are restricted to reading project files and writing markdown documentation to the specs/ and contracts/ folders.
Sanitization: The skill does not implement content validation or sanitization for the data retrieved from the documentation files.

descomponer-multirepo