The Agent Skills Directory

[SAFE]: The skill is designed to structure agent reasoning and improve project clarity through predefined discovery techniques. It emphasizes minimal resource usage and user consent.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided artifacts, such as existing codebases or research files, to identify project unknowns.
Ingestion points: Inspects local files, repositories, and prior artifacts (SKILL.md).
Boundary markers: The instructions do not define specific delimiters for ingested content, though it uses structured templates for output.
Capability inventory: Limited to writing documentation files (.plans/, PROJECT.md, decision-log.md) and calling specific vendor tools (gigio-write-plan, gigio-project-setup).
Sanitization: No specific sanitization or escaping of external content is mentioned.
[COMMAND_EXECUTION]: The instructions direct the agent to utilize specific planning tools, such as gigio-write-plan and gigio-project-setup, which are authorized vendor utilities for project organization. These references do not include arbitrary or user-controlled command execution.

find-unknowns