The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation and philosophical guidelines for software design. It does not include any scripts, executable code, or tool definitions. The instructions focus on improving agent reasoning during code reviews and refactoring tasks.
[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the agent must read local reference files ('mindsets') to calibrate its behavior. This represents a controlled use of local context to influence agent reasoning without exposure to untrusted external data.
Ingestion points: The references/ directory containing design philosophy documents.
Boundary markers: The agent is instructed to read these as grounding for its 'mindset' before proceeding with analysis.
Capability inventory: No system-level tools or network capabilities are requested or used by the skill.
Sanitization: The content consists of static markdown files authored as part of the skill package.

reducing-entropy