The Agent Skills Directory

[NO_CODE]: The skill consists entirely of markdown instructions and formatting templates for the AI agent to follow when documenting technical decisions. No scripts, binaries, or executable code are included.
[SAFE]: The instructions promote best practices for documentation, such as recording rationale and mandatory negative consequences for decisions. No security risks were identified in the instructions, metadata, or templates.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external inputs such as user conversations and chat history to generate documentation. While this is an ingestion point for untrusted data, the skill acts only as a formatting guide and includes no capabilities that would allow for malicious exploitation through this data.
Ingestion points: Chat history and conversation context (SKILL.md).
Boundary markers: Absent.
Capability inventory: Documentation drafting and formatting.
Sanitization: Absent.

recording-decisions