The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration attempts were detected. The skill operates within the expected scope of a design and documentation tool.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from the project environment and user dialogue. 1. Ingestion points: Contextual analysis of project files, documentation, and git commits as described in SKILL.md. 2. Boundary markers: No specific delimiters or instructions to ignore embedded prompts are defined for the project file analysis. 3. Capability inventory: The skill performs file writes to the docs/plans/ directory and executes git commits. 4. Sanitization: No explicit sanitization or filtering of ingested external content is specified in the workflow.

brainstorming