The Agent Skills Directory

[SAFE]: The skill content is limited to Markdown instructions. No executable code or suspicious patterns were found.
[NO_CODE]: This skill does not include any scripts or executable files.
[PROMPT_INJECTION]: The skill instructs the agent to follow implementation plans from external files, which constitutes a potential surface for indirect prompt injection. Ingestion points: Implementation plan files read in Step 1. Boundary markers: None provided in the instructions. Capability inventory: General agent tools used for task implementation as directed by the plan. Sanitization: None; the skill relies on the agent's critical review and human oversight to mitigate risks.

executing-plans