Design, write, and maintain skills and agent instructions. Use when the user asks to create, revise, evaluate, or troubleshoot skills or agent instructions, including investigating selection behavior to improve the guidance and deciding where guidance belongs.
91%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow reads repository-owned skill files, corpora, and recorded runs, but the "When importing guidance" step (SKILL.md [100-101]) can have the agent fetch and read third-party skill text that the user chooses, which is outsider-authored and selected by the user rather than pushed into a feed.
EpicenterHQ/epicenter
04f87cb
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.