Verify the project's riskiest invariant with TLA+, Lean, or Kani — chosen by property shape — and leave a project-local skill the next agent reruns; assumptions are part of the deliverable. For properties tests cannot reach.
82%
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 workflow's only possible outsider-text path is step 1's optional "infer from recent incidents," which names no service and is not a monitored feed, so the agent would have to actively search for incident text, which is low risk.
Yeachan-Heo/oh-my-claudecode
dec7e41
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.