Reviews unit/integration/E2E coverage, checks for fragile/flaky tests, asserts clinical safety checks, and reviews verification sequence. Use during test addition or refactoring.
83%
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 reviews PRs and posts a `Review record` comment on the PR, so the agent ingests GitHub PR content (descriptions, comments, and diffs from external contributors) without first selecting a specific outsider-authored item.
BigSimmo/PsychSift
fada614
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.