Review changes for correctness, security, accessibility, and performance. Use for scoped quality reviews or verification plans; bug fixes use oma-debug.
73%
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
Fix and improve this skill with Tessl
tessl review fix ./skills/oma-qa/SKILL.mdThe 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 collects a "PR" as review input (SKILL.md Expected inputs), and a GitHub PR can carry outsider-authored description and comment text, which the agent would read when collecting scope. The skill does not name a specific GitHub URL, so the source URL is null.
first-fluke/oh-my-agent
2bd468c
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.