Deep, findings-first review of one nrwl/nx pull request from a PR reference or associated Linear task, including drafts. Uses four fixed Sol/xhigh lanes, exact merge-base scope, inert snapshots, optional sandboxed checks, and produces one private record holding a postable review draft, without posting it.
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 workflow reads PR bodies, commits, issues, and issue comments from GitHub via `reviewctl.mjs begin`, which allow outsider submission into sources monitored by the agent.
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.