Runs two parallel agents — one performs a rigorous PR review (via the review-pr skill), the other evaluates findings against the project's design context (ADRs, sprint goals) — then synthesizes a decision-ready report with Apply / Skip / Discuss verdicts per finding. Copied from zora-pantheon `.claude/commands/review-and-evaluate.md` and adapted to this repo's skill structure.
81%
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 runs `git log` on the branch and has the reviewer read the branch's changed files and the `review-pr` skill, which covers GitHub PR content, so an outside contributor's commit messages and PR-branch code reach the LLM without the agent selecting a specific item.
agranado2k/ai-report-platform
caeb0da
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.