examine
Review a code change rigorously — a PR, branch, commit range, or the working tree. Confirm the problem is real, sketch the obvious solutions before reading the diff, then audit it for correctness, completeness, architecture, conventions, security, privacy, testing, reversibility, and dependencies, judge whether it is right-sized, and verify every significant finding independently. Returns a six-signal report: done well, gaps, issues rated Critical to Low with a separate confidence verdict, questions, suggestions, known limitations. Use when the user says "/examine", "examine this PR", "review this PR", "review pr #N", "review my branch", "look over my pull request", "check my PR before merge", or asks for a deep code review. Holistic where the host's built-in review is defect-first.
97%
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
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
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.
Why it was flagged
The workflow examines GitHub pull requests, branches, and commits via the GitHub CLI (`gh pr view`, `gh pr diff`), ingesting PR descriptions, commit messages, and code changes authored by third parties.
- Repository
korya/swd-skills
- Revision
b1520b9
- Audited
- Security analysis
Is this your skill?
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.