Skip to main content

pr-review

Multi-dimensional review of a PR or feature branch in the microsoft/WinAppVSCE repo. Activate when a contributor asks to "review my PR", "review my changes", "vet my branch before pushing", "do a full review", "PR review", "review this feature", or similar. Fans out parallel sub-agents covering security, correctness and tests, extension UX, alternative solutions, necessity and simplicity, shipping surfaces (docs/package.json contributions/VSIX packaging), and an independent different-model cross-check, then validates critical/high findings by building, packaging, and driving the extension the way a user would. Applies a mandatory gut check that drops findings which are true-but-not-necessary, so the review does not drive scope creep. Reports a compact, human-first decision and finding list to stdout. Does NOT apply fixes unless explicitly asked.

Source facts

Repository
microsoft/WinAppVSCE
Last source activity
October 9, 2026 at 22:05
Detected SKILL.md language
English
Stars
18
Forks
5

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer
9 files

Showing SKILL.md

SKILL.md
Source instructions · Read-only preview
namepr-review
descriptionMulti-dimensional review of a PR or feature branch in the microsoft/WinAppVSCE repo. Activate when a contributor asks to "review my PR", "review my changes", "vet my branch before pushing", "do a full review", "PR review", "review this feature", or similar. Fans out parallel sub-agents covering security, correctness and tests, extension UX, alternative solutions, necessity and simplicity, shipping surfaces (docs/package.json contributions/VSIX packaging), and an independent different-model cross-check, then validates critical/high findings by building, packaging, and driving the extension the way a user would. Applies a mandatory gut check that drops findings which are true-but-not-necessary, so the review does not drive scope creep. Reports a compact, human-first decision and finding list to stdout. Does NOT apply fixes unless explicitly asked.