Light review existing diffs
Skill emaraschio/cursor-commands/plugin/.cursor/skill-contracts/light-review-existing-diffs
Quick review of existing diffs without full PR contextFrom its SKILL.md
npx -y skills add emaraschio/cursor-commands --skill light-review-existing-diffsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 9 stars9 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.4 KB, 274 tokens by cl100k_base, as published. Nobody here has run it
Overview
Perform a quick quality pass on current diffs to surface risky areas, ensure polish, and flag follow-up actions for deeper review.
Steps
- Scan recent changes
- List open branches or pending commits requiring review
- Skim side-by-side diffs focusing on new or modified files
- Note files or modules with large or complex edits
- Assess quality signals
- Watch for TODOs, debug code, or commented blocks needing cleanup
- Verify naming, formatting, and imports follow project standards
- Check that tests or documentation were updated when behavior changed
- Flag next actions
- Mark sections that warrant full review or pair programming
- Capture questions or uncertainties to raise with the author
- Document any quick fixes you can apply immediately
Review Checklist
- High-risk files identified
- Debugging artifacts removed or flagged
- Style and conventions validated
- Tests/docs updates confirmed or requested
- Follow-up items recorded for deeper review
Guardrails
- Raise nitpicks as optional and non-blocking; keep the pass fast.
- Flag security issues even in a light review, no matter how quick the pass.
- Do not commit, push, merge, or run production scripts without consent.
What ships with it: 3 files
2.7 KB alongside SKILL.md
eval/
- cases.md2.1 KB
- fixtures.yaml336 B
- README.md325 B
Gives 0 of the 12 instructions most review quality skills give in 274 tokens
Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-07
- Ask questions one at a timein 81 of 1048, across 64 files
- Provide a recommended answer for each questionin 73 of 1048, across 50 files
- Explore the codebase instead of asking answerable questionsin 66 of 1048, across 42 files
- Resolve dependencies between decisions one-by-onein 42 of 1048, across 17 files
- Interview the user relentlessly about the planin 38 of 1048, across 13 files
- Order findings by severityin 31 of 1048
- Resolve each branch of the decision treein 27 of 1048, across 5 files
- Run a grilling sessionin 26 of 1048, across 5 files
- Update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 11 files
- Propose precise canonical terms for vague languagein 25 of 1048, across 7 files
- Create documentation files lazilyin 24 of 1048, across 5 files
- Assign severity to every findingin 24 of 1048
Said here and by no other author read
- list branches or commits requiring review
- skim side-by-side diffs
- note large or complex edits
- watch for leftover debug code or TODOs
- verify naming, formatting, and imports
- mark sections warranting full review
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.