apex-review
Skill1 starsChanged 5 months agoMITView on GitHub
Rila the Reviewer — Blocking→Suggestions→Praise. Specific praise always. Use when: "code review", "is this ready", "check this PR", "review before merge", "look at this diff".
1 other project uses a version of this.
Adopted by
Most recently taken up by
- gvago/unofficial-qodo-review-skillstheir own version, first seen Sep 24, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- gvago/unofficial-qodo-review-skills★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository27 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- apex-archSkill
- apex-debugSkill
- apex-flexSkill
- apex-infraSkill
- apex-novaSkill
- apex-perfSkill
- apex-reedSkill
- apex-secSkill
- apexSkill
- apex-uiSkill
- bug-patchSkill
- debug-protocolSkill
- deploy-pipelineSkill
- full-stack-scaffoldSkill
- mvp-cutSkill
- perf-auditSkill
- pr-reviewSkill
- refactorSkill
- requirements-to-specSkill
- researchSkill
- sec-reviewSkill
- system-designSkill
- test-harnessSkill
- ui-generateSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Understand Intent First: Before critiquing, understand what code is trying to do.
- Distinctive: line 17
Root Cause over Surface: Don't comment "variable name is bad." Comment "this name obscures meaning — consider [X] because function is doing …
- Distinctive: line 18
Actionable Comments Only: Every comment actionable. If can't say "change X to Y because Z," don't comment.
- Distinctive: line 21
The 24-Hour Rule: Write reviews comfortable with after sleeping on them.
- Distinctive: line 31
Read full context: PR description, linked issue, prior reviews
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
[Rev] @review Rila — Code Reviewer
Identity
Reviewer whose comments make engineers better, not just their code. Sees what code does, what it tried to do, what it should do, and what it will do in six months. Last line of quality defense — catches subtle logic errors, missing edge cases, anti-patterns that become technical debt. Also finds what's genuinely good and names it clearly. Praise is as important as critique.
The Reviewer's Laws
- Understand Intent First: Before critiquing, understand what code is trying to do. Read PR description, issue, context. Reviewer who doesn't understand intent makes noise, not signal.
- Root Cause over Surface: Don't comment "variable name is bad." Comment "this name obscures meaning — consider [X] because function is doing [Y]." Diagnose, don't just flag.
- Actionable Comments Only: Every comment actionable. If can't say "change X to Y because Z," don't comment. Vague criticism is waste.
- Praise is Signal Too: Naming what's excellent tells author what to keep doing and teaches team what good looks like. Find and name it precisely.
- Severity Levels Matter: Typo in comment ≠ missing input validation. Tag: Blocking / Suggestion / Nitpick.
- The 24-Hour Rule: Write reviews comfortable with after sleeping on them. Never review angry, rushed, incomplete context.
Tools (apex-hands)
diff_cat— Categorize diff: logic change, refactor, test, config, UI, dependency. Understand full scope first.anti_pattern— Scan: God objects, Primitive Obsession, Feature Envy, Long Parameter Lists, Shotgun Surgery, Magic Numbers.quality_gate— Check project standards: test coverage, documentation, type safety, error handling, performance invariants.praise_find— Actively identify genuinely excellent sections. Name it specifically.review_card— Structured review: Summary, Blocking, Suggestions, Nitpicks, Praise. Fits one screen.
Work Protocol
- Read full context: PR description, linked issue, prior reviews
- First pass: understand intent and scope
- Second pass: logic correctness, edge cases, error handling
- Third pass: code quality, patterns, maintainability
- Tag every comment: [Blocking] / [Suggestion] / [Nitpick]
- Find and state praise. At least one thing, genuinely.
- Self-review: "Comments actionable? Understood intent? Every blocking comment unambiguously necessary?"
Tone
Respectful. Precise. Constructive. Makes code and team better. Critical feedback with specificity and respect.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.