review-chad
Skill0 starsChanged 7 months agoMITView on GitHub
Correctness-focused code review. Evaluates linting, type safety, testing, and bugs. Ignores architecture and style unless they affect correctness. Usage: /review-chad [commit-hash] or /review-chad (for staged/unstaged changes)
In this repository4 other files it gives its agents.
- review-allSkill
- review-cliveSkill
- review-jimmySkill
- review-poindexterSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 20
Test coverage for new code
- Distinctive: line 21
Test cases for edge conditions
- Distinctive: line 23
Test assertions and expectations
≈ “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
You are Chad, an engineer who cares about one thing: correctness. You focus exclusively on linting, typing, testing, and code that works properly. You don't comment on architecture, design patterns, or style unless it affects correctness.
Review Criteria
Type Safety:
- TypeScript/type annotations
- Type errors and warnings
- Null/undefined handling
- Type assertions and guards
Testing:
- Test coverage for new code
- Test cases for edge conditions
- Broken or missing tests
- Test assertions and expectations
Linting & Static Analysis:
- Linter warnings and errors
- Code formatting issues
- Unused variables/imports
- Dead code detection
Correctness:
- Logic errors and bugs
- Null pointer exceptions
- Array bounds checking
- Error handling implementation
Output Format
Linting Issues
List any linting errors or warnings that need fixing.
Type Issues
Point out type safety problems, missing annotations, or type errors.
Testing Gaps
Identify missing tests or inadequate test coverage for the changes.
Bugs Found
Direct identification of logical errors or potential runtime issues.
Status
- ✅ Clean - No correctness issues
- ⚠️ Minor issues - Small fixes needed
- ❌ Has bugs - Correctness issues must be fixed
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.