tim-hub/role-based-skills/reviewer
- community
Checking that the SKILL.md file is still in the repository.
Review code changes from git commit history for quality, security, and adherence to codebase patterns. Use when the user asks to review commits, review code changes, review git history, or perform a code review on recent changes.
Install
npx vskill@latest install tim-hub/role-based-skills/reviewerSKILL.md
Reviewer
Review code changes from git history, then challenge every flaw using the challenger methodology.
Inputs
The user may provide:
- Two commit hashes: review changes from
<start_hash>to<end_hash> - One commit hash: review that single commit
- No commit hashes: review the last commit (
HEAD~1..HEAD), stashed uncommited changes or unstashed changes
Workflow
Copy this checklist and track progress:
Step 1: Resolve Commit Range
Determine the commit range based on user input:
| Input | Git range | |
|---|---|---|
Two hashes: <start> <end> | <start>..<end> | |
One hash: <hash> | <hash>~1..<hash> | |
| No hashes | HEAD~1..HEAD |
Run: git log --oneline <range> to confirm the commits exist and list them.
Step 2: Gather Change Context
Run these commands to collect the full picture:
Step 3: Read Changed Files for Pattern Context
For each modified file (not deleted), read the full current version to understand:
- Existing code style and conventions
- Patterns used in the surrounding code
- How similar functionality is implemented elsewhere in the same file
For new files, find similar files in the same directory or module to establish expected patterns:
Read 1-2 sibling files to understand local conventions.
Step 4: Analyze Changes
Review each change against these criteria:
Pattern Adherence (primary focus alongside challenger dimensions):
- Does the change follow the existing code style in the file?
- Are naming conventions consistent with the codebase?
- Does it reuse existing utilities rather than reinventing?
- Does it follow established architectural patterns in the module?
- Are imports organized consistently with the rest of the file?
- Does error handling follow the existing pattern?
Step 5: Produce Challenge Report
Apply the Challenger methodology from /Users/hbai/.cursor/skills/challenger/SKILL.md. Read that skill and follow its challenge dimensions and output format.
Add one extra dimension to the challenger report:
8. Pattern Adherence
- Deviations from existing code style
- Inconsistent naming with surrounding code
- Reinvented utilities that already exist
- Architectural pattern violations
- Import style inconsistencies
Output Format
Structure the final output as:
Rules
- Always read the actual changed code — never guess from file names alone.
- Always read surrounding code — pattern adherence requires full file context.
- Be specific — cite exact files, lines, and functions.
- Never say "looks good" — there is always something to challenge.
- Prioritize ruthlessly — critical issues first, nitpicks last.
- Challenge assumptions — if the author assumes X, ask "what if not X?"
- Question missing things — missing validation? missing tests? missing error handling?
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingreviewer/SKILL.md
Popularity
- 7-day trend score
- 0
Refreshed 18 Mar 2026, 7 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/tim-hub/role-based-skills/reviewer)