gemini-review
Skill17 starsChanged 52 days agoMITView on GitHub
Local code review with Gemini CLI for pre-commit reviews. Use when user says review code, code review, check my changes, or review before commit.
- Reads credentials
7 other projects use a version of this.
Adopted by
Most recently taken up by
- itgenius-au/skills-librarytheir own version, first seen Oct 30, 2026
- alinaqi/claude-bootstraptheir own version, first seen Oct 8, 2026
- iamneilroberts/claude-skillstheir own version, first seen Jul 3, 2026
- alinaqi/maggytheir own version, first seen Jun 12, 2026
- anydasa/claude-skillstheir own version, first seen Apr 26, 2026
- cukas/claudes-ai-buddiestheir own version, first seen Mar 22, 2026
Used with
Projects with it also use codex-review.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
juriwiensSkillcodex-review
Run code review via Codex CLI
Also in 5 projects that use this
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- alinaqi/maggy★ 711same name
- alinaqi/claude-bootstrap★ 708same name
- iamneilroberts/claude-skills★ 26same name
- cukas/claudes-ai-buddies★ 9same name
- jsshin-hamsterlab/claude-skills★ 2same name
- itgenius-au/skills-library★ 1same name
- anydasa/claude-skills★ 0same 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 repository37 other files it gives its agents.
- adrSkill
- android-kotlinSkill
- apple-swiftSkill
- autoresearch-promptSkill
- blog-writerSkill
- cloud-infrastructureSkill
- commitSkill
- cover-imageSkill
- freezeSkill
- golangSkill
- harness-mechanicSkill
- harness-traceSkill
- humanizerSkill
- ios-debuggerSkill
- knowledge-syncSkill
- learning-docsSkill
- learning-loopSkill
- obsidianSkill
- orchestratorSkill
- plan-forgeSkill
- process-clippingsSkill
- project-analyzerSkill
- project-checksSkill
- pr-reviewSkill
- pythonSkill
- railsSkill
- react-nextjsSkill
- refine-requirementsSkill
- releasing-softwareSkill
- rubySkill
- scoreSkill
- second-opinionSkill
- skill-forgeSkill
- source-controlSkill
- terraformSkill
- test-design-reviewerSkill
- verify-frontendSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Every gemini call uses --model gemini-3.1-pro-preview, as in the commands below.
- Distinctive: line 46
If no changes, inform user and suggest:
- Distinctive: line 93
Read the diff yourself before sending it, so you can judge Gemini's findings against it
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
ABOUTME: Local code review skill using Gemini CLI for pre-commit reviews
ABOUTME: Supports staged, uncommitted, or branch diff with configurable prompts
Gemini Review - Local Code Review
Every gemini call uses --model gemini-3.1-pro-preview, as in the commands below; do not substitute or fall back to another model.
Options
| Option | Description | Default |
--all | Review all uncommitted changes | staged only |
--branch [base] | Review current branch vs base | main |
--prompt <name> | Use specific prompt template | default |
--extension | Use Gemini's built-in /code-review | custom prompt |
Execution Flow
Step 1: Determine diff scope
# Default: staged changes
git diff --cached
# With --all: all uncommitted
git diff HEAD
# With --branch [base]: branch vs base (default base: main)
git diff main...HEADStep 2: Check if there are changes to review
# Check if diff is empty
git diff --cached --quiet && echo "No staged changes" || echo "Has changes"If no changes, inform user and suggest:
git add <files>to stage changes--allflag for uncommitted changes--branchflag for branch review
Step 3: Load prompt template
Prompt templates are in ~/.claude/skills/gemini-review/prompts/:
default.md- Concise review focused on bugs/security/performanceci-style.md- Detailed review matching CI pipeline style
Step 4: Execute review
Option A - Using built-in extension (with --extension flag):
cd <project_root>
gemini --model gemini-3.1-pro-preview --yolo "/code-review"Option B - Using custom prompt (default):
cd <project_root>
# Generate diff
DIFF=$(git diff --cached)
# Read prompt template
PROMPT=$(cat ~/.claude/skills/gemini-review/prompts/default.md)
# Invoke Gemini with prompt and diff
gemini --model gemini-3.1-pro-preview --yolo <<EOF
$PROMPT
## Code Changes to Review
\`\`\`diff
$DIFF
\`\`\`
EOFStep 5: Present results
Gemini's output will appear in the terminal. Summarize key findings for the user.
Quality Notes
- Read the diff yourself before sending it, so you can judge Gemini's findings against it
- Summarize the findings instead of relaying raw output, and mark the false positives you spot
Important Notes
- Always run from project root - Gemini needs project context
- Check for CLAUDE.md/GEMINI.md - Include project guidelines in prompt if present
- Large diffs - For very large diffs (>10000 lines), suggest
--branchwith specific files - Exit codes - Gemini CLI returns 0 on success, non-zero on error
Troubleshooting
| Issue | Solution |
| "No staged changes" | Run git add <files> or use --all |
| "gemini: command not found" | Install Gemini CLI: see https://github.com/google-gemini/gemini-cli |
| API errors | Check GEMINI_API_KEY is set |
| Timeout on large diffs | Split into smaller reviews or use --extension |
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.

