Agent skill
gemini-reviewer
Dual code review: gets independent reviews from both Claude and Gemini API, then synthesizes agreements, unique findings, and a verdict. Use when users say "gemini review", "dual review", or want a second-perspective code review. Requires GEMINI_API_KEY environment variable to be set.
Install this agent skill to your Project
npx add-skill https://github.com/kwiggen/claude-code-plugin/tree/main/skills/gemini-reviewer
SKILL.md
Gemini Dual Code Review Skill
Before Reviewing
- Check Gemini availability — Run
test -n "$GEMINI_API_KEY"via Bash to verify the API key is configured. If it fails, inform the user and fall back to a Claude-only review using the code-reviewer skill. - Gather context — Read related files to understand existing patterns, naming conventions, and architectural decisions.
- Collect the diff — Use the same scope resolution as code-reviewer:
1→ Uncommitted changes (git diff+git diff --cached)2→ Last local commit (git show HEAD)3→ Unpushed local commits (git diff @{upstream}..HEAD)PR#→ GitHub PR diff (gh pr diff <number>)
Dual Review Process
Step 1: Send to Gemini
Pipe the diff to Gemini via Bash:
echo "<diff content>" | node {pluginDir}/dist/gemini/cli.js --prompt "Review this diff for:
1. Logic bugs, incorrect assumptions, unhandled edge cases
2. Security vulnerabilities (injection, auth, data exposure)
3. Performance issues (N+1 queries, unnecessary allocations)
4. Maintainability concerns (naming, complexity, duplication)
5. Missing test coverage
Format your response as:
## Summary
Brief overview of change quality.
## Findings
- **Critical** — Must fix (security, data loss, crashes)
- **Major** — Should fix (quality/maintainability impact)
- **Minor** — Nice to fix (lower priority improvements)
Include file:line references where possible.
Be specific and actionable. Do NOT flag pre-existing issues." --system "You are a senior code reviewer. Be thorough, specific, and actionable."
Capture Gemini's full response from the JSON output's output field.
Step 2: Claude Review
Independently review the same diff using the code-reviewer skill evaluation criteria. Do NOT look at Gemini's output first — form your own assessment.
Step 3: Synthesis
Compare both reviews and present a unified report:
Output Format
Dual Code Review
Scope: [description of what was reviewed]
Claude's Review
[Claude's independent findings using code-reviewer format]
Gemini's Review
[Gemini's response, formatted cleanly]
Synthesis
Agreements
Findings both reviewers identified (highest confidence).
Unique to Claude
Findings only Claude caught.
Unique to Gemini
Findings only Gemini caught.
Verdict
Overall assessment combining both perspectives. Note where reviewers disagree and which assessment seems more accurate based on the code.
Fallback Behavior
If Gemini API key is not configured or the call fails:
- Inform the user: "Gemini API key not configured — running Claude-only review."
- Proceed with a standard code-reviewer skill review.
- Do NOT block the review because of Gemini unavailability.
Guidelines
- Both reviews must be independent — do not let one influence the other.
- Present Gemini's output faithfully; do not rewrite or suppress its findings.
- If Gemini produces low-quality output, note it but still include it.
- The synthesis should add value, not just repeat findings.
When to Use This Skill
Use gemini-reviewer for structured dual code reviews with synthesis (agreements, unique findings, verdict). Use gemini-advisor (/ask-gemini) for general second opinions on any topic, file, or question — not limited to code review.
Pre-Delivery Checklist
Before presenting a dual review, verify:
- Claude's review was completed independently before reading Gemini's
- Gemini's output is presented faithfully without rewriting
- Synthesis contains all 3 sections: Agreements, Unique to Claude, Unique to Gemini
- Verdict addresses any disagreements between reviewers
- Fallback behavior was followed if Gemini was unavailable
CLI Reference
If unsure about Gemini CLI flags, run:
node {pluginDir}/dist/gemini/cli.js --help
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
pr-writer
This skill should be used when the user asks to "create a PR", "open a pull request", "write a PR description", "push and create PR", or needs to generate a best-in-class pull request description based on commits. Provides industry-standard PR description formatting following conventional commits, Microsoft Engineering Playbook, and HackerOne best practices.
code-reviewer
Reviews code for logic flaws, edge cases, performance bottlenecks, security vulnerabilities, maintainability concerns, architecture best practices, and adherence to local patterns and CLAUDE.md guidelines. Use when users ask for code review or analysis, including reviewing uncommitted changes, the last local commit, unpushed code, or a specific GitHub pull request.
antipattern-detector
Detects common failure patterns in proposals, architectures, plans, and decisions. Use when reviewing any plan to identify red flags before they become problems. Covers architecture, timeline, team, process, and technology anti-patterns. Works on any domain — not just code.
github-insights
Provides team GitHub activity insights including merged PRs, contributor leaderboards, merge velocity, review participation, and PR size analysis. Use when users ask about team productivity, who merged PRs, code contribution stats, review patterns, or developer activity.
teach-me
Pedagogical code walkthrough that teaches developers about their own code. Explains choices, tradeoffs, alternatives, and refactoring opportunities. Use when users say "teach me", "explain my changes", "walk me through", "what did I build", or want to understand their code at a deeper level. Works on uncommitted changes, last commit, unpushed commits, or a PR.
issue-creator
Creates GitHub issues and adds them to the ExamJam V.Next 25 project (project 19) with custom field values. Handles the complete workflow of gathering issue details, fetching project field options dynamically, creating the issue, adding it to the project, and setting Priority, Type, Initiative, and Status fields.
Didn't find tool you were looking for?