菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | gemini-review |
| description | 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. |
| allowed-tools | ["Read","Bash"] |
| compatibility | Requires Gemini CLI installed and GEMINI_API_KEY in environment. |
MANDATORY: Always use --model gemini-3.1-pro-preview. No other model. No fallback. No substitution.
Activate when user says: "gemini review", "review with gemini", "local review", or /gemini-review.
| 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 |
# 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...HEAD
# 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--all flag for uncommitted changes--branch flag for branch reviewPrompt templates are in ~/.claude/skills/gemini-review/prompts/:
default.md - Concise review focused on bugs/security/performanceci-style.md - Detailed review matching CI pipeline styleOption 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
\`\`\`
EOF
Gemini's output will appear in the terminal. Summarize key findings for the user.
--branch with specific files| 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 |
Execution trace capture and token baselining. Use when user says trace, extract trace, count tokens, token baseline, or /harness-trace. Not for harness optimization (use harness-mechanic).
Release prep and tagging with pre-flight verification. Use when user says release, tag, ship it, push to production, create release, or bump version. Not for editing a version string outside a release, a lockfile or a changelog entry by hand, and not for reading what changed in a past release: those are ordinary edits, just do them.
Mine LEARNING.md retrospectives across all repos for recurring failure-modes, then propose harness changes (hooks, rules, skills, checklist items) with falsifiable change-contracts. Also runs the doc-gardening pass over the governance docs (stale rules, dead cross-references, skill-table drift). Use when user says learning loop, mine learnings, recurring failures, what should I fix in my process, cross-repo retrospective, doc gardening, stale docs, or run learning-loop. Runs on human schedule, never autonomously. Not for single-project retrospectives (use learning-docs) or trace/token analysis (use harness-mechanic).
Full contractor-mode loop: sub-protocols (LOCALIZE, BENCH-BASELINE, REPRODUCE, DRIFT), review routing by file pattern, blast radius, UAT, parallelism and effort caps, escalation, just-do-it, goal-backed runs. Load it to RUN that loop, once you have an approved plan and are entering step 1, or when a step needs its detail. It is a protocol, not a way to do the work: it never replaces the language, review or planning skill the task itself calls for, and a task small enough to just edit (SKIP_SET) needs none of it. The always-on spine lives in rules/orchestrator-protocol.md. Not for trace capture (harness-trace) or harness optimization (harness-mechanic).
Ruby on Rails with service-oriented architecture, Dry-validation, Sidekiq/Solid Queue, Hotwire. Use for Rails API, Rails services, Rails forms, RSpec, ActiveRecord, Rails migrations. Not for standalone Ruby gems (use ruby skill), and not for judging whether a migration is safe to run in production (that is the database-reviewer agent).
Get three independent second opinions (isolated Claude + isolated Gemini + isolated DeepSeek) on a problem Claude is analyzing. Use when user says second opinion, another perspective, challenge this approach, or asks gemini/deepseek about a decision, approach, or diagnosis. Also invoke on your own initiative, without being asked: on a complex task before planning, after 2 failed root-cause attempts, on a 🔴 decision (rewrite, core logic, security), or when the review loop is stuck below 80 after 2 fix rounds. Gathers context, writes a focused prompt, calls all reviewers in isolated Docker containers, and synthesizes all viewpoints. Not for reviewing code or changes, even phrased as 'ask gemini to review' (use gemini-review).