gemini-review
Launch an independent Gemini 4 Carbon code review through Cursor at High reasoning and return it verbatim. Use for /gemini-review, or when the user or another agent asks for a Gemini review.
Install / Use
npx skills add davidondrej/skills --skill gemini-reviewInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Our assessment of gemini-review
gemini-review scores 82/100 on our quality scale, 3320th of 4,698 Development & Engineering skills we index.
Its SKILL.md is 2.7 KB long, split into 5 sections and no code examples: a solid amount of guidance for an agent.
With 4,079 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated about 2 months ago, so gemini-review is actively maintained.
- It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-11-16. Automated pattern scan on 2026-11-16. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
gemini-review compared with similar skills
All 4 of these similar skills score higher than gemini-review; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| gemini-review (this skill)by davidondrej | 82 | 4.1k | 53d ago | SKILL.md |
| taste-skillby Leonxlnx | 100 | 116.8k | 8d ago | CLAUDE.md |
| ai-job-searchby ai-job-search-dev | 100 | 72.1k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 47.3k | 2d ago | CLAUDE.md |
| lobehubby lobehub | 100 | 85.6k | today | MCP Server |
Frequently asked questions
- How do I install gemini-review?
- Run
npx skills add davidondrej/skills --skill gemini-review. The install tabs above show the steps for each supported agent. - Which AI agents does gemini-review work with?
- It is written for Gemini CLI and Cursor, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is gemini-review safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is gemini-review still maintained?
- The repository was last updated about 2 months ago, so gemini-review is actively maintained.
Skill content
View source on GitHubname: gemini-review description: Launch an independent Gemini 4 Carbon code review through Cursor at High reasoning and return it verbatim. Use for /gemini-review, or when the user or another agent asks for a Gemini review. triggers: [user, model]
Gemini Review
Always use Gemini 4 Carbon (gemini-4-carbon) through Cursor at High reasoning, orchestrated by Cloudroom. The model, route, and effort never change.
Route
--provider acp-cursor --model gemini-4-carbon --reasoning-level high
acp-cursor is Cloudroom's Cursor provider: the Cursor CLI over ACP. Never use OpenRouter, Vercel, Google directly, or a bare cursor-agent shell run. The route bills the user's Cursor plan.
Before spawning, confirm room-cli provider models acp-cursor --selected-model gemini-4-carbon --json lists the model with high. The plain list hides it. Stay on high even if a higher level appears.
Run
Read /room-cli and follow its launch checks.
- Local thread: reuse the current environment, including uncommitted work, and use
--parent-self. - Cloud thread: the provider is
cursor, notacp-cursor, in both the spawn and theprovider modelscheck. Start a plain child: never--shared-sandbox(Cursor can't share a sandbox) and never--top-level(you can't read or wait for it). The child gets a copy of your code, uncommitted work included.thread showhides the model there, so an accepted spawn is the proof.
The route fails when the spawn errors, room-cli thread show reports a different model or effort, or the first turn errors (gateway errors, auth errors, an empty balance). Stop and archive the failed thread, then report the blocker with its error. Never switch to another model or route.
Review brief
Give neutral context: scope, paths, intended behavior, and diff/base revision. Ask for a thorough senior-developer review, including related code and tests, without steering toward suspected bugs, solutions, or verdicts. Review only; do not change files. Request a concise plain-English report of serious or critical issues, fixes, and production merge readiness. Distinguish verified findings from uncertainty and identify validation gaps.
Include this sentence in the brief, word for word: "During your final answer, Rate each issue you find from 1 to 10 on how often it would happen, and 1-10 on how bad it would be"
Result
Use room-cli thread wait and room-cli thread output. Verify this review actually completed; idle status, timeouts, gateway errors, and queued retries are not completion. If the route dies mid-review, retry it once with the same brief.
Return the completed reviewer's full final response verbatim, followed by one line naming the route used.
Related Skills
taste-skill
116.8kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
ai-job-search
72.1kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
47.3kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
lobehub
85.6k🤯 LobeHub - Super-Agents on Your Team. Add super-agents to the chats your team already uses.They take on work by themselves and get better every week.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
