Is the Review Responder skill free?

Yes. The skill itself is free from Joncik91/ucai. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Review Responder SkillProof Score?

9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.

How do I install Review Responder?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Review Responder with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Review Responder

Blocks sycophantic PR-review capitulation and forces evidence before implementing 'best practice' suggestions.

by Joncik91 · Joncik91/ucai

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.6/10
Tested: Jul 15, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 35426df

Ran a real reviewer comment ('add memoization here, it's a best practice') through both arms: the baseline reply opened with 'You're absolutely right!' and implemented it unverified; the skill reply searched for actual re-render/perf evidence, found none, and pushed back with a file-referenced explanation instead — exactly the forbidden-phrase and YAGNI-gate mechanics the skill describes.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 5/5

What Review Responder does

Gives Claude a disciplined stance for receiving code review feedback: separate signal (bugs, security, spec deviations) from noise (style opinions), run a YAGNI gate on 'best practice' suggestions by searching the codebase for actual usage before implementing, and push back on wrong feedback with file:line evidence instead of capitulating. Triggers when responding to reviewer comments or deciding which suggestions to implement.

How to install Review Responder

git clone https://github.com/Joncik91/ucai
cd ucai
mkdir -p ~/.claude/skills
cp -r skills/review-responder ~/.claude/skills/review-responder

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Review Responder

/review-responder Blocks sycophantic PR-review capitulation and forces evidence before implementing 'best practice' suggestions.

It also activates on plain-language prompts like these:

the reviewer wants memoization added here, should I just do it
push back on this PR comment if it isn't backed by real evidence
help me respond to this code review without just agreeing blindly

Frequently asked questions

Is the Review Responder skill free?: Yes. The skill itself is free from Joncik91/ucai. SkillProof publishes the install command and an independent test verdict at no cost.
Does Review Responder work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Tested · Works. Ran a real reviewer comment ('add memoization here, it's a best practice') through both arms: the baseline reply opened with 'You're absolutely right!' and implemented it unverified; the skill reply searched for actual re-render/perf evidence, found none, and pushed back with a file-referenced explanation instead — exactly the forbidden-phrase and YAGNI-gate mechanics the skill describes.
What is the Review Responder SkillProof Score?: 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install Review Responder?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Review Responder with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.