Is the Review All skill free?

Yes. The skill itself is free from ncoevoet/claude-review-all. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Review All SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Review All?

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 All 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 All

Diff-scoped review orchestrator with real automated gates, severity/confidence-tagged findings, and a mandatory triage menu.

by ncoevoet · ncoevoet/claude-review-all

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 15, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 6a8d398

⚠ The author changed this skill after we tested it. The verdict below describes the version we ran on Jul 15, 2026; it's queued for a re-test.

Ran the bundled discover.sh live and it worked cleanly; caught a real command-injection bug in a throwaway diff (child_process.exec with unsanitized template-literal input) and then proved it exploitable with an actual PoC that wrote a marker file to disk under /tmp -- that's a VERIFIED-confidence finding, not a guess.

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 8/10
Docs & honesty 5/5

What Review All does

Reviews a git diff (uncommitted, staged, a commit range, or a GitHub PR) against automated gates plus a bugs/security/DRY/perf/a11y heuristic pass, verifying every finding before it reaches the report. Triggers on /review-all, 'pre-PR review', 'pre-commit check', or an ask to audit uncommitted or staged changes.

How to install Review All

git clone https://github.com/ncoevoet/claude-review-all
mkdir -p ~/.claude/skills
cp -r claude-review-all/skills/review-all ~/.claude/skills/review-all

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

Commands — how to trigger Review All

/review-all Diff-scoped review orchestrator with real automated gates, severity/confidence-tagged findings, and a mandatory triage menu.

It also activates on plain-language prompts like these:

Review my uncommitted changes before I open a pull request
Do a thorough pre-commit review of my staged diff for bugs and security holes
Audit this pull request diff for bugs, security issues, and DRY violations

Frequently asked questions

Is the Review All skill free?: Yes. The skill itself is free from ncoevoet/claude-review-all. SkillProof publishes the install command and an independent test verdict at no cost.
Does Review All work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Tested · Works. Ran the bundled discover.sh live and it worked cleanly; caught a real command-injection bug in a throwaway diff (child_process.exec with unsanitized template-literal input) and then proved it exploitable with an actual PoC that wrote a marker file to disk under /tmp -- that's a VERIFIED-confidence finding, not a guess.
What is the Review All SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Review All?: 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 All 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.