Is the Clab skill free?

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

What is the Clab SkillProof Score?

8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 5/5.

How do I install Clab?

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 Clab 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.

Clab

Self-hosted GitLab MR reviewer: deterministic lint plus inline comments

by mberneti · mberneti/clab

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.0/10
Tested: Jul 24, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 30, 2026 · f0b6362

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 24, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Built the Go lint binary from source and ran it on a crafted diff: it correctly caught a hardcoded sk_live_ API key (critical), a 5-line commented-out block (major, dead-code), and a ticketless TODO (minor), all as structured JSON. That deterministic pre-pass works, but the end-to-end value cannot be measured here: fetch-diff and post-comments need a live self-hosted GitLab host plus a glpat token, and the semantic-review step is just Claude reading the diff with no special harness. Binaries also require a curl-pipe-bash install (release v1.1.0 exists); the command docs match the binary behavior exactly and honestly warn never to commit the token env file.

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 5/10
Docs & honesty 5/5

What Clab does

A Claude Code command pair backed by Go binaries that reviews self-hosted GitLab merge requests: it fetches the MR diff, runs regex lint rules (secrets, dead code, TODOs, oversized files), adds a semantic pass, and posts inline comments. A second command mines past MRs to synthesize project-specific review rules. Triggers on requests to review a GitLab MR or generate review rules from MR history.

How to install Clab

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Clab

/clab Self-hosted GitLab MR reviewer: deterministic lint plus inline comments

It also activates on plain-language prompts like these:

Review this GitLab merge request and post inline comments
Run the lint pass on our self-hosted GitLab MR for secrets
Mine past MRs to generate project-specific review rules

Frequently asked questions

Is the Clab skill free?: Yes. The skill itself is free from mberneti/clab. SkillProof publishes the install command and an independent test verdict at no cost.
Does Clab work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 24, 2026. Verdict: Works with setup. Built the Go lint binary from source and ran it on a crafted diff: it correctly caught a hardcoded sk_live_ API key (critical), a 5-line commented-out block (major, dead-code), and a ticketless TODO (minor), all as structured JSON. That deterministic pre-pass works, but the end-to-end value cannot be measured here: fetch-diff and post-comments need a live self-hosted GitLab host plus a glpat token, and the semantic-review step is just Claude reading the diff with no special harness. Binaries also require a curl-pipe-bash install (release v1.1.0 exists); the command docs match the binary behavior exactly and honestly warn never to commit the token env file.
What is the Clab SkillProof Score?: 8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 5/5.
How do I install Clab?: 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 Clab 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.