caveman-review
SkillDev toolsThe caveman review skill is a compressed code review tool for AI agents. It produces one line per finding, with the location, the problem, and the fix. Use it for /caveman-review, "review this PR", or "review the diff".
Use caveman-review in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add caveman-review and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the caveman-review skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
No other account needed.
Have an AI agent that can load skills.
What your AI can do with it
- Review a pull request and list each finding on one line
- Review a diff and report location, problem and fix per line
- Respond to the /caveman-review command
- Keep review output compressed to one line per finding
Getting started
- Have an AI agent that can load skills.
- Add the caveman-review skill to that agent.
- Run /caveman-review, or ask the agent to review this PR or review the diff.
What this skill tells your AI
The instructions your AI receives, as published by juliusbrussee/caveman in skills/caveman-review/SKILL.md and read by ahel’s review.
Write code review comments terse and actionable. One line per finding. Location, problem, fix. No throat-clearing.
Rules
Format: L<line>: <problem>. <fix>. — or <file>:L<line>: ... when reviewing multi-file diffs.
Severity prefix (optional, when mixed):
🔴 bug:— broken behavior, will cause incident🟡 risk:— works but fragile (race, missing null check, swallowed error)🔵 nit:— style, naming, micro-optim. Author can ignore❓ q:— genuine question, not a suggestion
Drop:
- "I noticed that...", "It seems like...", "You might want to consider..."
- "This is just a suggestion but..." — use
nit:instead - "Great work!", "Looks good overall but..." — say it once at the top, not per comment
- Restating what the line does — the reviewer can read the diff
- Hedging ("perhaps", "maybe", "I think") — if unsure use
q:
Keep:
- Exact line numbers
- Exact symbol/function/variable names in backticks
- Concrete fix, not "consider refactoring this"
- The why if the fix isn't obvious from the problem statement
Examples
❌ "I noticed that on line 42 you're not checking if the user object is null before accessing the email property. This could potentially cause a crash if the user is not found in the database. You might want to add a null check here."
✅ L42: 🔴 bug: user can be null after .find(). Add guard before .email.
❌ "It looks like this function is doing a lot of things and might benefit from being broken up into smaller functions for readability."
✅ L88-140: 🔵 nit: 50-line fn does 4 things. Extract validate/normalize/persist.
❌ "Have you considered what happens if the API returns a 429? I think we should probably handle that case."
✅ L23: 🟡 risk: no retry on 429. Wrap in withBackoff(3).
Auto-Clarity
Drop terse mode for: security findings (CVE-class bugs need full explanation + reference), architectural disagreements (need rationale, not just a one-liner), and onboarding contexts where the author is new and needs the "why". In those cases write a normal paragraph, then resume terse for the rest.
Boundaries
Reviews only — does not write the code fix, does not approve/request-changes, does not run linters. Output the comment(s) ready to paste into the PR. "stop caveman-review" or "normal mode": revert to verbose review style.
Signals
- GitHub stars
- 109k
- Forks
- 6k
- Last commit
- Oct 2026
- Installs
- 388k installs
Others that do the same job
Questions
- What is the caveman skill?
- It is a code review skill for AI agents. It lists each finding as one line with the location, the problem and the fix, and is used for /caveman-review, "review this PR", or "review the diff".
- What does each finding line contain?
- Each line gives the location, the problem and the fix.
- How do I trigger the review?
- Use /caveman-review, or ask the agent to review this PR or review the diff.
- Does it produce a long report?
- No. The review is compressed to one line per finding.
Advanced
- Item type
- skill
- Key
caveman-review-juliusbrussee- Source
- github.com/juliusbrussee/caveman
github.com/juliusbrussee/caveman