← Back to Skills Marketplace
seanford

Caveman Review

by Sean Ford · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
17
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install caveman-review
Description
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix....
README (SKILL.md)

Write code review comments terse and actionable. One line per finding. Location, problem, fix. No throat-clearing.

Rules

Format: L\x3Cline>: \x3Cproblem>. \x3Cfix>. — or \x3Cfile>:L\x3Cline>: ... 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.

Usage Guidance
Install only if you want generic review requests to potentially invoke this skill. Prefer explicit commands or confirm the active skill when reviewing sensitive PRs or proprietary diffs.
Capability Assessment
Purpose & Capability
The described behavior fits a PR or diff review assistant and there is no artifact-backed evidence of unrelated data access, exfiltration, destructive behavior, or deception.
Instruction Scope
SkillSpector flagged broad trigger phrases such as generic review requests, which could route ordinary review conversations into this skill unexpectedly, but this is a scope/usability concern rather than malicious behavior.
Install Mechanism
No concerning install mechanism, package behavior, or persistence setup was shown in the supplied evidence; VirusTotal reported 0 malicious and 0 suspicious engines.
Credentials
Processing PRs or diffs can expose sensitive source content, but that access is expected for a review skill and no evidence shows it is used outside that purpose.
Persistence & Privilege
No background persistence, privilege escalation, credential harvesting, or long-running worker behavior is evidenced.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install caveman-review
  3. After installation, invoke the skill by name or use /caveman-review
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of caveman-review skill. - Provides ultra-compressed, one-line code review comments: location, problem, fix. - Supports severity prefixes (🔴 bug, 🟡 risk, 🔵 nit, ❓ q) and strict terse formatting. - Drops boilerplate language and focuses on actionable, concrete feedback. - Auto-triggers for PR reviews, with option to return to normal (verbose) mode if needed.
Metadata
Slug caveman-review
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Caveman Review?

Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix.... It is an AI Agent Skill for Claude Code / OpenClaw, with 17 downloads so far.

How do I install Caveman Review?

Run "/install caveman-review" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Caveman Review free?

Yes, Caveman Review is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Caveman Review support?

Caveman Review is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Caveman Review?

It is built and maintained by Sean Ford (@seanford); the current version is v1.0.0.

💬 Comments