caveman-review

The caveman-review skill generates concise, one-line code review comments for pull requests. It enforces a strict format of location, problem, and fix to reduce noise in feedback.

219.4K
Installs
3
Use cases
5/10
Quality

Is caveman-review safe to install?

Safe to install

Safe to install: our audit of caveman-review's source files found 0 shell commands, 0 external URLs, no file writes (none risk). Every command and URL listed appears verbatim in the skill's source. The skill performs text processing and formatting based on provided code diffs. It does not execute shell commands, access the network, or modify local files.

How we audit skills: our security review methodology.

Who is this skill for?

Developers and reviewers who prefer terse, actionable feedback on code changes.

What can you do with it?

  • Generating one-line code review comments for pull requests.
  • Categorizing feedback by severity using prefixes like bug, risk, nit, and q.
  • Providing specific line numbers and concrete fix suggestions in code reviews.

How good is this skill?

Quality score: 5/10. The skill documentation is clear, provides specific formatting rules, and includes helpful examples for users.

What does the skill file contain?

SKILL.md
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):**
- `šŸ”“ bug:` — broken behavior, will cause incident
- `🟔 risk:` — works but fragile (race, missing null check, swallowed error)
- `šŸ”µ nit:` — style, naming, micro-optim. Author can ignore
- `ā“ q:` — genuine question, not a suggestion

**Drop:**
- "I noticed that...", "It seems like...", "You might want to consider..."
- "This ...

Frequently asked questions

How does the skill format comments?

It uses the format L<line>: <problem>. <fix>. or <file>:L<line>: <problem>. <fix>.

Can the skill automatically approve pull requests?

No, the skill only generates text comments and does not perform actions like approving or requesting changes.

Does the skill always use the terse format?

No, it reverts to verbose mode for security findings, architectural disagreements, or when the user requests normal mode.

Data sourced from juliusbrussee/caveman on GitHub. Install counts from skills.sh. The summary and security audit are derived from the skill's source files: every command and URL listed appears verbatim in the source.

Related skills