caveman-review · Skill Details

Mechanism

When It Triggers · How It Works · What It Produces

Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.

Trigger

User explicitly requests PR review: "review this PR", "code review", "review the diff", "/review", or /caveman-review.
Auto-triggers when the model is reviewing pull requests.

Mechanism

Each finding follows a fixed format: L<line>: <problem>. <fix>. or <file>:L<line>: ... (for multi-file diffs).
Optional severity prefix (🔴 bug / 🟡 risk / 🔵 nit / ❓ q) strips filler automatically.
Only outputs review comments — does not write code fixes, approve/reject, or run linters.
Auto-Clarity: switches to full paragraphs for security findings and architectural disagreements.

Result

One-line actionable review comments ready to paste into PR platforms.
Each comment includes: location, severity, problem, fix.
Reviewers and authors understand issues quickly without decoding verbose filler.

Use Cases

Two Typical Use Cases

Scenario 01

Daily PR code review

When a developer submits a PR and needs peer review, the user says "review this PR", "code review", "/review", or `/caveman-review`. The agent automatically reviews the diff and outputs one-line comments like `L42: 🔴 bug: user can be null after .find(). Add guard before .email.`, allowing both reviewer and author to quickly locate and understand each issue.

Scenario 02

Security and architecture-level deep review

For CVE-class security vulnerabilities or architectural disagreements requiring detailed explanation, caveman-review has a built-in Auto-Clarity mechanism: it switches to full paragraph explanation with rationale for critical findings, then resumes terse style afterward. This balances brevity with depth, ensuring important matters are not over-compressed.

Skill Relationships

Which Skills I Use · Which Skills Use Me

Dependency relationships read as "the upper tier points to the lower tier." The current Skill sits in the middle tier — above are Skills that depend on it, below are Skills it depends on.

Tier 1 · These Skills Use Me

caveman-helpCLI Manual

Tier 2 · Current Skill

caveman-reviewWorkflow

Tier 3 · I Use These Skills

No explicit dependency on other Skills

Full Relationship Graph

Browse this skill's relationships within its skillset. Click a node to switch the side panel; use the search box to jump to any skill.

Skill File

SKILL.md

Open in GitHub ↗

SKILL.mdLoading from GitHub…

Skill Composition

Open in GitHub ↗

SKILL.md50.0%
other50.0%

▸skills/caveman-review/
▸caveman-review
- ·README.md
- ·SKILL.md

Per the Agent Skills spec, SKILL.md is the only required file. The colored bars classify the rest into the three spec-aligned optional directories (scripts / references / assets) and an 'other' bucket. The full directory tree is below.

Related in Skillset

You May Also Need These Skills

cavecrew

The cavecrew skill provides a delegation decision guide for three caveman-style subagent presets: `cavecrew-investigator` (locate code), `cavecrew-builder` (surgical 1-2 file edits), and `cavecrew-reviewer` (diff review). Subagent output is caveman-compressed, returning tool results ~60% smaller into main context than standard subagents. Key output: ~60% context token savings per delegation, letting the main thread accomplish more before context exhaustion.

Workflow

caveman

The caveman skill is the core of the Caveman skillset. It saves ~65% output tokens by making the AI coding agent reply in ultra-terse "caveman speak". Supports 6 intensity levels (lite/full/ultra/wenyan), strips filler/pleasantries/hedging while preserving code, technical terms, and error messages verbatim. Key output: dramatically reduced output token consumption per session, faster code reading, lower API costs.

Workflow

caveman-commit

The caveman-commit skill generates ultra-compressed Git commit messages following Conventional Commits format. Subject line ≤50 chars, body only when "why" isn't obvious. Automatically strips "This commit does X", "I", "we" filler and AI attribution. Key output: a terse but information-complete commit message code block ready to paste into `git commit`. The agent only generates the message — it does not run git commit, stage files, or amend commits.

Workflow

caveman-compress

The caveman-compress skill compresses natural language memory files (CLAUDE.md, todos, preferences) into caveman format, saving ~46% input tokens on every subsequent session. It uses a Python script (`scripts/__main__.py`) for automated compression, preserving all technical content, code, URLs, and structure. The compressed version overwrites the original, with a human-readable backup saved as `FILE.original.md`. Key output: compress once, save tokens every session forever.

Workflow