caveman-review SKILL.md skillA

caveman-review from bolens/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add bolens/agent-skills/caveman-review@git:20260905.5a586b0

Pins git:20260905.5a586b0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
bolens/agent-skills
Path
skills/caveman-review/SKILL.md
Versions recorded
4
Latest version
git:20260905.5a586b0, committed Sep 5, 2026
First version recorded
Sep 2, 2026
Size
2,573 bytes
Repository stars
3
License
MIT

Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review or when the user requests terse, one-line review findings. Ordinary review requests use code-review.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Terse review findings

Use [code-review](../code-review/SKILL.md) for scope, contract tracing, evidence, severity, and coverage. This skill controls presentation, not review depth. If code-review is already active, format its results without restarting the review. If unavailable, inspect the requested diff and affected callers, verify reachable failure scenarios, and disclose coverage limits.

## Format

Write one line per finding: `<file>:<line>: [P1] <trigger and consequence>. <smallest fix>.`

Use the repository's severity labels when defined. Keep exact symbols, evidence, and meaningful uncertainty. Severity describes impact, not confidence. Label a source-proven finding as such when it could be mistaken for an executed reproduction. Use `question:` for an unresolved assumption and `nit:` for an optional preference, never to disguise a speculative bug as a finding.

Group duplicate symptoms under their shared cause. Omit praise, restatements of the diff, generic cleanup advice, and arbitrary prescriptions such as a retry count unsupported by the operation's contract.

Examples, only when the stated behavior is established by inspection:
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_fmuxifngviin7cvx/18c17aad3fa09314505f2b25b978fcd41aec53512474a472eaf3119abebac779.json

Then /plugin install caveman-review@markdownregistry-fmuxifngviin7cvx in Claude Code. It installs git:20260905.5a586b0, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add bolens/agent-skills/caveman-review@sha256:18c17aad3fa09314

The line at the top of this page pins the label git:20260905.5a586b0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_fmuxifngviin7cvx.svg)](https://markdownregistry.com/a/art_fmuxifngviin7cvx)

2 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in bolens/agent-skills/caveman-review since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of caveman-review from somewhere else? Ask it: where did my caveman-review come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 4 versions of this file, between Sep 2, 2026 and Sep 5, 2026, about one every day.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260905.5a586b0 latest2026-09-05 5a586b0 2,573 BA view · diff
git:20260905.85179302026-09-05 8517930 2,928 BA view · diff
git:20260902.57643bb2026-09-02 57643bb 2,567 BA view · diff
git:20260902.32224e72026-09-02 32224e7 3,063 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2573 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

bolens/agent-skills · 3 stars · license MIT · pushed 2026-11-17 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_fmuxifngviin7cvx
GET https://markdownregistry.com/api/v1/resolve?ref=bolens/agent-skills/caveman-review
GET https://markdownregistry.com/api/v1/blob/18c17aad3fa09314505f2b25b978fcd41aec53512474a472eaf3119abebac779

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from bolens/agent-skills

speckit-analyze SKILL.md skill
bolens/agent-skills · .agents/skills/speckit-analyze/SKILL.md · Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after…
git:20260915.e7c49bf · audit A · 3 stars
speckit-checklist SKILL.md skill
bolens/agent-skills · .agents/skills/speckit-checklist/SKILL.md · Generate a custom checklist for the current feature based on user requirements.
git:20260915.e7c49bf · audit A · 3 stars
speckit-clarify SKILL.md skill
bolens/agent-skills · .agents/skills/speckit-clarify/SKILL.md · Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and…
git:20261106.88eb75e · audit A · 3 stars
speckit-constitution SKILL.md skill
bolens/agent-skills · .agents/skills/speckit-constitution/SKILL.md · Create or update the project constitution from interactive or provided principle inputs.
git:20260915.e7c49bf · audit A · 3 stars
speckit-converge SKILL.md skill
bolens/agent-skills · .agents/skills/speckit-converge/SKILL.md · Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new…
git:20261106.88eb75e · audit A · 3 stars
speckit-implement SKILL.md skill
bolens/agent-skills · .agents/skills/speckit-implement/SKILL.md · Execute the implementation plan by processing and executing all tasks defined in tasks.md
git:20260915.e7c49bf · audit A · 3 stars
speckit-plan SKILL.md skill
bolens/agent-skills · .agents/skills/speckit-plan/SKILL.md · Execute the implementation planning workflow using the plan template to generate design artifacts.
git:20260915.e7c49bf · audit A · 3 stars
speckit-specify SKILL.md skill
bolens/agent-skills · .agents/skills/speckit-specify/SKILL.md · Create or update the feature specification from a natural language feature description.
git:20261106.88eb75e · audit A · 3 stars
speckit-tasks SKILL.md skill
bolens/agent-skills · .agents/skills/speckit-tasks/SKILL.md · Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
git:20260915.e7c49bf · audit A · 3 stars
AGENTS.md AGENTS.md file
bolens/agent-skills · AGENTS.md
git:20260906.e273861 · audit A · 3 stars
accessibility SKILL.md skill
bolens/agent-skills · skills/accessibility/SKILL.md · Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y…
v2.0 · audit A · 3 stars
animation-assets SKILL.md skill
bolens/agent-skills · skills/animation-assets/SKILL.md · Integrate, diagnose, and verify authored Lottie JSON, dotLottie, and Rive animations in web interfaces, including…
git:20260905.db6655e · audit A · 3 stars

Every file in bolens/agent-skills

Other files named caveman-review

caveman-review SKILL.md skill
juliusbrussee/caveman · skills/caveman-review/SKILL.md · Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this…
git:20260823.8909f6a · audit A · 121,172 stars
caveman-review SKILL.md skill
hoangnguyen0403/agent-skills-standard · .agents/skills/caveman-review/SKILL.md · Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment…
git:20260929.1450937 · audit A · 586 stars
caveman-review SKILL.md skill
skillmds/skillmd · plugins/code-security-review-pipeline/skills/caveman-review/SKILL.md · Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment…
git:20260919.fecc0d5 · audit A · 144 stars
caveman-review SKILL.md skill
eltmon/overdeck · src/lib/caveman/skills/caveman-review/SKILL.md · Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment…
git:20260415.334bbce · audit A · 36 stars
caveman-review SKILL.md skill
chinkan/rustfox · .agents/skills/caveman-review/SKILL.md · Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment…
git:20260804.0abefec · audit A · 12 stars
caveman-review SKILL.md skill
higoralves/orc · codex/orc/content/skills/caveman-review/SKILL.md · Ultra-compressed code review comments — one line per finding: location, problem, fix
git:20261106.693b476 · audit A · 7 stars
caveman-review SKILL.md skill
higoralves/orc · orc/skills/caveman-review/SKILL.md · Ultra-compressed code review comments — one line per finding: location, problem, fix
git:20261020.7a1f356 · audit A · 7 stars
caveman-review SKILL.md skill
chadixearth/graphyloop · skills/caveman-review/SKILL.md · Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment…
git:20260816.6319ca5 · audit A · 3 stars

Browse by kind, by grade A, or by owner.