dev:review-llm
LLM system review grounded in CMU 11-667 (Harms + Attacking LLMs), Berkeley CS294-196 (Safety/Guardrails), and OWASP LLM Top 10. Use this skill whenever the user wants to review an existing LLM-powered system or feature for architecture quality, eval coverage, safety, and production readiness. Triggers: "review my LLM system", "check my RAG", "is my prompt injection safe", "review my agent", "audit my AI feature", "LLM code review", "check my evals", "my RAG is not working properly", "review my LLM setup", "what is wrong with my agent", "LLM audit". Covers: integration pattern assessment, RAG quality, eval coverage, safety/security (OWASP LLM Top 10), production readiness (cost, observability, guardrails). Always use this skill for LLM system reviews.
Security AStatic scan found no risk patternsHow grading works ›
From the source SKILL.md
Structured review of existing LLM systems grounded in CMU 11-667, Berkeley CS294-196, and OWASP LLM Top 10. Identifies architecture gaps, eval blind spots, and safety risks.
What this skill does
dev:review-llm is a community-contributed Claude Code skill in the web-security sub-category. It ships as a SKILL.md file that Claude Code auto-discovers under ~/.claude/skills/review-llm/ and loads when your prompt matches the skill's trigger.
Who uses this skill
The dev:review-llm Claude Code skill is built for security engineers, penetration testers, DevSecOps practitioners, and development teams hardening codebases and infrastructure. It's part of ClaudSkills (also referred to as Claude Skills or Claude Code Skills) — the open community-curated registry of 115,000+ SKILL.md files for Anthropic's Claude Code agent and the wider Claude ecosystem (Claude API, Claude Agent SDK).
How to install
Free
Manual install (2 steps)
mkdir -p ~/.claude/skills/review-llm
curl -L https://claudskills.com/skills/review-llm/SKILL.md \
-o ~/.claude/skills/review-llm/SKILL.md
Or just download SKILL.md directly and drop it into ~/.claude/skills/review-llm/. Claude Code auto-discovers it on next session.
Skills live at ~/.claude/skills/review-llm/SKILL.md on macOS/Linux, or %USERPROFILE%\.claude\skills\review-llm\SKILL.md on Windows. See the full install guide for step-by-step instructions.
Telegram
📱 Install from your phone or desktop Telegram
Open @claudskills_bot on Telegram, tap Open Desktop App, and the desktop app installs this skill for you. Or share the bot link with a colleague — they get the same one-tap install. Learn more →
Pro
One-click install via the desktop app
The ClaudSkills desktop app installs any skill directly into ~/.claude/skills/ with one click — no terminal required. Pro starts at $9/mo or $149 lifetime.
Pro
For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.
Frequently asked questions
How do I install the dev:review-llm Claude Code skill?
Install via the ClaudSkills desktop app (one click) or copy
SKILL.md from the source repository to
~/.claude/skills/review-llm/SKILL.md and restart Claude Code. Both flows are detailed at
claudskills.com/install/.
What does the dev:review-llm skill do?
LLM system review grounded in CMU 11-667 (Harms + Attacking LLMs), Berkeley CS294-196 (Safety/Guardrails), and OWASP LLM Top 10. Use this skill whenever the user wants to review an existing LLM-powered system or feature for architecture quality, eval coverage, safety, and production readiness. Triggers: "review my LLM system", "check my RAG", "is my prompt injection safe", "review my agent", "audit my AI feature", "LLM code review", "check my evals", "my RAG is not working properly", "review my LLM setup", "what is wrong with my agent", "LLM audit". Covers: integration pattern assessment, RAG quality, eval coverage, safety/security (OWASP LLM Top 10), production readiness (cost, observability, guardrails). Always use this skill for LLM system reviews.
Is this skill free to install?
Yes. ClaudSkills is an open registry — every skill keeps its source repository's license, and manual install via copy is free. ClaudSkills Pro ($9/mo, $79/yr, or $149 one-time) adds one-click install via the desktop app and a multi-signal Quality Score.
When should I use the dev:review-llm skill?
Use dev:review-llm when your Claude Code task falls under the Security category — specifically in the web security area. Claude Code auto-discovers installed skills and invokes the right one based on the task description, so you can also ask Claude directly (e.g. "use dev:review-llm" or describe the task and let Claude pick). Browse related skills at
/category/security/.
What is a Claude Code skill and how does the dev:review-llm skill fit in?
A Claude Code skill is a
SKILL.md file that lives under
~/.claude/skills/<name>/ and tells the Claude Code CLI agent how to perform a specific task (instructions, prompts, allowed tools). Skills are auto-discovered at session start. dev:review-llm is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the Security category. Learn more at
/learn/what-is-a-claude-skill/.
Attribution & license
Cite this skill
If you reference this skill in a blog post, paper, or documentation, you can cite it as:
APA
gerfru. (2026). dev:review-llm [Claude Code skill]. ClaudSkills. https://claudskills.com/skills/review-llm/
BibTeX
@misc{review-llm-2026,
author = {gerfru},
title = {dev:review-llm [Claude Code skill]},
year = {2026},
publisher = {ClaudSkills},
url = {https://claudskills.com/skills/review-llm/}
}Embed this skill
Promote, attribute, or link this skill from your own README, blog post, or documentation. All three snippets are free to use — no sign-up, no API key. More distribution surfaces →
Badge
[](https://claudskills.com/skills/review-llm/?utm_source=badge&utm_medium=readme&utm_campaign=skill_badge)
<script>
<script src="https://claudskills.com/embed/review-llm.js" async></script>
<iframe>
<iframe src="https://claudskills.com/embed/review-llm.html" width="100%" height="160" frameborder="0" loading="lazy" title="ClaudSkills: dev:review-llm"></iframe>
Security scan
Grade A · scanned 2026-06-13 — free static scan against the OWASP Agentic Skills Top 10.
No risk patterns were found in any of the ten OWASP-aligned categories. How grading works ›
- ✓ Prompt injection
- ✓ Data exfiltration
- ✓ Supply chain
- ✓ Reverse shell
- ✓ Credentials
- ✓ Execution
- ✓ Filesystem
- ✓ Persistence
- ✓ Obfuscation
- ✓ Network
Show this grade on your repo (click to copy):
[](https://claudskills.com/skills/review-llm/#security)
More Security skills
Browse all Security skills in the ClaudSkills registry, or explore these other picks from the same category:
Part of Acreator Store — Adam Lankamer's AI tools:
PerfectStudio ·
Ucaption ·
UTagger ·
AutoXPoster ·
TestYourSkills ·
AutomationFlows ·
Au Naturel ·
Telegram @acreatorstore