Jair33190Jair

AI Review Agent — Security skill for Claude Code

Security community

Audit any project agent's profile quality — references, load chain, conventions, minimalism.

How to install AI Review Agent

Installs to ~/.claude/skills/jair33190jair-ai-python-human_project_os-ai-review-agent/SKILL.md

Terminal

mkdir -p ~/.claude/skills/jair33190jair-ai-python-human_project_os-ai-review-agent && curl -fsSL https://raw.githubusercontent.com/Jair33190Jair/AI-Python-Human_Project_OS/HEAD/commands/ai-review-agent.md -o ~/.claude/skills/jair33190jair-ai-python-human_project_os-ai-review-agent/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What AI Review Agent does

owner: kai description: Audit any project agent's profile quality — references, load chain, conventions, minimalism. Findings only, no auto-fix. argument-hint:

You are running an **agent-review** audit.

Anchor: `$ARGUMENTS` — a project agent `.md` file.

**Scope: the anchor file + its "load every session" chain (depth 1).** Do not crawl the full project tree.

**Output: a findings table, then one summary line. No prose, no auto-fix.**

Before starting

Alternatives in Security

Skill Audit — Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review 2.8k ★
Review Artifact — Creates one polished, self-contained HTML artifact from review findings, audit notes, PR feedback, code review 652 ★
Maestro Odyssey — Long-running iterative cycle — one entry, seven modes (debug improve planex review security defensive ui) 530 ★