Kai Review Project — Security skill for Claude Code
Audit a project's AI system against brigade conventions and project-structure rules.
How to install Kai Review Project
Installs to ~/.claude/skills/jair33190jair-ai-python-human_project_os-kai-review-project/SKILL.md
mkdir -p ~/.claude/skills/jair33190jair-ai-python-human_project_os-kai-review-project && curl -fsSL https://raw.githubusercontent.com/Jair33190Jair/AI-Python-Human_Project_OS/HEAD/commands/kai-review-project.md -o ~/.claude/skills/jair33190jair-ai-python-human_project_os-kai-review-project/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Kai Review Project does
description: Audit a project's AI system against brigade conventions and project-structure rules. Reports PASS/FAIL per check with fix actions. argument-hint: "[project-root-path]" status: draft owner: kai
/kai-review-project
Audit any project's AI system for convention compliance and quality issues. Use when onboarding a new project, after structural changes, or to spot-check convention compliance. Read-only — never edits files.
Arguments
`$ARGUMENTS` — absolute or relative pat
Alternatives in Security
- Review Artifact — Creates one polished, self-contained HTML artifact from review findings, audit notes, PR feedback, code review 652 ★
- UX A11y — WCAG 2.1 AA accessibility audit plus common-courtesy checks beyond the spec 66 ★
- Cache Audit — A Claude Code skill that audits your setup against the 6 prompt caching rules from Anthropic's engineering tea 58 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Google Business Profile AI Automation
Audit a Google Business Profile against 39 local SEO rules, get a client-ready HTML report, then fix it: rewri
AI Review Agent
Audit any project agent's profile quality — references, load chain, conventions, minimalism. Findings only, no
Review Test Quality
Audit test suite quality: coverage gaps, weak assertions, missing negative cases, over-mocking, and tests that
Reviewgate
Fail-closed independent review loop for Claude Code and Codex. Native hooks, six reviewer paths (Codex, Gemini
Verify Flow
Validates existing agents, commands, skills, and hooks against project conventions. Detects structural issues,
Audit Strict
Multi-pass consensus audit — runs the audit twice with different prompts, only reports consensus findings. Agg
Related Agents
Ddw Arch Auditor
Read-only architecture auditor. Spawn it in PLAN to check a proposed spec against the project's conventions, a
Daw Arch Auditor
Read-only architecture auditor. Spawn it in PLAN to check a proposed spec against the project's conventions, a
PR Check Watcher
Watches a GitHub PR's CI checks to completion via gh pr checks --watch and reports a concise pass/fail summary