#317317th of 324 in Skills, plugins and prompts
guard-skills
Review-pass skills that check AI-written code, tests and docs before merge
- Stars
- 1.3k
- License
- MIT
- Last commit
- Jul 2026
6 on 5 Jun 20261,302 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A package of five Markdown skills for coding agents, installed with the Skills CLI (`npx skills add`). Each guard is run on the agent's diff as a second pass: clean-code-guard, test-guard, docs-guard, plus wp-guard and woo-guard for WordPress and WooCommerce code. It works with Claude Code, Codex, Cursor, OpenCode and other agents the CLI supports.
Who it is for: Developers using coding agents who want review gates on generated output
Strengths
- Content is Markdown plus YAML metadata; README states no scripts, network calls or credentials
- Installs per skill or as a whole package, per agent or globally
- Deeper references load only when needed, keeping SKILL.md small
- Covers WordPress and WooCommerce specifics such as HPOS, nonces and escaping
Weaknesses
- Skills install as copies and need `npx skills update` to pick up changes
- Works as a reactive pass; the agent must be told to invoke each guard
- Two of five guards apply only to WordPress or WooCommerce code
- No tagged release; no catch-rate measurements in the README
What it needs
- no GPU
- Needs Skills CLI (npx skills), Node.js
- Models: Claude Code, Codex, Cursor, OpenCode
Quick answers
Is guard-skills open source?
Yes. Its code is on GitHub under the MIT license.
Also in Skills, plugins and prompts
See all 324| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 95 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 95 out of 100 |
| #4 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 95 out of 100 |
| #5 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |