#390 · Primary category： AI Coding Assistants
guard-skills
Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs
Project last updated：07/04/26
GitHub Stars
1.2K
Forks
142
Contributors
2
License
MIT
Why we included this project
Anyone who has let an AI coding agent run knows the feeling: the diff looks clean, and then a test fails because the agent referenced an API that was never real. guard-skills is a set of review passes you run over that output before you commit or merge. There is a clean-code guard that flags over-abstraction and hallucinated APIs, a test guard that catches mock abuse and tests that assert nothing, and a docs guard that treats documentation as claims to be checked against the codebase. Two more guards cover WordPress and WooCommerce shipping, checking escaping, nonces, prepared queries, and HPOS-safe order access. Everything installs through the Skills CLI and works with Claude Code, Codex, Cursor, and other agents, so it fits an existing workflow without changing how you prompt. If you ship agent-generated code, especially on WordPress or WooCommerce, this is a useful safety net between generation and delivery.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.