Ross ROSS = Recommend OSS · open-source software intelligence for agents

amElnagdy/guard-skills

Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs observed · 2026-08-28

github.com/amElnagdy/guard-skills · homepage · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

54/100

  • Activity 90
  • Release rhythm 35
  • Longevity 6

Flags: no_releases young

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 88
  • days_rel: n/a
  • days_push: 60
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

1203 stars · 142 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A collection of guard skills for AI coding agents that act as second-pass quality gates on AI-generated code, tests, and documentation. It ships five installable skills (clean-code-guard, test-guard, docs-guard, wp-guard, woo-guard) via the skills CLI for agents like Claude Code, Codex, and Cursor.

Use cases

  • review AI-generated code for LLM code smells before committing
  • catch useless or mock-abusing tests written by an AI agent
  • verify documentation claims against actual source code to catch hallucinated APIs
  • quality-check WordPress plugin changes made by a coding agent
  • review WooCommerce checkout code changes
  • add a reactive review pass to an AI coding workflow

When to choose

  • you use AI coding agents like Claude Code, Codex, or Cursor and want automated second-pass review of their output
  • you want to catch systematic AI failure modes like over-abstraction, broad error swallowing, and hallucinated symbols
  • you work with WordPress or WooCommerce and need domain-specific guard passes
  • you want lightweight, MIT-licensed skills installable via npx

When to avoid

  • you need a standalone linter or CI-integrated static analysis tool rather than agent-invoked skills
  • your workflow does not involve AI coding agents
  • you need deep semantic analysis or type checking rather than heuristic review passes
  • you require guaranteed correctness - these are heuristic guards, not formal verification

Facets

plugin · maturity active

code-review testing documentation developer-tools developer-tools large-language-models cli cross-platform agent-skills claude-code codex cursor quality-gates ai-generated-code llm-code-smells wordpress woocommerce skills-sh ai-agents automation

9 sources

Member repositories

RepositoryRoleHealth v2
amElnagdy/guard-skillsmain54

For agents

markdown · JSON · MCP: product_card(name="amElnagdy/guard-skills")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem