Skill that teaches AI agents how to build Agent Skills for Claude Code, Codex, Amp, and OpenCode. Production patterns from gno, sheets-cli, raindrop, outlookctl, and flow.
SaferSkills independently audited better-skill-builder (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Help users build clean, discoverable skills that work across Claude Code, Codex, Amp, and OpenCode.
Fetch from https://agentskills.io/specification for YAML frontmatter, file format, and client integration details.
my-skill/
SKILL.md # Required (<500 lines)
references/ # Optional: detailed docs
scripts/ # Optional: executable utilities---
name: my-skill
description: >
What it does. Include trigger phrases so AI knows when to activate.
---
# Title
## When to Use
- Trigger condition 1
- Trigger condition 2
## Quick Reference
[Tables, common commands]
## Detailed Docs
See [references/](references/) for full documentation.| Topic | File |
|---|---|
| Full SKILL.md template | format.md |
| Adding scripts | scripts.md |
| Safety/auth/trigger patterns | patterns.md |
| Installation paths | installation.md |
| Distribution (git/CLI/plugin) | distribution.md |
| Plugin/marketplace structure | plugin-structure.md |
| Production examples | real-examples.md |
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.