write-a-skill — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited write-a-skill (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.
skill-name/
├── SKILL.md # Main instructions (required)
├── reference.md # Detailed docs (if needed)
├── examples.md # Usage examples (if needed)
├── scripts/ # Scripts (if needed)
│ └── helper-script.sh # Utility script (if needed)
└── templates/ # Templates (if needed)
├── template-1.md
└── template-2.md---
name: skill-name
description: Brief description of capability. Use when [specific triggers].
---
# Skill name
## Quick start
[Minimal working example]
## Workflows
[Step-by-step processes with checklists for complex tasks]
## Advanced features
[Link to separate files: See [reference.md](reference.md)]The description is the only thing your agent sees when deciding which skill to load. It's surfaced in the system prompt alongside all other installed skills. Your agent reads these descriptions and picks the relevant skill based on the user's request.
Goal: Give your agent just enough info to know:
Format:
Good example:
Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when user mentions PDFs, forms, or document extraction.Bad example:
Helps with documents.The bad example gives your agent no way to distinguish this from other document skills.
Add utility scripts when:
Scripts save tokens and improve reliability vs generated code.
Split into separate files when the skill contains optional elements that don't always apply and don't always need to be read.
For example, a review-pr skill keeps its core workflow in SKILL.md but stores language-specific conventions in java.md or rust.md — only loaded when reviewing code in that language.
After drafting, verify:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.