skill-creator — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited skill-creator (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.
Create modular, self-contained packages that extend AI capabilities with specialized knowledge and workflows across different hosts.
Challenge each piece: "Does the AI really need this?" Prefer concise examples over verbose explanations.
skill-name/
├── SKILL.md (required)
│ ├── YAML frontmatter (name, description)
│ └── Markdown instructions
└── Bundled Resources (optional)
├── scripts/ - Executable code
├── references/ - Documentation
└── assets/ - Templates, icons---
name: my-skill
description: What it does AND when to use it (critical for triggering)
---
# Title
[Core instructions - imperative form]
## Sections as needed| Do | Don't |
|---|---|
| Clear, comprehensive description | Vague one-liner |
| Imperative form ("Create", "Run") | Passive voice |
| Concise examples | Verbose explanations |
| Reference files for details | Everything in SKILL.md |
| Test scripts by running them | Assume they work |
| Use host-agnostic paths and wording | Hard-code one assistant's directory layout |
<skill-root>, <workspace>, and <output-dir> in examplesUse this skill for the capability described in this document.
Use this skill when the request matches the capability, constraints, and activation cues described below.
Follow the primary workflow, commands, and decision points documented in the sections below.
Use the examples and snippets already present in this document whenever they apply to the task.
Use any linked scripts, assets, reference files, and companion resources mentioned in this document.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.