Claude draws a birb
SaferSkills independently audited claude-draws-a-birb (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.
An experiment where Claude (Anthropic's AI) attempts to draw a European Robin in pure HTML + SVG, using a reference photo found on Google Images.
tldr
Hosted on GitHub Pages: View the gallery
| Page | Description |
|---|---|
index.html | Landing page with links to each version |
freehand.html | First attempt — freehand SVG drawn from scratch |
traced.html | Second attempt — SVG traced over the reference photo coordinates |
lessons-learnt.html | What worked, what didn't, and technical notes |
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.