Protein Design Skills — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Protein Design Skills (Plugin) 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.
<p align="center"> <img src="assets/hero_animation.svg" width="560" alt="Protein Design Skills"> </p>
<p align="center"> <strong>24 Claude Code skills for computational protein design</strong> </p>
<p align="center"> <a href="docs/getting-started.md">Getting started</a> • <a href="docs/skills.md">Skills</a> • <a href="docs/standard-pipeline.md">Pipeline</a> </p>
/plugin marketplace add adaptyvbio/protein-design-skills
/plugin install adaptyv@protein-design-skills<p align="center"> <img src="assets/setup_steps.svg" width="600" alt="Setup steps"> </p>
<p align="center"> <img src="assets/skill_categories.svg" width="550" alt="Skill categories"> </p>
<p align="center"> <img src="assets/pipeline_flow.svg" width="550" alt="Pipeline flow"> </p>
"Design a binder for PDB 1ALU"
Claude will pick the right skills for the target (for example BoltzGen → Chai → QC, or RFdiffusion → ProteinMPNN → Chai → QC).
The easiest way to create a new skill is with Claude Code:
/skill skill-creatorThis uses Anthropic's skill-creator to guide you through the process.
See CONTRIBUTING.md for detailed guidelines.
MIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.