protein-design-skills — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by adaptyvbio · Claude Skill · ★ 162

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is protein-design-skills safe to install? View the security audit →

About protein-design-skills

24 Claude Code skills for computational protein design Getting started • Skills • Pipeline Install Setup (first time) → Getting started Skills → View all 24 skills Pipeline → Standard pipeline Quick start "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). Links Getting started Skills Standard pipeline Compute setup Contributing Contributing Creating a new skill The easiest way to create a new skill is with Claude Code:

agent-skillsclaude-codeprotein-designprotein-engineering

Quick Facts

Stars162
Forks21
CategoryClaude Skill
LicenseMIT
Quality Score65.5858442738478/100
Open Issues2
Last Updated2026-06-11
Created2026-01-15
Platformsclaude-code
Est. Tokens~13k

Compatible Skills

These tools work well together with protein-design-skills for enhanced workflows:

  • design-system-ops — semantic(0.65)+complementary+similar_pop+shared_platform (58%)
  • cc-polymath — semantic(0.51)+complementary+similar_pop+shared_platform (53%)
  • skills — semantic(0.49)+complementary+similar_pop+shared_platform (52%)
  • skills_collection — semantic(0.47)+complementary+similar_pop+shared_platform (51%)
  • reverse-skills — semantic(0.45)+complementary+similar_pop+shared_platform (51%)

protein-design-skills alternative? Top 6 similar tools

Looking for a protein-design-skills alternative? If you're comparing protein-design-skills with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • awesome-bio-agent-skills by BioTender-max · ⭐ 140

    A curated collection of AI agent skills for biomedical research, covering genomics, proteomics, single-cell an

  • digital-marketing-pro by indranilbanerjee · ⭐ 795

    An open-source AI marketing operating system for strategy, SEO, AEO/GEO, paid media, content, CRM, and analyti

  • comfyui-mcp by artokun · ⭐ 778

    Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video

  • ai-skills by sanjay3290 · ⭐ 422

    24 cross-platform agent skills for Claude Code, Cursor, Codex & Gemini CLI — databases, messaging, research, T

  • mcp-odoo by tuanle96 · ⭐ 366

    Odoo MCP for AI agents — 41 tools, gated writes, multi-instance. Free hosted: ERPipe → mcp.erpipe.com

  • claudepro-directory by JSONbored · ⭐ 217

    HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Frequently Asked Questions

What is protein-design-skills?

protein-design-skills is Claude Code skills for protein design. It is categorized as a Claude Skill with 162 GitHub stars.

How do I install or use protein-design-skills?

You can find installation instructions and usage details in the protein-design-skills GitHub repository at github.com/adaptyvbio/protein-design-skills. The project has 162 stars and 21 forks, indicating an active community.

What license does protein-design-skills use?

protein-design-skills is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to protein-design-skills?

The top alternatives to protein-design-skills on Agent Skills Hub include awesome-bio-agent-skills, digital-marketing-pro, comfyui-mcp. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Claude Skill tools