SCI Skills

EN Index
Data & ReproProtein Structure & DesignFreedomIntelligence/OpenClaw-Medical-SkillsData & Reproduction
TO

tooluniverse-protein-therapeutic-design

Maintainer FreedomIntelligence · Last updated April 1, 2026

Design novel protein therapeutics (binders, enzymes, scaffolds) using AI-guided de novo design. Uses RFdiffusion for backbone generation, ProteinMPNN for sequence design, ESMFold/AlphaFold2 for validation. Use when asked to design protein binders, therapeutic proteins, or engineer protein function.

OpenClawNanoClawAnalysisReproductiontooluniverse-protein-therapeutic-design🏥 medical & clinicalmedical toolsdesign

Original source

FreedomIntelligence/OpenClaw-Medical-Skills

https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills/tree/main/skills/tooluniverse-protein-therapeutic-design

Maintainer
FreedomIntelligence
License
MIT
Last updated
April 1, 2026

Skill Snapshot

Key Details From SKILL.md

2 min

Key Notes

  • AI-guided de novo protein design using RFdiffusion backbone generation, ProteinMPNN sequence optimization, and structure validation for therapeutic protein development.
  • KEY PRINCIPLES: 1. Structure-first design - Generate backbone geometry before sequence 2. Target-guided - Design binders with target structure in mind 3. Iterative validation - Predict structure to validate designs 4. Developability-aware - Consider aggregation, immunogenicity, expression 5. Evidence-graded - Grade designs by confidence metrics 6. Actionable output - Provide sequences ready for experimental testing 7. English-first queries - Always use English terms in tool calls (protein names, target names), even if the user writes in another language. Only try original-language terms as a fallback. Respond in the user's language.

Source Doc

Excerpt From SKILL.md

When to Use

Apply when user asks:

  • "Design a protein binder for [target]"
  • "Create a therapeutic protein against [protein/epitope]"
  • "Design a protein scaffold with [property]"
  • "Optimize this protein sequence for [function]"
  • "Design a de novo enzyme for [reaction]"
  • "Generate protein variants for [target binding]"

1. Report-First Approach (MANDATORY)

  1. Create the report file FIRST:

    • File name: [TARGET]_protein_design_report.md
    • Initialize with section headers
    • Add placeholder: [Designing...]

  2. Progressively update as designs are generated

  3. Output separate files:

    • [TARGET]_designed_sequences.fasta - All designed sequences
    • [TARGET]_top_candidates.csv - Ranked candidates with metrics

2. Design Documentation (MANDATORY)

Every design MUST include:

Use cases

  • Use when asked to design protein binders, therapeutic proteins, or engineer protein function.

Not for

  • Do not rely on this catalog entry alone for installation or maintenance details.

Related skills

Related skills

Back to directory
AD
Data & ReproProtein Structure & Design

Adaptyv

Adaptyv is a cloud laboratory platform that provides automated protein testing and validation services. Submit protein sequences via API or…

Claude CodeOpenClawAnalysis
K-Dense-AI/claude-scientific-skillsView
AL
Data & ReproProtein Structure & Design

alphafold

Validate protein designs using AlphaFold2 structure prediction. Use this skill when: (1) Validating designed sequences fold correctly, (2) P…

OpenClawNanoClawAnalysis
FreedomIntelligence/OpenClaw-Medical-SkillsView
AL
Data & ReproProtein Structure & Design

AlphaFold DB

AlphaFold DB is a public repository of AI-predicted 3D protein structures for over 200 million proteins, maintained by DeepMind and EMBL-EBI…

Claude CodeOpenClawAnalysis
K-Dense-AI/claude-scientific-skillsView
AN
Data & ReproProtein Structure & Design

antibody-design-agent

Antibody design: epitope mapping, CDR engineering, bispecific construction.

OpenClawNanoClawAnalysis
FreedomIntelligence/OpenClaw-Medical-SkillsView