Agent skill

Tooluniverse Protein Therapeutic Design

Design novel protein therapeutics (binders, enzymes, scaffolds) using AI-guided de novo design.

No licenceAuto-check passedResearch & Science

Install Tooluniverse Protein Therapeutic Design

skills CLI

$ npx skills add wu-yc/LabClaw --skill tooluniverse-protein-therapeutic-design -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install wu-yc/LabClaw tooluniverse-protein-therapeutic-design --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/wu-yc/LabClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/pharma/tooluniverse-protein-therapeutic-design .claude/skills/tooluniverse-protein-therapeutic-design && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "tooluniverse-protein-therapeutic-design" agent skill from https://github.com/wu-yc/LabClaw/tree/main/skills/pharma/tooluniverse-protein-therapeutic-design into .claude/skills/tooluniverse-protein-therapeutic-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tooluniverse-protein-therapeutic-design", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/wu-yc/LabClaw/tree/main/skills/pharma/tooluniverse-protein-therapeutic-design

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add wu-yc/LabClaw --skill tooluniverse-protein-therapeutic-design -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install wu-yc/LabClaw tooluniverse-protein-therapeutic-design --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/wu-yc/LabClaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/pharma/tooluniverse-protein-therapeutic-design .agents/skills/tooluniverse-protein-therapeutic-design && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "tooluniverse-protein-therapeutic-design" agent skill from https://github.com/wu-yc/LabClaw/tree/main/skills/pharma/tooluniverse-protein-therapeutic-design into .agents/skills/tooluniverse-protein-therapeutic-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tooluniverse-protein-therapeutic-design", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add wu-yc/LabClaw --skill tooluniverse-protein-therapeutic-design -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install wu-yc/LabClaw tooluniverse-protein-therapeutic-design --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/wu-yc/LabClaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/pharma/tooluniverse-protein-therapeutic-design .cursor/skills/tooluniverse-protein-therapeutic-design && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "tooluniverse-protein-therapeutic-design" agent skill from https://github.com/wu-yc/LabClaw/tree/main/skills/pharma/tooluniverse-protein-therapeutic-design into .cursor/skills/tooluniverse-protein-therapeutic-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tooluniverse-protein-therapeutic-design", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/wu-yc/LabClaw.git --path skills/pharma/tooluniverse-protein-therapeutic-design

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add wu-yc/LabClaw --skill tooluniverse-protein-therapeutic-design -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install wu-yc/LabClaw tooluniverse-protein-therapeutic-design --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/wu-yc/LabClaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/pharma/tooluniverse-protein-therapeutic-design .gemini/skills/tooluniverse-protein-therapeutic-design && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "tooluniverse-protein-therapeutic-design" agent skill from https://github.com/wu-yc/LabClaw/tree/main/skills/pharma/tooluniverse-protein-therapeutic-design into .gemini/skills/tooluniverse-protein-therapeutic-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tooluniverse-protein-therapeutic-design", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install wu-yc/LabClaw tooluniverse-protein-therapeutic-design

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add wu-yc/LabClaw --skill tooluniverse-protein-therapeutic-design -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/wu-yc/LabClaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/pharma/tooluniverse-protein-therapeutic-design .github/skills/tooluniverse-protein-therapeutic-design && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "tooluniverse-protein-therapeutic-design" agent skill from https://github.com/wu-yc/LabClaw/tree/main/skills/pharma/tooluniverse-protein-therapeutic-design into .github/skills/tooluniverse-protein-therapeutic-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tooluniverse-protein-therapeutic-design", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add wu-yc/LabClaw --skill tooluniverse-protein-therapeutic-design -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install wu-yc/LabClaw tooluniverse-protein-therapeutic-design --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/wu-yc/LabClaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/pharma/tooluniverse-protein-therapeutic-design .opencode/skills/tooluniverse-protein-therapeutic-design && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "tooluniverse-protein-therapeutic-design" agent skill from https://github.com/wu-yc/LabClaw/tree/main/skills/pharma/tooluniverse-protein-therapeutic-design into .opencode/skills/tooluniverse-protein-therapeutic-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tooluniverse-protein-therapeutic-design", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: tooluniverse-protein-therapeutic-design
GitHub stars: 1.1k
Used in: 2 other repos
Token cost: ~4.4k tokens
SKILL.md length: 613 words
Files: 1
Skills in repo: 68
Repo updated: Mar 19, 2026
First seen: Oct 7, 2026
Licence: None found

At a glance

Design novel protein therapeutics (binders, enzymes, scaffolds) using AI-guided de novo design.

Works in 8 steps: Report-First Approach (MANDATORY) → Design Documentation (MANDATORY) → Target → …
Asked to design protein binders
SKILL.md covers When to Use, Critical Workflow Requirements, Phase 0: Tool Verification and Workflow Overview, plus 5 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Tooluniverse Protein Therapeutic Design is an agent skill from wu-yc/LabClaw. 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.

Its SKILL.md is about 4.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Protein structure and design, Project scaffolding and Creative writing and fiction. The repository describes itself as: LabClaw – Operating Layer for LabOS (Stanford-Princeton AI Co-Scientists).

When your agent uses it

Asked to design protein binders
Therapeutic proteins
Engineer protein function

Example prompts

“/tooluniverse-protein-therapeutic-design”

Requirements

Python 3

Workflow steps

8 steps, taken from the step headings in SKILL.md.

Report-First Approach (MANDATORY)
Design Documentation (MANDATORY)
Target
Backbones
Sequences
Validation
Developability
Deliverables

What it can do on your machine

Read from SKILL.md and the folder at commit df37802. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and python).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Tooluniverse Protein Therapeutic Design loads about 4.4k tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 613 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~85
When it runs · the whole SKILL.md, loaded when a task matches: ~4.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 613 words (~4,433 tokens).

“AI-guided de novo protein design using RFdiffusion backbone generation, ProteinMPNN sequence optimization, and structure validation for therapeutic protein development.”

— opening of SKILL.md by wu-yc

name: tooluniverse-protein-therapeutic-design

Outline of SKILL.md

Therapeutic Protein Designer
When to Use
Critical Workflow Requirements
1. Report-First Approach (MANDATORY)
2. Design Documentation (MANDATORY)
Phase 0: Tool Verification
NVIDIA NIM Tools Required
Parameter Verification
Workflow Overview
Phase 1: Target Characterization
1.1 Get Target Structure
1.1b EMDB for Membrane Proteins (NEW)
1.2 Identify Binding Epitope
1.3 Output for Report
Phase 2: Backbone Generation
2.1 RFdiffusion Design
2.2 Design Modes
2.3 Output for Report
Phase 3: Sequence Design
3.1 ProteinMPNN Design
3.2 Sampling Parameters
3.3 Output for Report
Phase 4: Structure Validation
4.1 ESMFold Validation
4.2 Validation Criteria
4.3 Output for Report
Phase 5: Developability Assessment
5.1 Aggregation Propensity
5.2 Developability Metrics
5.3 Output for Report

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/pharma/tooluniverse-protein-therapeutic-design of wu-yc/LabClaw.

Open the folder on GitHubat commit df37802

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in wu-yc/LabClaw, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Tooluniverse Protein Therapeutic Design next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Tooluniverse Protein Therapeutic Design compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Tooluniverse Protein Therapeutic Design this skillwu-yc/LabClaw	1.1k	2 repos	~4.4k	Automated safety check: Pass	None	6 mo ago
Rfdiffusionadaptyvbio/protein-design-skills	164	3 repos	~2.3k	Automated safety check: Pass	MIT	4 mo ago
Complexa DesignNVIDIA-BioNeMo/bionemo-agent-toolkit	479	—	~4.1k	Automated safety check: Notes	Custom licence	yesterday
RfdiffusionPKU-YuanGroup/OpenAI4S	622	—	~2.2k	Automated safety check: Pass	MIT	yesterday
Bio Structural Biology Modern Structure PredictionFreedomIntelligence/OpenClaw-Medical-Skills	3.1k	1 repos	~2.5k	Automated safety check: Pass	None	2 mo ago
Esmdavila7/claude-code-templates	33k	9 repos	~2.6k	Automated safety check: Warn	MIT	today

Similar skills

Rfdiffusion
adaptyvbio/protein-design-skills
Generate protein backbones using RFdiffusion, a diffusion-based generative model for de novo protein structure generation.
164 GitHub starsUsed in 3 repos~2.3k tokens
Research & ScienceAuto-check passed
Complexa Design
NVIDIA-BioNeMo/bionemo-agent-toolkit
End-to-end Proteina-Complexa design pipeline driver. An agent skill from NVIDIA-BioNeMo/bionemo-agent-toolkit.
479 GitHub stars~4.1k tokensUpdated yesterday
Research & ScienceAuto-check: notes
Rfdiffusion
PKU-YuanGroup/OpenAI4S
Generate de novo protein backbones with RFdiffusion for protein-target binders, hotspot-conditioned interfaces, motif scaffolding, partial diffusion, or symmetric assemblies.
622 GitHub stars~2.2k tokensUpdated yesterday
Research & ScienceAuto-check passed
Bio Structural Biology Modern Structure Prediction
FreedomIntelligence/OpenClaw-Medical-Skills
Predict protein structures using modern ML models including AlphaFold3, ESMFold, Chai-1, and Boltz-1.
3.1k GitHub starsUsed in 1 repo~2.5k tokens
Research & ScienceAuto-check passed
Esm
davila7/claude-code-templates
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and…
33k GitHub starsUsed in 9 repos~2.6k tokens
AI & LLM EngineeringAuto-check: warnings
Rfdiffusion Nim
NVIDIA/skills
Official
Run RFDiffusion protein backbone design via NVIDIA NIM. An agent skill from NVIDIA/skills.
3.6k GitHub starsUsed in 1 repo~1.3k tokens
DevOps & CloudAuto-check: notes

More from wu-yc/LabClaw

All 68 skills in this repo

Tooluniverse Chemical Compound Retrieval
wu-yc/LabClaw
Retrieves chemical compound information from PubChem and ChEMBL with disambiguation, cross-referencing, and quality assessment.
1.1k GitHub starsUsed in 2 repos~2.3k tokens
Auto-check passed
Tooluniverse Clinical Guidelines
wu-yc/LabClaw
Search and retrieve clinical practice guidelines across 12+ authoritative sources including NICE, WHO, ADA, AHA/ACC, NCCN, SIGN, CPIC, CMA, CTFPHC, GIN, MAGICapp, PubMed, EuropePMC, TRIP, and…
1.1k GitHub starsUsed in 2 repos~4.9k tokens
Auto-check passed
Tooluniverse Disease Research
wu-yc/LabClaw
Generate comprehensive disease research reports using 100+ ToolUniverse tools.
1.1k GitHub starsUsed in 2 repos~4.7k tokens
Auto-check passed
Tooluniverse Drug Repurposing
wu-yc/LabClaw
Identify drug repurposing candidates using ToolUniverse for target-based, compound-based, and disease-driven strategies.
1.1k GitHub starsUsed in 2 repos~4.4k tokens
Auto-check passed
Tooluniverse Expression Data Retrieval
wu-yc/LabClaw
Retrieves gene expression and omics datasets from ArrayExpress and BioStudies with gene disambiguation, experiment quality assessment, and structured reports.
1.1k GitHub starsUsed in 2 repos~2.6k tokens
Auto-check passed
Tooluniverse Gene Enrichment
wu-yc/LabClaw
Perform comprehensive gene enrichment and pathway analysis using gseapy (ORA and GSEA), PANTHER, STRING, Reactome, and 40+ ToolUniverse tools.
1.1k GitHub starsUsed in 2 repos~4k tokens
Auto-check passed

Questions about Tooluniverse Protein Therapeutic Design

What does Tooluniverse Protein Therapeutic Design do?

Design novel protein therapeutics (binders, enzymes, scaffolds) using AI-guided de novo design. Tooluniverse Protein Therapeutic Design is an agent skill from wu-yc/LabClaw. Design novel protein therapeutics (binders, enzymes, scaffolds) using AI-guided de novo design.

When should I use Tooluniverse Protein Therapeutic Design?

Tooluniverse Protein Therapeutic Design fits situations like: asked to design protein binders; therapeutic proteins; engineer protein function.

How do I install Tooluniverse Protein Therapeutic Design in Claude Code?

Run `npx skills add wu-yc/LabClaw --skill tooluniverse-protein-therapeutic-design -a claude-code`. Or copy the skill folder (skills/pharma/tooluniverse-protein-therapeutic-design in wu-yc/LabClaw) into .claude/skills/tooluniverse-protein-therapeutic-design in your project. Claude Code loads it when a task matches its description.

How do I install Tooluniverse Protein Therapeutic Design in Codex?

Run `npx skills add wu-yc/LabClaw --skill tooluniverse-protein-therapeutic-design -a codex`. Or copy the skill folder (skills/pharma/tooluniverse-protein-therapeutic-design in wu-yc/LabClaw) into .agents/skills/tooluniverse-protein-therapeutic-design in your project. Codex loads it when a task matches its description.

Can I use Tooluniverse Protein Therapeutic Design in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add wu-yc/LabClaw --skill tooluniverse-protein-therapeutic-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tooluniverse-protein-therapeutic-design, .gemini/skills/tooluniverse-protein-therapeutic-design, .github/skills/tooluniverse-protein-therapeutic-design and .opencode/skills/tooluniverse-protein-therapeutic-design in your project.

What does Tooluniverse Protein Therapeutic Design need to run?

SKILL.md names no scripts, command-line tools or credentials: Tooluniverse Protein Therapeutic Design is instructions for the agent only. Our summary lists: Python 3.

Does Tooluniverse Protein Therapeutic Design access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Tooluniverse Protein Therapeutic Design safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Tooluniverse Protein Therapeutic Design use?

No licence was found for Tooluniverse Protein Therapeutic Design or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Tooluniverse Protein Therapeutic Design use?

About 4.4k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Tooluniverse Protein Therapeutic Design?

Skills that share tags, products or a category with Tooluniverse Protein Therapeutic Design: Rfdiffusion (adaptyvbio/protein-design-skills, 164 stars), Complexa Design (NVIDIA-BioNeMo/bionemo-agent-toolkit, 479 stars), Rfdiffusion (PKU-YuanGroup/OpenAI4S, 622 stars) and Bio Structural Biology Modern Structure Prediction (FreedomIntelligence/OpenClaw-Medical-Skills, 3.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tooluniverse Protein Therapeutic Design?

wu-yc (a GitHub user) maintains it in wu-yc/LabClaw, which has 1,055 GitHub stars. The repository holds 68 skills in this directory. The repository was last updated on March 19, 2026.

Source: wu-yc/LabClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Tooluniverse Protein Therapeutic Design

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Files

Used in 2 other repositories

Compare with similar skills

Similar skills

More from wu-yc/LabClaw

Related

Questions about Tooluniverse Protein Therapeutic Design