Skip to main content
ClaudeWave
Skill237 repo starsupdated 1mo ago

adaptyv

Adaptyv is a cloud laboratory platform that automates protein testing and validation by submitting sequences via API for experimental assays including binding, expression, thermostability, and enzyme activity measurements, with results delivered in approximately 21 days. Use this skill when designing proteins and requiring wet-lab validation, optimizing sequences computationally before submission, tracking experiment status, or managing protein design workflows integrated with actual laboratory testing.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/Microck/ordinary-claude-skills /tmp/adaptyv && cp -r /tmp/adaptyv/skills_all/claude-scientific-skills/scientific-skills/adaptyv ~/.claude/skills/adaptyv
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# Adaptyv

Adaptyv is a cloud laboratory platform that provides automated protein testing and validation services. Submit protein sequences via API or web interface and receive experimental results in approximately 21 days.

## Quick Start

### Authentication Setup

Adaptyv requires API authentication. Set up your credentials:

1. Contact support@adaptyvbio.com to request API access (platform is in alpha/beta)
2. Receive your API access token
3. Set environment variable:

```bash
export ADAPTYV_API_KEY="your_api_key_here"
```

Or create a `.env` file:

```
ADAPTYV_API_KEY=your_api_key_here
```

### Installation

Install the required package using uv:

```bash
uv pip install requests python-dotenv
```

### Basic Usage

Submit protein sequences for testing:

```python
import os
import requests
from dotenv import load_dotenv

load_dotenv()

api_key = os.getenv("ADAPTYV_API_KEY")
base_url = "https://kq5jp7qj7wdqklhsxmovkzn4l40obksv.lambda-url.eu-central-1.on.aws"

headers = {
    "Authorization": f"Bearer {api_key}",
    "Content-Type": "application/json"
}

# Submit experiment
response = requests.post(
    f"{base_url}/experiments",
    headers=headers,
    json={
        "sequences": ">protein1\nMKVLWALLGLLGAA...",
        "experiment_type": "binding",
        "webhook_url": "https://your-webhook.com/callback"
    }
)

experiment_id = response.json()["experiment_id"]
```

## Available Experiment Types

Adaptyv supports multiple assay types:

- **Binding assays** - Test protein-target interactions using biolayer interferometry
- **Expression testing** - Measure protein expression levels
- **Thermostability** - Characterize protein thermal stability
- **Enzyme activity** - Assess enzymatic function

See `reference/experiments.md` for detailed information on each experiment type and workflows.

## Protein Sequence Optimization

Before submitting sequences, optimize them for better expression and stability:

**Common issues to address:**
- Unpaired cysteines that create unwanted disulfides
- Excessive hydrophobic regions causing aggregation
- Poor solubility predictions

**Recommended tools:**
- NetSolP / SoluProt - Initial solubility filtering
- SolubleMPNN - Sequence redesign for improved solubility
- ESM - Sequence likelihood scoring
- ipTM - Interface stability assessment
- pSAE - Hydrophobic exposure quantification

See `reference/protein_optimization.md` for detailed optimization workflows and tool usage.

## API Reference

For complete API documentation including all endpoints, request/response formats, and authentication details, see `reference/api_reference.md`.

## Examples

For concrete code examples covering common use cases (experiment submission, status tracking, result retrieval, batch processing), see `reference/examples.md`.

## Important Notes

- Platform is currently in alpha/beta phase with features subject to change
- Not all platform features are available via API yet
- Results typically delivered in ~21 days
- Contact support@adaptyvbio.com for access requests or questions
- Suitable for high-throughput AI-driven protein design workflows
activitypub-testingSkill

Testing patterns for PHPUnit and Playwright E2E tests. Use when writing tests, debugging test failures, setting up test coverage, or implementing test patterns for ActivityPub features.

add-uint-supportSkill

Add unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions enabling unsigned types, barebones unsigned types, or uint support.

Agent DevelopmentSkill

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

AgentDB Advanced FeaturesSkill

Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications.

AgentDB Learning PluginsSkill

Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.

AgentDB Memory PatternsSkill

Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.

AgentDB Performance OptimizationSkill

Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.

AgentDB Vector SearchSkill

Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.