A dedicated integration designed to automate protein experiment design, submission, and assay results retrieval using the Adaptyv Bio Foundry API and Python SDK.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install adaptyv
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install adaptyv using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Adaptyv Bio Foundry API skill bridges computational biology and physical wet-lab automated infrastructure, converting digital protein sequences into tangible experimental results in roughly 21 days. This tool enables developers and researchers to design sequences, evaluate targets, request instant cost estimates, and manage live experiments programmatically. By using this powerful integration from the Openclaw Skills registry, computational agents can drive automated laboratory processes directly from code.
Whether you are executing high-throughput screening or fine-tuning affinity measurements via BLI or SPR assays, this skill provides standard SDK workflows and robust API schemas. Incorporating Openclaw Skills into your automated discovery pipelines minimizes manual coordination overhead, accelerating experimental iterations and biological research.
Configure your local environment to interact with the Adaptyv Bio Foundry API. First, secure your credentials within a .env file:
export ADAPTYV_API_KEY="your_api_token_here"
export ADAPTYV_API_URL="https://foundry-api-public.adaptyvbio.com/api/v1"
Next, install the required SDK tool. If using uv, run:
uv add adaptyv-sdk
Or fallback to standard pip installation in Python environments:
pip install adaptyv-sdk
For rapid testing, you can authenticate and run a quick query using standard tools:
curl https://foundry-api-public.adaptyvbio.com/api/v1/targets?limit=3 -H "Authorization: Bearer $ADAPTYV_API_KEY"
Experiments require target associations and sequence lists depending on the assay type. The data supports structured sequences in simple or rich metadata formats:
| Parameter | Format / Syntax | Notes |
|---|---|---|
| Simple Sequence | {"seq1": "EVQL..."} |
Case-insensitive single-letter code formats. |
| Rich Sequence | {"seq1": {"aa_string": "EVQL...", "control": false, "metadata": {}}} |
Allows structured JSON metadata payloads. |
| Multi-Chain | "MVLS:EVQL" |
Uses a colon separator to bind multiple chains. |
| Type | Method | Measures | Requires Target |
|---|---|---|---|
affinity |
bli or spr |
KD, kon, koff kinetics | Yes |
screening |
bli or spr |
Yes/no binding | Yes |
thermostability |
— | Melting temperature (Tm) | No |
expression |
— | Expression yield | No |
fluorescence |
— | Fluorescence intensity | No |
@lab.experiment(...) to map inputs to physical assay orders.Loading
An AI-powered reconciliation assistant that parses, validates, and analyzes local Settlement Detail report files while offering natural-language domain Q&A.

An AI-powered historical toolkit that translates the history of the Lewis and Clark Expedition and Meriwether Lewis's leadership into actionable lessons.

An advanced Traditional Chinese Medicine (TCM) diagnostic and dietary therapy skill that equips AI agents with professional syndrome differentiation, nutritional recommendations, and wellness plans.

A secure, offline-first local billing event ingestor and normalization utility designed to run revenue and telemetry audits without exposing sensitive financial records to external cloud services.

A high-performance, cross-platform CLI tool designed to batch-convert PDF, DOCX, and PPTX documents into Markdown using the doc2md API.

An expert scikit-learn compatible Python toolkit for advanced time series machine learning tasks like forecasting, classification, clustering, and anomaly detection.








































