API + Python SDK for ordering cell-free protein expression and binding assays. Submit sequences for expression (10–100 µg), measure binding affinity (KD) against targets, track status, and retrieve results programmatically — no wet-lab setup. Built for ML-guided directed evolution and antibody/nanobody optimization. Requires Adaptyv account and API key.
SkillScore100Maintained
Automatic
◆Research pack
Last verified 8/23/2026
What it changes
Passed 22 of 22 test cases with the skill, and 11 of 22 without it.
Without skill52%
With skill100%
Checks it passed that the model alone missed
Calls client.get_experiment_results('exp_12345').
Identifies project as the keyword parameter name.
Specifies 48 or 96 candidates per submission batch.
and 16 more in the full report
11 fixed12 passed either way0 still failing0 broke
Pass-rate lift
+48 pp
Tokens
+241%
Agent turns
0%
Response time
-33%
Model gemini-3.6-flashMeasured 8/23/2026v123 of 23 cases passed with skill · 22 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 10
Prompt
When querying past experiments using the Adaptyv Bio Python SDK, what client method is called to list experiments, and what keyword parameter filters by project name?
What was checked, without and with the skill
Checked
Without skill
With skill
Identifies list_experiments as the method name.
Passed
Passed
Identifies project as the keyword parameter name.
Missed
Passed
case-21 · gemini-3.6-flash · 8/23/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md451 linessingle file
Adaptyv Bio
Overview
Adaptyv Bio is a protein expression and characterization platform accessed via a REST API and Python SDK. Users submit protein sequences (antibodies, nanobodies, enzymes, binding proteins) and receive expressed protein along with binding affinity measurements (KD via biolayer interferometry) within days. The platform is designed for high-throughput directed evolution loops: generate candidate sequences (computationally or by library design) → order expression + assay via API → receive affinity data → retrain model or select top candidates → repeat. The SDK handles experiment submission, status polling, and result retrieval in Python.
When to Use
Screening computationally designed protein variants for experimental binding affinity validation
Running ML-guided directed evolution loops where in silico candidate generation alternates with wet-lab characterization
Ordering cell-free expression of nanobodies, antibodies, or binding domains without maintaining wet-lab infrastructure
Automating high-throughput protein characterization pipelines using the REST API
Integrating experimental affinity data (KD values) with computational models for Bayesian optimization of protein sequences
Validating ESM, AlphaFold, or docking predictions with experimental binding data
Use benchling-integration for LIMS-style sequence and plasmid management; use Adaptyv Bio instead when you need automated cell-free expression and affinity characterization without wet-lab setup
Prerequisites
Python packages: adaptyvbio, requests, pandas
Account: Adaptyv Bio account required; obtain API key from dashboard
Data requirements: protein sequence(s) in FASTA or plain string format; target protein specification
pip install adaptyvbio requests pandas
# Set API key as environment variable
export ADAPTYV_API_KEY="your_api_key_here"
Quick Start
import adaptyvbio as ab
import os
# Initialize client
client = ab.Client(api_key=os.environ["ADAPTYV_API_KEY"])
# List available experiment types
experiment_types = client.get_experiment_types()
for et in experiment_types: