Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Adaptyv Foundry API & SDK

Teaches Claude how to design, submit and retrieve protein experiments through the Adaptyv Bio Foundry API and Python SDK.

Web & APIIntermediate★ 46,134⑂ 4,181AI score 8/10Last updated: Sep 21, 2026

What it does

  • Documents the Foundry base URL, Bearer-token auth, and the rule to always read keys from ADAPTYV_API_KEY or a .env file instead of hardcoding them.
  • Shows both SDK usage patterns: the @lab.experiment decorator and the explicit FoundryClient client, including GitHub-only installation of adaptyv-sdk 0.1.0.
  • Maps experiment types (affinity, screening, thermostability, expression, fluorescence), the full status lifecycle from Draft to Done, cost estimation, submission, webhooks and results retrieval.
  • Covers list-endpoint s-expression filtering, sorting, pagination, error payloads with request_id, and Biscuit token attenuation/revocation.

Who it's for

  • Protein engineers and researchers with an Adaptyv Foundry account who want to order wet-lab assays programmatically.
  • ML / bioinformatics developers wiring a design→assay→data loop into an automated pipeline.
  • Not useful if you don't use Adaptyv's cloud lab.

Examples

  1. "Find the EGFR target and quote a BLI screening run for my 20 designs" → generates targets.list + experiments.cost_estimate code.
  2. "Build an unattended pipeline that skips draft, auto-accepts the quote, and notifies my webhook" → uses skip_draft, auto_accept_quote, webhook_url.
  3. "List all experiments created this year that are done and pull their results" → builds filter=and(gte(created_at,...),eq(status,done)).

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/adaptyv/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/adaptyv folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/adaptyv/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/adaptyv ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the skills repo: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Create the skills directory: mkdir -p ~/.claude/skills
  4. Copy just this skill: cp -r scientific-agent-skills/skills/adaptyv ~/.claude/skills/
  5. Confirm Python 3.10+ and install the SDK: uv pip install "git+https://github.com/adaptyvbio/adaptyv-sdk.git"
  6. Grab an API key from the foundry.adaptyvbio.com sidebar and put it in a project .env as ADAPTYV_API_KEY=... — never hardcode or commit it.
  7. Restart Claude Code and ask something like "submit a BLI screening experiment on Adaptyv" to trigger the skill.
View source on GitHub ↗License: MIT