Skip to content
Get packs

PyLabRobot Lab Automation Planner

Plan and review lab-automation protocols offline, with a hard safety gate before any physical equipment runs.

Source Download skill
Repository
K-Dense-AI/scientific-agent-skills
Stars
55,780
Licence
MIT
Files
15 files

What it does

It teaches an AI agent to help write and review PyLabRobot code and protocol plans for lab liquid-handling robots. The agent can validate a protocol manifest, check deck layout for simple overlaps, check transfer tables, and produce a JSON simulation plan using software-only backends. It is built to refuse to drive real hardware automatically and requires a trained human to approve any live run.

Great for

  • Lab engineers drafting PyLabRobot protocols who want offline checks before touching a robot
  • Students learning liquid-handling workflows and deck layout in a safe software-only setting
  • Teams reviewing a transfer table or deck geometry before a supervised commissioning run

Skip it if

  • Directly controlling a physical liquid handler without a trained operator, since the skill itself says live execution must stay behind a human safety gate and its checks are not a motion planner or proof of safety
  • Clinical or hazardous-sample workflows that need validated, certified software, since simulation and bookkeeping do not prove liquid location or collision freedom

Try asking

  • “Validate my protocol manifest and tell me what is missing before a dry run”
  • “Check whether these plate and tip-rack positions overlap on the deck”
  • “Plan a 96-well transfer table from my CSV and flag volume or dead-volume problems”
  • “Generate an offline simulation plan for review with the chatterbox backend”
Step-by-step guide: how to use PyLabRobot Lab Automation PlannerInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 15 original files, the MIT licence and an attribution note.

    pylabrobot.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip pylabrobot.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip pylabrobot.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Provide a complete manifest with device model, tip type, volumes and heights up front, since the skill refuses to guess missing values
  • Treat the offline plan as a draft and have a qualified operator reconcile the physical deck before any live run
  • Run the bundled scripts from the repository root against the synthetic fixtures first to see the expected output

What's inside

  • assets/protocol-manifest.schema.json
  • references/analytical-equipment.md
  • references/hardware-backends.md
  • references/liquid-handling.md
  • references/material-handling.md
  • references/resources.md
  • references/review.md
  • references/visualization.md
  • scripts/__init__.py
  • scripts/_common.py
  • scripts/check_deck_geometry.py
  • scripts/generate_simulation_plan.py
  • scripts/inspect_backends.py
  • scripts/plan_transfers.py
  • SKILL.md

Redistributed unmodified from K-Dense-AI/scientific-agent-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.