Skip to content
Get packs

FlowKit Flow Cytometry Analysis

Apply gating strategies and FlowJo 10 workspaces to flow cytometry data in Python

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

What it does

Flow cytometry produces measurements for thousands of individual cells, and researchers sort them into populations by drawing 'gates' on plots. This skill teaches the agent to run that gating in Python with the FlowKit library: applying spillover compensation, logicle transforms, and hierarchical gates, then reporting event counts and percentages per population. It can also reproduce supported FlowJo 10 workspace analyses and includes a helper script that writes a CSV report and a provenance file with input hashes and package versions.

Great for

  • Researchers who want reproducible gate counts and population percentages from FCS files
  • Analysts reproducing a FlowJo 10 workspace analysis in Python and checking agreement
  • Developers building batch gating pipelines with explicit input files

Skip it if

  • Clinical or diagnostic decisions: the skill was tested only on synthetic data and its thresholds are teaching values, not biological validation
  • Simple FCS metadata inspection or file repair, where the skill itself points to FlowIO instead
  • Assuming FlowJo parity without checking: it supports only a subset of FlowJo 10 features and import success does not establish agreement

Try asking

  • “Apply my GatingML strategy gates.xml to sample.fcs and give me count and percent per population”
  • “Reproduce the 'Study' group from my FlowJo workspace study.wsp across these FCS files”
  • “Build a Python gating strategy with logicle transform and compensation for my panel and export the results”
  • “Check my gate report for empty parent populations and duplicate sample IDs before I trust the numbers”
Step-by-step guide: how to use FlowKit Flow Cytometry AnalysisInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 4 original files, the MIT licence and an attribution note.

    flowkit.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

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

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip flowkit.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

  • Supply your own validated compensation controls, gate thresholds and FMO/negative controls; do not rely on the demonstration values in the examples
  • Supply every FCS file in the selected FlowJo group, and use $FIL sample IDs unless file basenames match your analysis definition
  • Compare a few representative results against FlowJo yourself before relying on the output, and keep biological replicates separate from events

What's inside

  • references/compensation-and-gating.md
  • references/workspaces-and-results.md
  • scripts/analyze_gates.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.