GPTomics' bioSkills includes 15 MIT-licensed skills for pooled CRISPR screens. They cover library design, QC, batch and copy-number correction, hit calling with MAGeCK, BAGEL2, JACKS and drugZ, and specialized screens: base editing, prime editing, combinatorial, in vivo and Perturb-seq. The skills cite the papers behind each method, so the agent can explain its choices.
All 15 install with one command from Cuttlefish.MD, HackerNoon's license-checked skills marketplace. They follow the open Agent Skills standard, so they run in Claude Code, Codex CLI and 30+ other tools, and each is indexed in HackerNoon's SKILL.md Library.
The 15 CRISPR screen skills
| Skill | What it does |
|---|---|
| Finds essential genes in Cas9 fitness screens with BAGEL2 Bayes factors | |
| Analyzes base-editing screens for variant function | |
| Corrects batch effects with ComBat, RUV, SVA or control-sgRNA normalization | |
| Designs and analyzes paired-Cas9 and multiplexed Cas12a screens | |
| Removes the gene-independent copy-number artifact in Cas9 screens | |
| Quantifies editing outcomes (indels, HDR, base and prime edits) with CRISPResso2 | |
| Analyzes drug-modifier screens with drugZ | |
| A decision tree for picking the right hit-calling method | |
| Designs and analyzes screens in tumor models, organoids and adoptive transfers | |
| Runs JACKS to model per-sgRNA efficacy across screens | |
| Designs sgRNA libraries for knockout, CRISPRi, CRISPRa and Cas12a | |
| Runs MAGeCK from counts through RRA and MLE analysis | |
| Analyzes Perturb-seq, CROP-seq and ECCITE-seq single-cell screens | |
| Designs and analyzes pooled prime-editor screens for precise variants | |
| Checks library representation, Gini index, skew and replicate correlation |
For the full run from FASTQ to hit genes, the crispr-screen-pipeline workflow skill chains these together.
Install them
All 15 come with the Data & Science plugin, along with the rest of the 562 bioSkills:
/plugin marketplace add hackernoon/cuttlefish-agent-skills /plugin install data-science@cuttlefish For Codex CLI or another agent that supports the standard, clone the repo and copy plugins/data-science/skills/ into your agent's skills folder, such as .agents/skills/.
Each skill keeps its MIT license and an ATTRIBUTION.md crediting GPTomics and the source commit. Browse the full library at hackernoon.com/skills, and star Cuttlefish.MD on GitHub.
