M
Mutation Technology Publications
Guest
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.
For the full run from FASTQ to hit genes, the crispr-screen-pipeline workflow skill chains these together.
All 15 come with the Data & Science plugin, along with the rest of the 562 bioSkills:
For Codex CLI or another agent that supports the standard, clone the repo and copy
Each skill keeps its MIT license and an
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 |
|---|---|
| bagel-essentiality | Finds essential genes in Cas9 fitness screens with BAGEL2 Bayes factors |
| base-editing-analysis | Analyzes base-editing screens for variant function |
| batch-correction | Corrects batch effects with ComBat, RUV, SVA or control-sgRNA normalization |
| combinatorial-screens | Designs and analyzes paired-Cas9 and multiplexed Cas12a screens |
| copy-number-correction | Removes the gene-independent copy-number artifact in Cas9 screens |
| crispresso-editing | Quantifies editing outcomes (indels, HDR, base and prime edits) with CRISPResso2 |
| drugz-chemogenomic | Analyzes drug-modifier screens with drugZ |
| hit-calling | A decision tree for picking the right hit-calling method |
| in-vivo-screens | Designs and analyzes screens in tumor models, organoids and adoptive transfers |
| jacks-analysis | Runs JACKS to model per-sgRNA efficacy across screens |
| library-design | Designs sgRNA libraries for knockout, CRISPRi, CRISPRa and Cas12a |
| mageck-analysis | Runs MAGeCK from counts through RRA and MLE analysis |
| perturb-seq-analysis | Analyzes Perturb-seq, CROP-seq and ECCITE-seq single-cell screens |
| prime-editing-screens | Designs and analyzes pooled prime-editor screens for precise variants |
| screen-qc | 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:
Code:
/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.