Bio Research Toolkit
Research skill, available on Zeplik
Bio Research Toolkit is a ready-to-run research skill on Zeplik. Not for literature research (use deep-research). Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer.
The Bio Research Toolkit skill loads automatically when your request matches it, or you can invoke it directly by typing /bio-research-toolkit in any chat. It works with attachments, connectors, and any model that supports the task, so you get the same expert method every time without setting anything up.
What the Bio Research Toolkit skill can do
- Run single-cell RNA-seq QC with MAD-based filtering and scverse best practices
- Build and train scvi-tools deep models for integration, batch correction, and label transfer
- Deploy nf-core Nextflow pipelines like rnaseq, sarek, and atacseq with samplesheets and configs
- Convert laboratory instrument data into Allotrope ASM format with field mapping guidance
Try these prompts on Zeplik
Pick a prompt to open it in the Zeplik app. If you are not signed in yet, your prompt is waiting for you the moment you do.
How the Bio Research Toolkit skill works
/bio-research-toolkit
Umbrella skill for computational-biology research engineering: single-cell RNA-seq quality control, deep-learning single-cell modeling with scvi-tools, nf-core Nextflow pipeline deployment, laboratory instrument-to-Allotrope data conversion, and systematic scientific problem selection. The user describes their data, pipeline, or research decision; deliver runnable analysis steps, code, and configs in the chat. For general biomedical literature search and synthesis use deep-research; for one-off tabular dataset analysis use analyze-dataset.
Dispatch table
Pick the reference file(s) that match the request, read them, then answer. Read at most 2-3 files per turn.
| Topic | Read |
|---|---|
| Single-cell RNA-seq QC: scverse best practices, MAD filtering, plots | references/single-cell-rna-qc.md (+ --scverse_qc_guidelines.md) |
| scvi-tools deep models: scVI/scANVI/totalVI/PeakVI/MultiVI/DestVI/veloVI, integration, batch correction, label transfer | references/scvi-tools.md (+ --scrna_integration.md, --batch_correction_sysvi.md, --label_transfer.md, --scarches_mapping.md, --citeseq_totalvi.md, --atac_peakvi.md, --multiome_multivi.md, --spatial_deconvolution.md, --rna_velocity_velovi.md, --data_preparation.md, --environment_setup.md, --troubleshooting.md) |
| nf-core Nextflow pipelines: rnaseq, sarek, atacseq, GEO/SRA acquisition, samplesheets | references/nextflow-development.md (+ --pipelines-rnaseq.md, --pipelines-sarek.md, --pipelines-atacseq.md, --geo-sra-acquisition.md, --installation.md, --troubleshooting.md) |
| Instrument data to Allotrope ASM: parsing, flattening, field classification, LIMS handoff | references/instrument-data-to-allotrope.md (+ --asm_schema_overview.md, --flattening_guide.md, --field_classification_guide.md, --supported_instruments.md) |
| Scientific problem selection: idea pitching, risk assessment, decision trees, project troubleshooting | references/scientific-problem-selection.md (+ --01-intuition-pumps.md through --09-meta-framework.md) |
How to work
- Identify the task class: QC, deep modeling, pipeline run, data conversion, or research strategy. Establish the input format (h5ad/h5, FASTQ, GEO/SRA accession, instrument file) and the goal. Ask for the missing detail rather than guessing scale or species.
- Read the matching reference file(s) from the table above before answering. Read at most 2-3 files per turn.
- Deliver runnable artifacts -- QC commands, scvi-tools training code, Nextflow configs and samplesheets, ASM conversion code -- with a short rationale, matching the user's naming and conventions when they paste existing code.
- Confirm decision points the source material flags (genome build, sample subset, filtering thresholds, ambiguous ASM field mappings) with the user instead of guessing.
- Route out when the request is not computational biology: general literature search and synthesis goes to deep-research, plain tabular dataset exploration to analyze-dataset.
Usage
/bio-research-toolkit $ARGUMENTS
How to use the Bio Research Toolkit skill
Sign in to Zeplik
Create a free Zeplik account or sign in. New accounts start with free credits, so you can try the Bio Research Toolkit skill right away.
Describe your research task
Ask in plain language, or type /bio-research-toolkit to invoke the skill directly. Zeplik recognizes the Bio Research Toolkit skill and applies its method.
Review and refine the result
Zeplik returns a clear, structured answer. Ask follow-ups in the same chat to refine it or take the next step.
Source and credit
- Author
- anthropic
- License
- Apache-2.0
Adapted from the open-source anthropics/knowledge-work-plugins project and tuned to run natively on Zeplik. View source on GitHub.
Frequently asked questions
- What is the Bio Research Toolkit skill?
- Bio Research Toolkit is a ready-to-run research skill on Zeplik. Not for literature research (use deep-research). Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer.
- How do I use Bio Research Toolkit on Zeplik?
- Sign in to Zeplik and ask in plain language, or type /bio-research-toolkit in any chat to invoke it directly. The skill applies its method and returns a result you can refine in the same conversation.
- Which AI model does the Bio Research Toolkit skill use?
- Any model you choose. Zeplik works across every model in one chat, so the Bio Research Toolkit skill runs on your preferred model for the task.
- Where does the Bio Research Toolkit skill come from?
- The Bio Research Toolkit skill is adapted from the open-source anthropics/knowledge-work-plugins project (Apache-2.0) and tuned to run natively on Zeplik. The original source is linked on this page.
- How much does the Bio Research Toolkit skill cost?
- Using the skill is free to start. You only spend Zeplik credits when the assistant runs, and new accounts begin with free credits.
Related research skills
- Academic PublishingAcademic publishing workflows — citation/reference management, LaTeX research posters, and venue templates with submission requirements. Use for "manage citations" or "format for a venue / make a poster"; for the writing itself see research-writing.
- Cheminformatics ToolkitsCheminformatics and molecular modeling — RDKit/Datamol molecular handling, DeepChem molecular ML, COBRApy metabolic modeling, Pymatgen materials, matchms/pyOpenMS mass spectrometry. Use for "work with molecules/chemistry data"; for genomics see genomics-toolkits.
- Clinical WritingClinical and medical document generation — clinical decision-support docs, clinical/case reports (CARE guidelines), and focused treatment plans in LaTeX/PDF. Use for "write a clinical report/treatment plan/CDS doc"; for research manuscripts see research-writing.
- Competitive BriefUse for competitor research or a competitive analysis -- 'compare us against X', 'build a battlecard for sales', 'competitor Y just launched Z, what does it mean for us' -- producing a positioning/messaging comparison with gaps, opportunities, threats. Not for general market reports (use deep-research).
- Deep Research ReportsUse for a long, multi-step, sourced research report -- market analysis, competitive landscaping, literature review, due diligence: 'do deep research on X', 'write a full report with citations'. Plans, searches, and synthesizes autonomously. Not for a quick look-up or short synthesis (use research).
- Fact CheckerVerify claims in supplied text or a question - decompose into checkable claims, verify with sources, return verdicts with confidence and citations. Use when the user asks is this true, fact check this, verify, or pastes a viral post or article to vet. Not for broad topic research (use research).
More on Zeplik
Try Bio Research Toolkit on Zeplik
Every model, one chat. Bring the Bio Research Toolkit skill into your next conversation and let the assistant do the work.