Copy Number Agent Skill
Workflow for copy-number estimation, segmentation, annotation, and visualization in sequencing-based assays.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/BioTender-max/awesome-bio-agent-skills --skill copy-numberWhat comes with it
2 438 bytes besides the instructionThe instruction itself
22 sections, as written by the authorCopy Number
Version Compatibility
Reference examples assume recent stable releases of the preferred tools, especially CNVkit-style and the other tools listed below.
Before using code or command patterns, verify installed versions match the environment:
- Python:
python -c "import <module>; print(<module>.__version__)" - CLI:
<tool> --version - If signatures differ, inspect the installed help or API and adapt the pattern instead of retrying unchanged.
Overview
Workflow for copy-number estimation, segmentation, annotation, and visualization in sequencing-based assays.
When To Use This Skill
- use when the task is CNV calling or copy-number visualization
- use when coverage-based segment inference is needed for tumor or cohort samples
- use when the user needs gene-level CNV summaries or segment plots
Quick Route
- If the input is raw or minimally processed data, start with validation and QC before any modeling.
- If the input is already processed, skip directly to the first workflow step that matches the user goal.
- If the user asks for a biological conclusion, always produce at least one QC or confidence artifact alongside the final result.
Progressive Disclosure
- Read
references/technical_reference.mdwhen you need deeper tool-selection rules, environment adaptation notes, or extra validation guidance. - Keep
SKILL.mdas the main execution path and load the reference file only when the task or failure mode needs the extra detail.
Default Rules
- Prefer Python-first workflows unless the task explicitly requires something else.
- Keep intermediate and final outputs separated.
- Record software versions, reference builds, and key parameters when they affect interpretation.
- Favor reproducible tables and figures over one-off interactive-only outputs.
Expected Inputs
- coverage or ratio data
- target bins or intervals
- sample metadata
Expected Outputs
- CNV segments
- gene-level CNV tables
- CNV plots
Preferred Tools
- CNVkit-style workflows
- GATK CNV-style workflows
- pandas
- matplotlib
Starter Pattern
Preferred starting point: CNVkit-style
Inputs: coverage or ratio data, target bins or intervals, sample metadata
Outputs: CNV segments, gene-level CNV tables, CNV plots
Workflow
1. Confirm assay context
Clarify tumor-normal versus tumor-only design and target capture versus genome-wide coverage.
2. Generate or import coverage summaries
Build bin- or target-level signals suitable for segmentation.
3. Call segments
Infer copy-number segments and classify gains, losses, or focal events.
4. Annotate to genes and loci
Map segments to biologically relevant genes and recurrent regions.
5. Report with visualization
Produce chromosome-level plots and gene-centric summaries.
Output Artifacts
- Recommended output layout:
results/for final tables and serialized objectsfigures/for plots and static visual exportsqc/for checks that justify downstream interpretation- Minimum expected outputs for this skill:
CNV segmentsgene-level CNV tablesCNV plots
Quality Review
- Confirm identifiers and metadata join correctly before modeling or summarizing.
- Generate at least one QC artifact before final biological interpretation.
- Keep raw or minimally processed inputs separate from transformed outputs.
- Record reference build, caller assumptions, and filtering rules in the final outputs.
- Separate raw calls from filtered or interpreted results.
Anti-Patterns
- treating noisy ratio shifts as confident focal events without segmentation support
- ignoring tumor purity or ploidy context when it matters
- reporting copy-number calls without genome build and binning details
Related Skills
Variant CallingLong-Read GenomicsGenome AssemblyComparative Genomics
Optional Supplements
- None required for the first pass.
Other skills for the same job
different authors, same section of the catalogue
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair, unbiased selection with transparency.
Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.
MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Use when writing MATLAB/Octave scripts for linear algebra, signal processing, image processing, differential equations, optimization, statistics, or creating scientific visualizations. Also use when the user needs help with MATLAB syntax, functions, or wants to convert between MATLAB and Python code. Scripts can be executed with MATLAB or the open-source GNU Octave interpreter.
UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
Creating interactive data visualisations using d3.js. This skill should be used when creating custom charts, graphs, network diagrams, geographic visualisations, or any complex SVG-based data visualisation that requires fine-grained control over visual elements, transitions, or interactions. Use this for bespoke visualisations beyond standard charting libraries, whether in React, Vue, Svelte, vanilla JavaScript, or any other environment.
How to use it
Take biotender-max/copy-number from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.