Bio Workflows Cnv Pipeline

What it does

When your agent uses it

• Committing the build + target/access BED + PoN once (assay-matched)
• Building the reference from normals BEFORE segmenting
• Fitting purity/ploidy BEFORE integer calls in tumors
• Centering on the true (non-diploid) mode before GISTIC2 recurrence

Example prompts

• “Use the bio-workflows-cnv-pipeline skill to orchestrate the copy-number pipeline from BAM to segmented, integer-called, annotated CNVs, forking on…”
• “/bio-workflows-cnv-pipeline”

Requirements

• A Bash shell

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1The reference build + target/access BED + reference/PoN is one made-once commitment inherited by everything downstream. The capture-kit…
2. 2The reference/PoN is built BEFORE anything is segmented, and it absorbs shared signal. fix needs the reference to bias-correct; segmenting…
3. 3The diploid baseline is a commitment, not a given — fit purity/ploidy BEFORE integer calls in tumors. In WGD/hyper-aneuploid tumors the…

What it can do on your machine

Read from SKILL.md and the folder at commit d91ed3d. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships script files (Shell), which the agent can run.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Bio Workflows Cnv Pipeline loads about 3k tokens when it runs. Until then it costs about 187 tokens; SKILL.md has 1,015 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~187

When it runs · the whole SKILL.md, loaded when a task matches

~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from GPTomics/bioSkills at commit d91ed3d, republished under its MIT licence (© GPTomics). 1,015 words, ~2,979 tokens.

name

bio-workflows-cnv-pipeline

description

Orchestrates the copy-number pipeline from BAM to segmented, integer-called, annotated CNVs, forking on germline-vs-somatic - CNVkit (somatic exome/panel: coverage -> assay-matched reference/PoN -> fix -> segment -> purity/ploidy-aware call), GATK gCNV (germline rare-CNV cohort), and allele-specific callers (ASCAT/FACETS/PURPLE) for purity/ploidy. Use when committing the build + target/access BED + PoN once (assay-matched), building the reference from normals BEFORE segmenting, fitting purity/ploidy BEFORE integer calls in tumors, centering on the true (non-diploid) mode before GISTIC2 recurrence, or routing cfDNA to ichorCNA. Hands mechanism to the copy-number component skills; not a re-teach of any single step.

tool_type

mixed

primary_tool

CNVkit

goal_approach_exempt

true

workflow

true

depends_on

- copy-number/cnvkit-analysis - copy-number/gatk-cnv - copy-number/copy-ratio-segmentation - copy-number/allele-specific-copy-number…

qc_checkpoints

- after_coverage: "Uniform coverage across targets; flag systematically low-depth targets (capture dropout)" - after_fix: "log2-ratio noise (.cnr spread/MAD)…

BAM (tumor +/- matched normal, OR germline cohort)
  | fork: germline rare-CNV cohort? --> GATK gCNV  (copy-number/gatk-cnv)
  v  else somatic exome/panel:
  | [1] target/access/antitarget BED (build-matched)   (copy-number/cnvkit-analysis)
  v
  | [2] per-sample coverage
  v
  | [3] build reference/PoN from NORMALS first (assay-matched)
  v     ^-- tangent absorbs CNV shared across the PoN
  | [4] fix (bias-correct) -> segment -> call
  v     ^-- purity/ploidy fitted BEFORE integer call (copy-number/allele-specific-copy-number)
  | [5] visualize + gene-level annotate            (copy-number/cnv-visualization, cnv-annotation)
  v
  | [6] (cohort) center on true mode -> GISTIC2 recurrence  (copy-number/recurrent-cnv)
  v
Segmented, integer-called, annotated CNVs

# 1. Targets on the committed build (annotate with refFlat, split for WES)
cnvkit.py target capture_targets.bed --annotate refFlat.txt --split -o targets.bed
cnvkit.py access genome.fa -o access.bed
cnvkit.py antitarget targets.bed --access access.bed -o antitargets.bed

# 2-3. Coverage per sample, then build the reference from NORMALS (assay-matched) BEFORE any fix
cnvkit.py coverage $bam targets.bed -o cov/${s}.targetcoverage.cnn
cnvkit.py coverage $bam antitargets.bed -o cov/${s}.antitargetcoverage.cnn
cnvkit.py reference cov/normal*.{,anti}targetcoverage.cnn --fasta genome.fa -o reference.cnn

# 4. fix (bias-correct) -> segment -> call. Fit purity/ploidy first (ASCAT/FACETS) for tumors:
cnvkit.py fix cov/${s}.targetcoverage.cnn cov/${s}.antitargetcoverage.cnn reference.cnn -o ${s}.cnr
cnvkit.py segment ${s}.cnr -o ${s}.cns
cnvkit.py call ${s}.cns --purity 0.6 --ploidy 2 -o ${s}.call.cns   # purity/ploidy from an allele-specific fit

© GPTomics, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in workflows/cnv-pipeline of GPTomics/bioSkills.

• SKILL.md
• examples/cnvkit_workflow.sh
• usage-guide.md

Open the folder on GitHubat commit d91ed3d

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in GPTomics/bioSkills, which our catalogue first saw on October 7, 2026.

• PKU-YuanGroup/OpenAI4Sskills/bioskills/bio-workflows-cnv-pipeline