Bio workflow methods docwriter
Skill fmschulz/omics-skills/skills/bio-workflow-methods-docwriter
Generate reproducible Methods from Nextflow, Snakemake, or CWL run artifacts. Use when documenting exact commands, versions, parameters, QC gates, provenance, and outputs.From its SKILL.md
npx -y skills add fmschulz/omics-skills --skill bio-workflow-methods-docwriterAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 11 stars11 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
3.3 KB, as published. Nobody here has run it
Bio Workflow Methods Docwriter
Create publication-ready Methods and run documentation from real workflow artifacts.
Instructions
- Collect the workflow evidence package (logs, configs, version files).
- Build
run_manifest.yamlstrictly from evidence. - Validate the manifest against the schema.
- Draft
METHODS.mdwith a concise workflow summary at the top. - Verify QC gates and reproducibility details are captured.
Resolve the installed skill with:
METHODS_SKILL="${METHODS_SKILL:-$HOME/.agents/skills/bio-workflow-methods-docwriter}"
Quick Reference
| Task | Action |
|---|---|
| Evidence checklist | See reference/evidence-checklist.md |
| Standards to align with | See reference/standards.md |
| Manifest schema | schemas/run-manifest.schema.json (LinkML source: schemas/workflow-run-schema.yaml) |
| Drafting templates | METHODS.md template, paper-summary YAML |
| Extract a Nextflow draft | uv run "$METHODS_SKILL/scripts/extract_nextflow_run.py" --help |
| Extract Snakemake evidence | uv run --script "$METHODS_SKILL/scripts/extract_snakemake_run.py" --help |
| Extract CWL evidence | uv run --script "$METHODS_SKILL/scripts/extract_cwl_run.py" --help |
| Validate manifest | uv run "$METHODS_SKILL/scripts/validate_run_manifest.py" run_manifest.yaml |
| Examples | See examples/ |
Input Requirements
- Workflow artifacts (Nextflow/Snakemake/CWL logs and configs)
- Tool version records or container digests
- QC reports and output manifests
Output
METHODS.md(agent-authored; workflow summary + detailed steps)run_manifest.yaml(machine-readable run manifest)- Artifact contract: schemas/run-manifest.schema.json
- LinkML source: schemas/workflow-run-schema.yaml
- Paper-summary schema: schemas/bio-paper-schema.yaml
Quality Gates
- No invented commands, versions, or parameters
- Every step has inputs, outputs, and versions captured
- Commands were sourced from task scripts, not environment-bearing wrappers, and contain no credentials
- No
NOT CAPTURED,UNKNOWN, orTBDplaceholder remains in a required field - Workflow summary appears at top of
METHODS.md - The engine-specific extractor output passes
validate_run_manifest.py; the fixture-backed Nextflow path proves trace, task script, input, output, version, and final-output evidence end to end.
Examples
Example 1: Validate a manifest
METHODS_SKILL="${METHODS_SKILL:-$HOME/.agents/skills/bio-workflow-methods-docwriter}"
uv run "$METHODS_SKILL/scripts/validate_run_manifest.py" run_manifest.yaml
Troubleshooting
Issue: Missing tool versions in logs
Solution: Use NOT CAPTURED only while assembling a draft. The final validator rejects it; recover the version from provenance or report the missing evidence in limitations without claiming a reproducible manifest.
What ships with it: 22 files
31.1 KB alongside SKILL.md, 5 of them executable
examples/
fixtures/
reference/
- evidence-checklist.md2.0 KB
- standards.md719 B
schemas/
- bio-paper-schema.yaml2.6 KB
- run-manifest.schema.json5.3 KB
- workflow-run-schema.yaml2.7 KB
scripts/
- extract_cwl_run.pyruns1.7 KB
- extract_nextflow_run.pyruns6.7 KB
- extract_snakemake_run.pyruns2.3 KB
- validate_run_manifest.pyruns2.9 KB
templates/
- methods_report.md1.0 KB
- paper_summary.yaml627 B
- requirements.txt18 B
Gives 0 of the 12 instructions most automation workflows skills give
Counted across 813 of the 1,214 authors here whose files we hold, read 2026-09-06
- Use conventional commit message formatin 38 of 813, across 34 files
- Write tests before implementing codein 26 of 813, across 12 files
- Achieve at least 80 percent test coveragein 24 of 813, across 11 files
- Mock external dependencies for unit testsin 22 of 813, across 10 files
- Read product marketing context before asking questionsin 21 of 813, across 6 files
- Implement rollback plans for every deploymentin 21 of 813, across 9 files
- Follow the arrange-act-assert patternin 20 of 813, across 9 files
- Delete branches after mergingin 20 of 813, across 18 files
- Test all edge cases and error scenariosin 20 of 813, across 8 files
- Use semantic selectors for UI testsin 19 of 813, across 7 files
- Define sequence type and audience contextin 18 of 813, across 5 files
- Monitor feature drift and prediction distribution driftin 18 of 813, across 5 files
Said here and by no other author read
- Collect workflow logs and configuration files
- Build run_manifest.yaml strictly from evidence
- Validate the manifest against the schema
- Draft METHODS.md with a workflow summary
- Verify QC gates and reproducibility details
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.