<< All versions
Skill v1.0.1
LLM-judged scan95/100fmschulz/omics-skills/bio-workflow-methods-docwriter
1 files
──Details
PublishedSeptember 25, 2026 at 11:00 PM
Content Hashsha256:955e201f61a107da...
Git SHA7a4eb5bace3f
Bump Typepatch
──Files
Files (1 file, 3.3 KB)
SKILL.md3.3 KBactive
SKILL.md · 75 lines · 3.3 KB
version: "1.0.1" name: bio-workflow-methods-docwriter description: Generate reproducible Methods from Nextflow, Snakemake, or CWL run artifacts. Use when documenting exact commands, versions, parameters, QC gates, provenance, and outputs.
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:
bash
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
bash
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.