vimalinx/bio-agent / .claude/skills/pmc2bioc
pmc2bioc
VerifiedUse when converting PubMed Central article XML into BioC collection XML for downstream text-mining or annotation pipelines.
pmc2bioc
EDirect shell pipeline that converts PMC <article> XML into BioC-style collection / document / passage XML. It lifts front-matter metadata into the first passage, then emits abstract, title, and body passages for downstream text-mining workflows.
Quick Start
- Command:
pmc2bioc - Local executable:
/home/vimalinx/miniforge3/envs/bio/bin/pmc2bioc - Environment prerequisite: add
/home/vimalinx/miniforge3/envs/bio/bintoPATHsoxtract,transmute, and related EDirect helpers are available
When To Use This Tool
- Convert PMC full-text XML into BioC collection XML.
- Feed PMC articles into BioC-oriented NLP, annotation, or corpus-building pipelines.
- Preserve article metadata, title, abstract, and body passages in a text-mining-friendly structure.
- Use this on PMC article XML, not on PubMed citation XML or summary XML.
Common Patterns
# 1) Convert a live PMC article fetch into BioC XML
export PATH=/home/vimalinx/miniforge3/envs/bio/bin:$PATH
efetch -db pmc -id 6260607 -format xml | pmc2bioc > article.bioc.xml
# 2) Convert XML streamed from a PMC OA tarball
export PATH=/home/vimalinx/miniforge3/envs/bio/bin:$PATH
tar -xOzf oa_bundle.tar.gz --to-stdout | pmc2bioc > batch.bioc.xml
# 3) Inspect the first BioC passages before batch processing
export PATH=/home/vimalinx/miniforge3/envs/bio/bin:$PATH
efetch -db pmc -id 6260607 -format xml | pmc2bioc | sed -n '1,40p'
Recommended Workflow
- Fetch or extract PMC article XML first, because this wrapper does not retrieve articles on its own.
- Activate the bio environment or export the EDirect bin directory into
PATHso sibling utilities resolve. - Convert one representative article and inspect the first
passageblocks to confirm the BioC shape your downstream tool expects. - Only then batch-convert larger PMC corpora or OA archive payloads.
Guardrails
- The source itself labels this converter as
WORK IN PROGRESS, so treat the emitted BioC schema as practical but not deeply stabilized. - There is no true help path. With dependencies available,
pmc2bioc -helpstill runs the conversion pipeline and only errors because no XML input was supplied. - Without the bio bin directory on
PATH, the live failure isxtract: command not foundplustransmute: command not found. - With dependencies available but no XML input, the live failure is
No data supplied to xtract from stdin or file. - This script expects PMC
<article>XML and emits BioC XML; it is not a generic PMC metadata lister or PubMed citation converter.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 318k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse 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. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 117k | Updated | Claude CodeCodex | Verified | Install |