polars-dovmed
Search the PMC Open Access literature with polars-dovmed. Author structured JSON queries directly, then use the hosted API when an API key is available or fall back to local dovmed scan over PMC, bioRxiv, or both parquet corpora.
npx skills add BioTender-max/awesome-bio-agent-skills --skill polars-dovmed --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# polars-dovmed Search the PubMed Central Open Access subset and the bioRxiv parquet corpus with `polars-dovmed`. The preferred workflow is always: 1. decide execution mode up front 2. author a structured query JSON directly 3. inspect and refine the query JSON 4. run structured discovery first 5. fetch paper details for candidate PMC IDs or bioRxiv DOIs 6. use structured advanced scans only for final refinement when needed Search execution has two modes: - Preferred when available: hosted API over `pmc`/OpenPMC, `biorxiv`, or `both` - Fallback: local `dovmed scan` over local parquet files for `pmc`, `biorxiv`, or `both` PMC is physically materialized into clean publication-year chunks: - `pre_2010` - `2010_2020` - `2021_2023` - `2024_plus` For latest-literature discovery, prefer the hosted API helper with parallel clean chunks: `--year-bands recent_split` for `2024_plus` plus `2021_2023`. Use `--year-bands clean_split` when the user needs broad coverage across all clean PMC chunks. Use a single `--year-band` only when the question is explicitly restricted to one era. Avoid the unmaterialized `2020_2023` split. Do not skip the structured-query authoring step unless the user explici
- Input Requirements
- Hosted API Reachability Rules
- Instructions
- Preferred Workflow
- Step 1: Author Query JSON Directly
- Query Authoring Rules
- Quick Templates
- Step 2: Create A Run Directory
- Step 3A: Search With Hosted API
- Step 3B: Search Locally With dovmed scan
- Search Semantics
- Retrieval Quality Playbook
- Hit Ranking Guidance
- Recall-First Principle
curl -sS --max-time 20 https://api.newlineages.com/ curl -sS --max-time 45 \ mkdir -p runs/klosneuvirinae-hosts printf '%s\n' "find papers that describe hosts of Klosneuvirinae" > runs/klosneuvirinae-hosts/prompt.txt cp queries/klosneuvirus_hosts.json runs/klosneuvirinae-hosts/query.json python skills/polars-dovmed/scripts/query_literature.py \ python skills/polars-dovmed/scripts/smoke_test.py skills/polars-dovmed/runs/smoke-test/
What does the polars-dovmed skill do?
Search the PMC Open Access literature with polars-dovmed. Author structured JSON queries directly, then use the hosted API when an API key is available or fall back to local dovmed scan over PMC, bioRxiv, or both parquet corpora.
How do I install it?
Run `npx skills add BioTender-max/awesome-bio-agent-skills --skill polars-dovmed --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From BioTender-max/awesome-bio-agent-skills, a repository with 135 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.