Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add fmschulz/omics-skills --skill polars-dovmedgit clone --depth 1 https://github.com/fmschulz/omics-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fmschulz/omics-skills/polars-dovmed)<a href="https://agentmods.dev/skills/fmschulz/omics-skills/polars-dovmed"><img src="https://agentmods.dev/badge/skills/fmschulz/omics-skills/polars-dovmed/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fmschulz/omics-skills/polars-dovmed"><img src="https://agentmods.dev/badge/skills/fmschulz/omics-skills/polars-dovmed.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 75 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00042 | $0.04640 |
| Opus 5 | $0.00021 | $0.02320 |
| Sonnet 5 | $0.00008 | $0.00928 |
| Haiku 4.5 | $0.00004 | $0.00464 |
Grade A, and why
polars-dovmed scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS --max-time 20 https://api.newlineages.com/ How it starts
The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
polars-dovmed
Search PubMed Central Open Access and bioRxiv parquet corpora with polars-dovmed.
Use the bundled helper, skills/polars-dovmed/scripts/query_literature.py, for hosted API or local parquet-backed searches. The helper auto-loads ~/.config/polars-dovmed/.env.
Run the helper with uv run --script so its pinned Parquet fallback dependency is available. Local runs record --corpus-revision (or DOVMED_CORPUS_REVISION) and fall back from flattened.csv to processed.parquet or the legacy prcoessed.parquet only when the compact output is absent.
Current hosted API defaults:
- Treat API keys as secrets in artifacts. Do not save keys in run directories, memory records, summaries, or final answers.
- Save generated run artifacts under
tasks/polars-dovmed-runs/<slug>/by default, not underskills/polars-dovmed/. - Prefer structured async search through
/api/jobstargetingscan_literature_advanced(mode="discovery"). - Do not use the flat
/api/search_literatureendpoint for smoke tests or normal skill work. It is opt-in only with--allow-flat-queryand may hang behind the edge proxy. - Do not start with
--corpus both. Run--corpus biorxivand--corpus pmcas separate calls, then merge results. - For OpenPMC/PMC, do not run a broad unbanded scan. Use the materialized clean year bands in parallel with direct FTS-backed calls:
--sync --year-bands clean_split --year-band-workers 4. - If the user names a specific publication year or narrow range, map it to the matching clean band(s) and search only those bands. Use all clean bands only when no year constraint is given.
- For recent or emerging taxa, run bioRxiv anchor-only discovery and OpenPMC clean-band discovery as separate searches. bioRxiv is small and often returns first; OpenPMC should still use parallel clean bands.
- For any entity-centric prompt with topic modifiers, such as "distribution and genomics of X", first search the exact entity/aliases only. Treat topic words as triage labels or a second-pass refinement after confirming anchor hits; do not build a large first-pass query of generic topic terms.
- Do not invent aliases by splitting compact taxon, gene, or clade names into common words unless the prompt or literature supports that synonym. Keep aliases evidence-based; when a real synonym is multi-word, keep it as one phrase in a single JSON term.
- For OpenPMC clean-band discovery, skip automatic details rerank: pass
--skip-details-rerank. The FTS index searches title, abstract, and full text, but PMC details lookups still read parquet and can dominate wall time. Fetch details only for selected PMCID values after discovery. - Citation metadata should come from the corpus response/details endpoint first. If DOI/year/journal are missing, use bounded Crossref lookup through
--crossref-metadataor thecrossref-lookupskill. Do not use generic web search for DOI repair except as a final publisher-page check for unresolved/ambiguous records. - If OpenPMC clean-band search returns
Database not found, stop and report that the deployment is not exposing the indexed OpenPMC bands. Do not fall back to a monolithic unbanded OpenPMC scan. - For interactive work, pass
--poll-timeoutand, when available, wrap searches intimeout. Do not rerun OpenPMC with longer waits after one bounded clean-band failure.
Public access note:
omics-skillsdoes not provide a hosted API key or the PMC/bioRxiv parquet corpora.- Public users can prepare local PMC searches from Uri Neri's upstream package: https://github.com/UriNeri/polars-dovmed.
- Local setup uses upstream
dovmed download,dovmed build-parquet, anddovmed scan. - If no API key and no local corpus exist, state that
polars-dovmedis not configured and use another literature fallback.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 352 lines · 42 tokens per session scan A c2c813ce136b
polars-dovmed is a skill published in the GitHub repository fmschulz/omics-skills (7 stars, last pushed 5d ago), licensed MIT. It adds 42 tokens to every session and 4,640 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons. Invoke for any question about IDC collections, cancer imaging datasets, DICOM data access, radiology (CT, MR, PET) or pathology AI training sets, metadata queries, visualization, or license checks — even when the user doesn't explicitly…
tamarind
Access a collection of open-source molecular design and structural biology tools on the Tamarind Bio platform, via its REST API or MCP server — no local GPUs required. Tamarind bundles popular open-source models for structure prediction (AlphaFold, Boltz, Chai, ESMFold), protein, binder, and de novo design…
lab-hardware-cad
Design custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a research…
pkpd-modeling
Pharmacokinetic and pharmacodynamic modelling and simulation - non-compartmental analysis, compartmental and population PK, PK/PD and exposure-response, TMDD, PBPK orientation, bioequivalence, allometric scaling and first-in-human dose, drug interaction prediction, and Bayesian therapeutic drug monitoring. Use when…
relsa-severity-assessment
Multivariate severity assessment and humane endpoint prediction for laboratory animal studies using the RELSA (RELative Severity Assessment) score and ARIMA-based foRcast forecasting. Use when combining welfare readouts — body weight or weight loss, body temperature, clinical or nesting scores, biomarkers, activity…
scientific-slides
Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and…