Science Skills is a collection of add-ons that give AI agents structured instructions, scripts, and references for scientific research, including genomics, structural biology, cheminformatics, and literature search. Researchers use it to guide agents through specialized scientific tasks with information from databases and tools such as AlphaGenome, AFDB, and UniProt. The catalogue entries are individual skills from this collection.
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 google-deepmind/science-skills --skill literature_search_biorxivgit clone --depth 1 https://github.com/google-deepmind/science-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/google-deepmind/science-skills/literature_search_biorxiv)<a href="https://agentmods.dev/skills/google-deepmind/science-skills/literature_search_biorxiv"><img src="https://agentmods.dev/badge/skills/google-deepmind/science-skills/literature_search_biorxiv/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/google-deepmind/science-skills/literature_search_biorxiv"><img src="https://agentmods.dev/badge/skills/google-deepmind/science-skills/literature_search_biorxiv.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 19 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 | $0.00074 | $0.01996 |
| Opus 5 | $0.00037 | $0.00998 |
| Sonnet 5 | $0.00015 | $0.00399 |
| Haiku 4.5 | $0.00007 | $0.00200 |
Grade A, and why
literature-search-biorxiv 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 13d 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.
To ensure you respect terms-of-service, do NOT write custom `curl` queries. How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bioRxiv and medRxiv Literature Search
Prerequisites
uv: Read theuvskill and follow its Setup instructions to ensureuvis installed and on PATH.- User Notification: If .licenses/literature_search_biorxiv_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://api.biorxiv.org/ and https://www.biorxiv.org/content/about-biorxiv and to always check the license of the papers retrieved by the skill for any restrictions, then (2) create the file recording the notification text and timestamp.
Search Strategy Guide (Read First)
This skill browses a date-based preprint archive. It is NOT a keyword search engine. Choose your approach based on what you already know:
- A DOI (e.g., from a citation): Use
search_by_doi.py. Fast and reliable. - Approximate date + category: Use
search_by_dates.pywith a 1–4 week range and--category. - Only a topic or keywords, no date: Do NOT use this skill for discovery. Use a keyword-capable literature skill first to find relevant DOIs, then return here to fetch metadata.
CRITICAL ANTI-PATTERN — Do NOT do this: Do NOT attempt to search broad date ranges (months or years) with
--keywordshoping to find a specific paper. The bioRxiv API does not support server-side keyword search. The script must download ALL metadata for the entire date range and filter locally in Python. Broad ranges will result in thousands of API calls, timeouts, and your request being blocked for API abuse. This is the #1 reason this skill fails.
Core Rules
- Use the Wrapper: ALWAYS execute the provided helper scripts to query the database rather than accessing the database directly. The scripts automatically enforce the required rate limit gracefully.
- Local Filtering (CRITICAL WARNING): Unlike arXiv, the bioRxiv API does
not support server-side keyword or author searches. Keyword and author
filtering is performed locally by the scripts after downloading all
metadata for a specified date range. You MUST use narrow date ranges
(e.g., 1-4 weeks) AND the
--categoryfilter when searching with--keywordsor--author. - Abstracts Excluded By Default: To save context space in the resulting
JSON, abstracts are stripped from the output by default. If you are
searching by
--keywordsand want to read the abstracts of the resulting papers to understand their context, you MUST pass the--include_abstractsflag. - Output Redirection: Search commands output JSON arrays to standard
output. Always redirect output to a file (e.g.,
> results.json) and parse the file separately. - List Sources If this skill is used, ensure this is mentioned in the output AND list the URLs of all papers that were used in producing the output.
What ships with it
3 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.
- 13d ago First seen · 170 lines · 74 tokens per session scan A bb9477b5a0b8
literature-search-biorxiv is a skill published in the GitHub repository google-deepmind/science-skills (3,003 stars, last pushed 4d ago), licensed Apache-2.0. It adds 74 tokens to every session and 1,996 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…