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_arxivgit 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_arxiv)<a href="https://agentmods.dev/skills/google-deepmind/science-skills/literature_search_arxiv"><img src="https://agentmods.dev/badge/skills/google-deepmind/science-skills/literature_search_arxiv/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_arxiv"><img src="https://agentmods.dev/badge/skills/google-deepmind/science-skills/literature_search_arxiv.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 Prompt Injection · line 27 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
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 | $0.00056 | $0.01164 |
| Opus 5 | $0.00028 | $0.00582 |
| Sonnet 5 | $0.00011 | $0.00233 |
| Haiku 4.5 | $0.00006 | $0.00116 |
Grade A, and why
literature-search-arxiv 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 12d 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.
use these scripts rather than writing your own curl/python requests. How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
arXiv Search and Retrieval
Prerequisites
uv: Read theuvskill and follow its Setup instructions to ensureuvis installed and on PATH.- User Notification: If .licenses/literature_search_arxiv_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://info.arxiv.org/help/api/index.html 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.
Core Rules
- Terms of Use: You MUST respect arXiv's Terms of Use.
- Maximum 1 request every 3 seconds.
- The provided utility scripts handle rate limiting automatically. Always use these scripts rather than writing your own curl/python requests.
- 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.
Utility Scripts
1. Search and Extract Metadata
Search arXiv and return a clean JSON array of matching papers.
uv run scripts/search_arxiv.py --query "au:einstein AND ti:relativity" \
--max_results 5 2>/dev/null > /tmp/arxiv_search_results.json
Important: The tool outputs a large JSON result to stdout. Requesting 100+ results will produce a massive JSON that might exceed your context length. Limit
--max_results(e.g., 5-10) or paginate carefully using--start. Always redirect output to a file and parse it separately, otherwise terminal output will be truncated.
Returned Metadata: JSON results include id, title, summary, published,
authors, pdf_url, primary_category, doi, journal_ref, and comment.
Note: the doi field only contains DOI information in case the paper has an
external DOI and if only an arXiv-issued DOI exists, this is DOI is not
returned.
Options:
--query: Search string. See references/query_syntax.md for advanced syntax.--id_list: Comma-separated list of arXiv IDs to fetch directly (e.g.,1706.03762v5).--start: Pagination offset (default 0).--max_results: Number of results to return (default 10).--sort_by:relevance,lastUpdatedDate, orsubmittedDate. (Use--sort_by submittedDate --sort_order descendingfor the most recent papers).--sort_order:ascendingordescending.
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.
- 12d ago First seen · 121 lines · 56 tokens per session scan A b71daf2b4f84
literature-search-arxiv is a skill published in the GitHub repository google-deepmind/science-skills (3,003 stars, last pushed 3d ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,164 once invoked, about $0.0003 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…
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…
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.
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…