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 alphagenome_atlas_website_linksgit 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/alphagenome_atlas_website_links)<a href="https://agentmods.dev/skills/google-deepmind/science-skills/alphagenome_atlas_website_links"><img src="https://agentmods.dev/badge/skills/google-deepmind/science-skills/alphagenome_atlas_website_links/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/alphagenome_atlas_website_links"><img src="https://agentmods.dev/badge/skills/google-deepmind/science-skills/alphagenome_atlas_website_links.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00103 | $0.03123 |
| Opus 5 | $0.00051 | $0.01562 |
| Sonnet 5 | $0.00021 | $0.00625 |
| Haiku 4.5 | $0.00010 | $0.00312 |
Grade A, and why
alphagenome-atlas-website-links scanned grade A with 0 findings 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 3d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AlphaGenome Atlas Deep-Linking & URL Configuration
Construct and validate deep-links for the AlphaGenome Atlas web application
(https://deepmind.google.com/science/alphagenome/atlas).
Base URL: https://deepmind.google.com/science/alphagenome/atlas
[!IMPORTANT] Mandatory Atlas Deep-Linking with Variant Scores: Whenever presenting, discussing, or scoring genetic variants, you MUST always provide clickable deep-links to the AlphaGenome Atlas. Use
scripts/alphagenome_atlas_links.pyto automate link and table generation.
Prerequisites
# 1. Single Variant Exploration Link:
uv run scripts/alphagenome_atlas_links.py variant "chr9:128225994:G>A" \
--biosample K562 \
--modalities RNA_SEQ,DNASE,CHIP_TF
# 2. Genomic Locus / Interval Link:
uv run scripts/alphagenome_atlas_links.py locus "chr11:5288500-5290500" \
--biosample K562 \
--modalities RNA_SEQ,DNASE,CHIP_TF
# 3. Format Candidate Variant Records Table (with embedded clickable links):
uv run scripts/alphagenome_atlas_links.py table --input top_variants.json --biosample K562
# 4. Construct Ref vs. Alt Track Predictions Link (/atlas/track-predictions):
uv run scripts/alphagenome_atlas_links.py track-predictions \
--variant "chr15:42387805:C>G" \
--gene CAPN3 \
--biosample "Muscle_Skeletal"
2. URL Query Parameters
q(string, Required): Primary search target. Supports 1-based closed intervals (chr11:5288500-5290500), gene symbols (BRCA1), Ensembl IDs (ENSG00000012048), or 1-based variants (chr7:27170000:A>G).m(enum, Optional): View mode. Defaults toentityfor genes/variants andlocusfor coordinate intervals. Usevariantfor variant queries. (Allowed:locus,entity,variant,motifs).i(string, Optional): Centered viewport zoom interval in 1-based closedchr:start-endformat (e.g.chr11:5289310-5289690). Required for automatic motif rendering.f(string, Optional): Comma-separated filter predicates inKEY:VALUEformat (e.g.BIOSAMPLE_NAME:K562,SCORER_MODALITY:RNA-seq,ASSAY_TRANSCRIPTOR_FACTOR:GATA1). Controls visible heatmap rows.lItems(string, Optional): Layout item sequence, AVI score track toggle (avi), section heatmaps, and pinned tracks list (e.g.avi,section:RNA_SEQ,section:DNASE,pinned:<TrackKey>).scores(string, Optional): Comma-separated list ofScoreIdtokens for the/atlas/track-predictionspage comparison (e.g.<ScoreId1>,<ScoreId2>).md(enum, Optional): Active modality tab selector on the track predictions view (RNA_SEQ,SPLICE_JUNCTIONS,SPLICE_SITE_USAGE,DNASE).tpRenames(string, Optional): Custom title overrides for specific score predictions (ScoreId:CustomTitle).tpLegendTitle(string, Optional): Custom legend title for the track predictions chart card (e.g.Predicted Gene Expression).
What ships with it
2 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.
- 3d ago First seen · 249 lines · 103 tokens per session scan A 32260de03795
alphagenome-atlas-website-links 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 103 tokens to every session and 3,123 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-09.
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…