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 chembl_databasegit 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/chembl_database)<a href="https://agentmods.dev/skills/google-deepmind/science-skills/chembl_database"><img src="https://agentmods.dev/badge/skills/google-deepmind/science-skills/chembl_database/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/chembl_database"><img src="https://agentmods.dev/badge/skills/google-deepmind/science-skills/chembl_database.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.02911 |
| Opus 5.5 | $0.00021 | $0.01164 |
| Sonnet 5.5 | $0.00011 | $0.00582 |
| Haiku 4.5 | $0.00005 | $0.00291 |
Grade A, and why
chembl-database 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 1mo 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.
including checking status. NEVER use `curl` or custom Python requests to How it starts
The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChEMBL Database Query
Prerequisites
uv: Read theuvskill and follow its Setup instructions to ensureuvis installed and on PATH.- User Notification: If .licenses/chembl_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://chembl.gitbook.io/chembl-interface-documentation/about, then (2) create the file recording the notification text and timestamp.
Core Rules
-
[!IMPORTANT] Use the Utility Scripts: You MUST ALWAYS use the provided utility script
scripts/chembl_api.pyfor all ChEMBL API interactions, including checking status. NEVER usecurlor custom Python requests to query the ChEMBL API directly. This ensures rate limit is enfoced and also retries on network errors. -
Output to File (Required): The
--outputflag is required for every subcommand. All JSON results are written to the specified file. After running the command, read the output file with jq or your own code to extract the data. List results are typically wrapped in a JSON array keyed by the endpoint name (e.g.,molecules,activities). -
Notification: If this skill is used, ensure this is mentioned in the output.
Utility Script
All ChEMBL API queries use one script with subcommands:
uv run scripts/chembl_api.py <subcommand> --output <file> [options]
1. Check API Status
uv run scripts/chembl_api.py status --output /tmp/status.json
2. Molecule Queries
Fetch by ChEMBL ID: bash uv run scripts/chembl_api.py molecule --id CHEMBL25 --output /tmp/mol.json
Search by name: bash uv run scripts/chembl_api.py molecule --search "aspirin" --limit 3 --output /tmp/mol_search.json
Batch fetch: bash uv run scripts/chembl_api.py molecule --ids "CHEMBL25;CHEMBL1642" --limit 10 --output /tmp/mol_batch.json
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.
- 1mo ago First seen · 284 lines · 53 tokens per session scan A 67d375e3a869
chembl-database is a skill published in the GitHub repository google-deepmind/science-skills (3,307 stars, last pushed 6d ago), licensed Apache-2.0. It adds 53 tokens to every session and 2,911 once invoked, about $0.0002 per session on Opus 5.5. 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
tiledbvcf
Stores and retrieves genomic variant calls with TileDB-VCF. Use for indexed single-sample VCF/BCF ingestion, incremental cohorts, region and sample queries, streaming results, allele statistics, QC, and VCF/BCF export locally or through TileDB Cloud.
lamindb
Manages biological datasets and models with LaminDB, including artifact registration, lineage tracking, schema validation, Bionty ontology annotation, query/search, collections, branches, storage, and workflow integrations. Use for reproducible biological data curation or a LaminDB lakehouse.
defining-cohort-phenotypes
Authors computable phenotype and cohort definitions in the OHDSI ATLAS / CIRCE style over the OMOP CDM, combining standard concept sets with NLP-derived features that OpenMed extracts. Use when the user wants to define a patient cohort, write a computable phenotype, reuse PheKB or OHDSI Phenotype Library logic, build…
benchling-integration
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
nvalchemi-data-storage
How to write, read, compose, and load atomic data using nvalchemi's composable Zarr-backed storage pipeline (Writer, Reader, Dataset, MultiDataset, DataLoader). Use when saving simulation outputs or trajectories to disk, converting structures (e.g. ASE / extxyz) into Zarr stores, assembling datasets for training or…
sun-simiao-perspective
A historical medical-perspective skill based on research about Sun Simiao, a physician from China's Tang dynasty. It uses his clinical ideas and writings to discuss traditional Chinese medicine, health advice, medical ethics, and communication with patients.