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 silverstein/claude-scientific-skills-desktop --skill zinc-databasegit clone --depth 1 https://github.com/silverstein/claude-scientific-skills-desktopWrote 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/silverstein/claude-scientific-skills-desktop/zinc-database)<a href="https://agentmods.dev/skills/silverstein/claude-scientific-skills-desktop/zinc-database"><img src="https://agentmods.dev/badge/skills/silverstein/claude-scientific-skills-desktop/zinc-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/silverstein/claude-scientific-skills-desktop/zinc-database"><img src="https://agentmods.dev/badge/skills/silverstein/claude-scientific-skills-desktop/zinc-database.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 | $0.00047 | $0.03508 |
| Opus 5 | $0.00023 | $0.01754 |
| Sonnet 5 | $0.00009 | $0.00702 |
| Haiku 4.5 | $0.00005 | $0.00351 |
Grade A, and why
zinc-database scanned grade A with 2 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 8d 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 "https://cartblanche22.docking.org/[email protected]_fields=smiles,zinc_id" Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run(['curl', url], capture_output=True, text=True) This is a copy
97% identical to zinc-database — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ZINC Database
Overview
ZINC is a freely accessible repository of 230M+ purchasable compounds maintained by UCSF. Search by ZINC ID or SMILES, perform similarity searches, download 3D-ready structures for docking, discover analogs for virtual screening and drug discovery.
When to Use This Skill
This skill should be used when:
- Virtual screening: Finding compounds for molecular docking studies
- Lead discovery: Identifying commercially-available compounds for drug development
- Structure searches: Performing similarity or analog searches by SMILES
- Compound retrieval: Looking up molecules by ZINC IDs or supplier codes
- Chemical space exploration: Exploring purchasable chemical diversity
- Docking studies: Accessing 3D-ready molecular structures
- Analog searches: Finding similar compounds based on structural similarity
- Supplier queries: Identifying compounds from specific chemical vendors
- Random sampling: Obtaining random compound sets for screening
Database Versions
ZINC has evolved through multiple versions:
- ZINC22 (Current): Largest version with 230+ million purchasable compounds and multi-billion scale make-on-demand compounds
- ZINC20: Still maintained, focused on lead-like and drug-like compounds
- ZINC15: Predecessor version, legacy but still documented
This skill primarily focuses on ZINC22, the most current and comprehensive version.
Access Methods
Web Interface
Primary access point: https://zinc.docking.org/ Interactive searching: https://cartblanche22.docking.org/
API Access
All ZINC22 searches can be performed programmatically via the CartBlanche22 API:
Base URL: https://cartblanche22.docking.org/
All API endpoints return data in text or JSON format with customizable fields.
Core Capabilities
1. Search by ZINC ID
Retrieve specific compounds using their ZINC identifiers.
Web interface: https://cartblanche22.docking.org/search/zincid
API endpoint:
curl "https://cartblanche22.docking.org/[email protected]_fields=smiles,zinc_id"
What ships with it
1 file 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.
- 8d ago First seen · 399 lines · 47 tokens per session scan A 498afb950360
zinc-database is a skill published in the GitHub repository silverstein/claude-scientific-skills-desktop (22 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 3,508 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). It is 97% identical to zinc-database, differing in 7 lines, and is treated as a copy.
Other skills, from other repositories
bio-ortholog-inference
Pull pre-computed ortholog calls from public databases (OrthoDB, Ensembl Compara, OMA browser, eggNOG, PANTHER, KEGG Orthology, HomoloGene) via their REST APIs. Use when orthologs are already curated upstream, when the question is "what is the X ortholog of Y" rather than "how to infer orthology de novo", when…
admet_genetic
ADMET-guided genetic molecule optimization workflow from seed SMILES; use when the agent needs to build or run an RDKit/SA-Score/ADMET-AI GA pipeline for molecule optimization, enforce molecule lineage logs, render optimization-history HTML dashboards, and write candidate triage reports.
bioprobench
Score an LLM's biological-protocol reasoning on the BioProBench benchmark: protocol QA, step ordering, error detection, protocol generation, and LLM-judged error reasoning; or generate the responses.
alphafold2
Predict protein structure for monomers and multimers with AlphaFold2 via the ColabFold runner (Mirdita et al. 2022, github.com/sokrypton/ColabFold; AlphaFold2 Jumper et al. 2021). Reach for this skill to fold a sequence or complex with the AF2/AF2-Multimer evoformer, to validate designed sequences by self-consistency…
bio-alignment-msa-parsing
Parse and analyze multiple sequence alignments using Biopython. Extract sequences, identify conserved regions, analyze gaps, work with annotations, and manipulate alignment data for downstream analysis. Use when parsing or manipulating multiple sequence alignments.
bio-causal-genomics-heritability-partitioning
Estimates SNP heritability and partitions it across functional annotations, cell types, and loci from GWAS summary statistics or individual-level genotypes. Implements LDSC, stratified LDSC with the baseline-LD model, Finucane 2018 cell-type prioritization, LDAK SumHer, HDL, HESS local heritability, BOLT-REML…