SkillsBench is a benchmark for measuring how effectively AI agents use modular skills—folders containing instructions, scripts, and resources—to complete specialized tasks. It helps researchers and developers evaluate both skill quality and agent behavior, including tasks that require combining multiple skills. The catalogue’s skills and instructions are evaluated as part of this workflow.
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 benchflow-ai/skillsbench --skill pubchem-databasegit clone --depth 1 https://github.com/benchflow-ai/skillsbenchWrote 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/benchflow-ai/skillsbench/pubchem-database)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/pubchem-database"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/pubchem-database.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.04223 |
| Opus 5 | $0.00024 | $0.02112 |
| Sonnet 5 | $0.00010 | $0.00845 |
| Haiku 4.5 | $0.00005 | $0.00422 |
Grade A, and why
pubchem-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 7d 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.
response = requests.get(url) This is a copy
86% identical to pubchem-database — 5 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 — 575 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PubChem Database
Overview
PubChem is the world's largest freely available chemical database with 110M+ compounds and 270M+ bioactivities. Query chemical structures by name, CID, or SMILES, retrieve molecular properties, perform similarity and substructure searches, access bioactivity data using PUG-REST API and PubChemPy.
When to Use This Skill
This skill should be used when:
- Searching for chemical compounds by name, structure (SMILES/InChI), or molecular formula
- Retrieving molecular properties (MW, LogP, TPSA, hydrogen bonding descriptors)
- Performing similarity searches to find structurally related compounds
- Conducting substructure searches for specific chemical motifs
- Accessing bioactivity data from screening assays
- Converting between chemical identifier formats (CID, SMILES, InChI)
- Batch processing multiple compounds for drug-likeness screening or property analysis
Core Capabilities
1. Chemical Structure Search
Search for compounds using multiple identifier types:
By Chemical Name:
import pubchempy as pcp
compounds = pcp.get_compounds('aspirin', 'name')
compound = compounds[0]
By CID (Compound ID):
compound = pcp.Compound.from_cid(2244) # Aspirin
By SMILES:
compound = pcp.get_compounds('CC(=O)OC1=CC=CC=C1C(=O)O', 'smiles')[0]
By InChI:
compound = pcp.get_compounds('InChI=1S/C9H8O4/...', 'inchi')[0]
By Molecular Formula:
compounds = pcp.get_compounds('C9H8O4', 'formula')
# Returns all compounds matching this formula
2. Property Retrieval
Retrieve molecular properties for compounds using either high-level or low-level approaches:
Using PubChemPy (Recommended):
import pubchempy as pcp
# Get compound object with all properties
compound = pcp.get_compounds('caffeine', 'name')[0]
# Access individual properties
molecular_formula = compound.molecular_formula
molecular_weight = compound.molecular_weight
iupac_name = compound.iupac_name
smiles = compound.canonical_smiles
inchi = compound.inchi
xlogp = compound.xlogp # Partition coefficient
tpsa = compound.tpsa # Topological polar surface area
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.
- 7d ago First seen · 575 lines · 49 tokens per session scan A fa2a98dd762a
pubchem-database is a skill published in the GitHub repository benchflow-ai/skillsbench (1,747 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 4,223 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 86% identical to pubchem-database, differing in 5 lines, and is treated as a copy.
Other skills, from other repositories
tiledbvcf
Efficient storage and retrieval of genomic variant data using TileDB. Scalable VCF/BCF ingestion, incremental sample addition, compressed storage, parallel queries, and export capabilities for population genomics.
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.
chembl-database
Query the ChEMBL database for bioactive molecules, drug targets, bioactivity data, approved drugs, and chemical structures. Use when the user asks about compounds, targets, IC50/Ki values, drug mechanisms, or structure searches.
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.
Database Access Skills Index
Skills for querying and downloading data from genomic, transcriptomic, 3D-genome, and cancer-genomics databases. Covers programmatic access to public repositories, gene annotation, sequence retrieval, processed functional-genomics tracks, Hi-C / Micro-C contact matrices, TCGA-style cohorts, and large-scale single-cell…