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 meteorology-driver-classificationgit 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/meteorology-driver-classification)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/meteorology-driver-classification"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/meteorology-driver-classification/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/benchflow-ai/skillsbench/meteorology-driver-classification"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/meteorology-driver-classification.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 | $0.00033 | $0.00392 |
| Opus 5 | $0.00016 | $0.00196 |
| Sonnet 5 | $0.00007 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
meteorology-driver-classification 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 6d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- meteorology-driver-classification — 100% identical, 0 lines differ
What it actually says
Driver Classification Guide
Overview
When analyzing what drives changes in an environmental system, it is useful to group individual variables into broader categories based on their physical meaning.
Common Driver Categories
Heat
Variables related to thermal energy and radiation:
- Air temperature
- Shortwave radiation
- Longwave radiation
- Net radiation (shortwave + longwave)
- Surface temperature
- Humidity
- Cloud cover
Flow
Variables related to water movement:
- Precipitation
- Inflow
- Outflow
- Streamflow
- Evaporation
- Runoff
- Groundwater flux
Wind
Variables related to atmospheric circulation:
- Wind speed
- Wind direction
- Gust speed
- Atmospheric pressure
Human
Variables related to anthropogenic activities:
- Developed area
- Agriculture area
- Impervious surface
- Population density
- Industrial output
- Land use change rate
Derived Variables
Sometimes raw variables need to be combined before analysis:
# Combine radiation components into net radiation
df['NetRadiation'] = df['Longwave'] + df['Shortwave']
Grouping Strategy
- Identify all available variables in your dataset
- Assign each variable to a category based on physical meaning
- Create derived variables if needed
- Variables in the same category should be correlated
Validation
After statistical grouping, verify that:
- Variables load on expected components
- Groupings make physical sense
- Categories are mutually exclusive
Best Practices
- Use domain knowledge to define categories
- Combine related sub-variables before analysis
- Keep number of categories manageable (3-5 typically)
- Document your classification decisions
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.
- 6d ago First seen · 79 lines · 33 tokens per session scan A 5faebbffdf7c
meteorology-driver-classification is a skill published in the GitHub repository benchflow-ai/skillsbench (1,754 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 392 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
run-aeon-benchmark
Use when asked to run, benchmark, evaluate, or score an LLM with AEON Bench. You run the AEON Bench Pod on the user's machine, point it at a model, run the benchmark, and submit the signed result to the public leaderboard at aeon-bench.com. All work happens on the pod. The mothership only shows the board and accepts…
plate-tectonics-geospatial
Analyze plate tectonics data using GeoPandas, identify points within plates, and calculate distances to boundaries.
data-matching
Matching observation data to simulation output with exact datetime and depth binning.
model-calibration
Calculating RMSE metrics and parameter calibration for lake model validation.
dbscan-custom-metric
Run DBSCAN clustering with a custom distance metric using sklearn, including how to define weighted Euclidean metrics and extract cluster centroids.
greedy-bipartite-matching
Implement greedy bipartite matching for pairing cluster centroids with expert annotations.