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 flood-detectiongit 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/flood-detection)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/flood-detection"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/flood-detection/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/flood-detection"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/flood-detection.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 | $0.00040 | $0.00825 |
| Opus 5 | $0.00020 | $0.00413 |
| Sonnet 5 | $0.00008 | $0.00165 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
flood-detection 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 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.
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:
- flood-detection — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flood Detection Guide
Overview
Flood detection involves comparing observed water levels against established flood stage thresholds. This guide covers how to process water level data and identify flood events.
Flood Stage Definition
According to the National Weather Service, flood stage is the water level at which overflow of the natural banks begins to cause damage. A flood event occurs when:
water_level >= flood_stage_threshold
Aggregating Instantaneous Data to Daily
USGS instantaneous data is recorded at ~15-minute intervals. For flood detection, aggregate to daily maximum:
# df is DataFrame from nwis.get_iv() with datetime index
# gage_col is the column name containing water levels
daily_max = df[gage_col].resample('D').max()
Why Daily Maximum?
| Aggregation | Use Case |
|---|---|
max() |
Flood detection - captures peak water level |
mean() |
Long-term trends - may miss short flood peaks |
min() |
Low flow analysis |
Detecting Flood Days
Compare daily maximum water level against flood threshold:
flood_threshold = <threshold_from_nws> # feet
# Count days with flooding
flood_days = (daily_max >= flood_threshold).sum()
# Get specific dates with flooding
flood_dates = daily_max[daily_max >= flood_threshold].index.tolist()
Processing Multiple Stations
flood_results = []
for site_id, site_data in all_data.items():
daily_max = site_data['water_levels'].resample('D').max()
threshold = thresholds[site_id]['flood']
days_above = int((daily_max >= threshold).sum())
if days_above > 0:
flood_results.append({
'station_id': site_id,
'flood_days': days_above
})
# Sort by flood days descending
flood_results.sort(key=lambda x: x['flood_days'], reverse=True)
Flood Severity Classification
If multiple threshold levels are available:
def classify_flood(water_level, thresholds):
if water_level >= thresholds['major']:
return 'major'
elif water_level >= thresholds['moderate']:
return 'moderate'
elif water_level >= thresholds['flood']:
return 'minor'
elif water_level >= thresholds['action']:
return 'action'
else:
return 'normal'
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 · 128 lines · 40 tokens per session scan A 14e55948af7a
flood-detection is a skill published in the GitHub repository benchflow-ai/skillsbench (1,764 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 825 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.