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 vital-sign-extractiongit 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/vital-sign-extraction)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/vital-sign-extraction"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/vital-sign-extraction/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/vital-sign-extraction"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/vital-sign-extraction.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 | $0.00128 | $0.01077 |
| Opus 5 | $0.00064 | $0.00539 |
| Sonnet 5 | $0.00026 | $0.00215 |
| Haiku 4.5 | $0.00013 | $0.00108 |
Grade A, and why
vital-sign-extraction 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 9d 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:
- vital-sign-extraction — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vital-Sign Extraction
Given a cleaned 1-D periodic signal (radar phase, WiFi CSI, PPG, piezo), estimate heart rate and breathing rate in bpm.
Upstream ingestion of radar captures is the radar-signal-processing skill. This skill picks up after a 1-D signal is extracted.
Pipeline (do every step)
- Split into BR and HR bands with two separate bandpasses:
- BR:
butter(4, [0.08, 0.5], btype='band', fs=fs)— 4.8–30 bpm - HR:
butter(4, [0.7, 3.0], btype='band', fs=fs)— 42–180 bpm
- BR:
- Peak frequency via zero-padded Welch PSD:
nperseg = min(len(x), int(fs * 25)) f, p = welch(x, fs=fs, nperseg=nperseg, noverlap=nperseg//2, nfft=8*nperseg, detrend='constant') in_band = (f >= lo) & (f <= hi) peak_hz = f[in_band][np.argmax(p[in_band])] - HR harmonic rejection — always run:
f_sub = f_peak / 2.0 if 0.7 <= f_sub <= 3.0: p_sub = np.interp(f_sub, f, p) p_top = np.interp(f_peak, f, p) if p_sub > 0.5 * p_top: f_peak = f_sub # the peak was the 2nd harmonic hr_bpm = f_peak * 60 - Cross-check with autocorrelation:
Ifac = np.correlate(x - x.mean(), x - x.mean(), mode='full') ac = ac[len(ac)//2:] / ac[len(ac)//2] lag = int(fs/f_hi) + np.argmax(ac[int(fs/f_hi):int(fs/f_lo)]) bpm_ac = 60 * fs / lagabs(bpm_ac - bpm_psd) > 5, flag as low confidence.
Decision rules
| If | Then |
|---|---|
f_peak/2 in HR band and p_sub > 0.5 × p_top |
Pick sub-harmonic (fundamental) |
| PSD and autocorrelation disagree by > 5 bpm | Flag low confidence; do not commit to one value |
| BR estimate < 10 bpm (slow breather) | Expect HR-band contamination — see references/harmonic-pitfalls.md |
| HR > 150 bpm (tachycardia) | Widen HR band upper to 3.3 Hz, re-estimate |
| Clip < 15 s long | PSD bin spacing > tolerance — prefer autocorrelation or flag inconclusive |
Sanity checks before reporting
What ships with it
2 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.
- 9d ago First seen · 73 lines · 128 tokens per session scan A aff09b876c5c
vital-sign-extraction is a skill published in the GitHub repository benchflow-ai/skillsbench (1,764 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 128 tokens to every session and 1,077 once invoked, about $0.0006 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.