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 radar-signal-processinggit 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/radar-signal-processing)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/radar-signal-processing"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/radar-signal-processing/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/radar-signal-processing"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/radar-signal-processing.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 | $0.00109 | $0.00626 |
| Opus 5 | $0.00055 | $0.00313 |
| Sonnet 5 | $0.00022 | $0.00125 |
| Haiku 4.5 | $0.00011 | $0.00063 |
Grade A, and why
radar-signal-processing 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:
- radar-signal-processing — 100% identical, 0 lines differ
What it actually says
Radar Signal Processing
Get from a raw binary I/Q capture to a clean 1-D phase trace that downstream vital-signs / motion analysis can consume.
Pipeline (do every step in order)
- Parse binary I/Q to complex samples. Use the JSON/YAML sidecar to determine format — never assume. See references/iq-formats.md.
- (FMCW only) Range FFT across fast time → 2-D range matrix. CW skips this step.
- Remove static clutter. Subtract the temporal mean:
- CW:
iq -= iq.mean() - FMCW:
R -= R.mean(axis=0, keepdims=True)on the range matrix
- CW:
- (FMCW only) Pick the subject range bin. See references/range-bin.md.
- Extract phase with unwrap:
phase = np.unwrap(np.angle(iq_or_bin)) phase -= phase.mean() - If
fs >= 500 Hzand downstream needs sub-Hz filtering, decimate first:from scipy.signal import decimate phase_ds = decimate(phase, q=int(fs/50), ftype='iir', zero_phase=True) fs_new = fs / int(fs/50) # ~50 Hz target
Critical rules
| rule | why (short) |
|---|---|
| Use phase, not magnitude | 1 mm motion at 24 GHz ≈ 1 rad; magnitude is ~40 dB worse SNR |
Clutter removal goes before np.angle |
DC offset anchors phase off zero, eats the unwrap budget |
| Never design a 0.1 Hz filter against a 2 kHz signal | SciPy biquad silently NaNs; decimate to ~50 Hz first |
Never argmax(magnitude) across all range bins |
DC bin (bin 0) and static reflectors dominate — restrict to a physical subject-range window |
When things go wrong
If the output is garbage, walk through references/debugging.md in order — it's fast and catches most ingestion/SNR bugs.
Not in scope
Pulse/UWB time-of-flight, MIMO angle-of-arrival, Doppler-only gesture radar.
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.
- 9d ago First seen · 46 lines · 109 tokens per session scan A 0f1194ad676b
radar-signal-processing is a skill published in the GitHub repository benchflow-ai/skillsbench (1,764 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 109 tokens to every session and 626 once invoked, about $0.0005 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
ruview-applications
Run RuView sensing applications — presence/occupancy, breathing & heart rate, activity & fall detection, 17-keypoint pose estimation (WiFlow), sleep monitoring & apnea screening, environment mapping, Mass Casualty Assessment (MAT), and the 3D point-cloud fusion demo. Use when someone wants to actually do something…
lab-hardware-cad
Design custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a research…
calibrate-room
Run the ADR-151 per-room calibration pipeline — baseline → enroll → extract → train → a bank of small specialists (presence/posture/breathing/heartbeat/restlessness/anomaly).
i4h-catheter-navigation
Overview of workflows/catheternavigation/ (fluorosim DRR, XPBD physics, vasculature digital twin). Use when the user asks what the catheter navigation workflow is, what's supported, or where to start.
opentrons-integration
Official Opentrons Protocol API for OT-2 and Flex robots. Use when writing protocols specifically for Opentrons hardware with full access to Protocol API v2 features. Best for production Opentrons protocols, official API compatibility. For multi-vendor automation or broader equipment control use pylabrobot.
pylabrobot
Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API…