GitHub
Skills harvested from GitHub repositories
14810 skills availablemotor-model-dynamics
Two modules form the physics layer of the simulator: Motor model — maps desired [F, Mx, My, Mz] → desired motor RPMs → a...
vital-sign-extraction
Given a cleaned 1-D periodic signal (radar phase, WiFi CSI, PPG, piezo), estimate heart rate and breathing rate in bpm. ...
task-review
End-to-end review of a SkillsBench task PR. Two artifacts are produced: a human-readable .txt report, and a pr<N>.zip bu...
grpo
Group Relative Policy Optimization (GRPO) is a policy gradient method that eliminates the need for a learned critic by c...
geometric-layout-repair
Use this skill when the deliverable is a repaired plan-view layout and a modified CAD/DXF file, not a rendered drawing. ...
prefix-cache-replay
Modern LLM serving systems — vLLM, SGLang, Mooncake — pack the KV tensors of a prompt into fixed-size blocks of blocksiz...
nanogpt-training
Training GPT-2 scale models (124M parameters) efficiently on a single GPU. It provides: GPT-124M Architecture: Standard ...
multimodal-fusion
When working with video files, you can significantly improve speaker diarization by combining audio features with visual...
plot-quadrotor
Given actual and desired state matrices from a simulation run, generates three figures and saves them as PNG files. stat...
skillsbench
Benchmark evaluating how well AI agents use skills. GitHub: https://github.com/benchflow-ai/skillsbench BenchFlow SDK: h...
stepinfo-3d
| Scenario | Metric to use | |---|---| | Pure z-step (hover, takeoff, land) | 1D stepinfo on z signal | | Diagonal fligh...
ada-plan-view-accessibility
Use this skill for plan-view accessibility checks. It is not a full legal ADA compliance review; apply only the geometri...
constraint-parser
This skill parses the constraints from raw email text containing a meeting scheduling request. Raw email text containing...
modal-gpu
Modal is a serverless platform for running Python code on cloud GPUs. It provides: Serverless GPUs: On-demand access to ...
mhc-algorithm
mHC (Manifold-Constrained Hyper-Connections) stabilizes deep network training by constraining residual mixing matrices t...
trl
TRL is organized around a trainer hierarchy that extends Hugging Face transformers.Trainer. trl/ ├── trainer/ │ ├── gr...
mip-solver-and-solution-audit
A valid optimization submission has one final solution, one set of recomputed metrics, and one truthful solver report. T...
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. ...
transaction-concurrency-control-foundations
Use this skill when you need shared vocabulary + decision lenses for transaction concurrency control before analyzing a ...
milp-solver-workflow
Use this skill for binary/integer decisions, linear constraints, and linear or piecewise-linear objectives. It is useful...
architectural-dxf-extraction
Use this skill for 2D architectural DXF plans where the CAD file is the authoritative source. Treat screenshots as orien...
rl-post-training
RL post-training optimizes a language model's policy using reward signals. The standard pipeline: prompt → generate comp...
ortools-pickup-delivery-routing
Use this skill when each job has related pickup and dropoff or delivery events that must be served together. Apply it af...
position-controller-trajectory-planner
Two cooperating modules form the outer loop: Trajectory planner — converts waypoints + modes into a (15 × maxiter) desir...