Ask me what skills you need
What are you building?
Tell me what you're working on and I'll find the best agent skills for you.
Use this skill when simulating quadrotor physical dynamics — mapping desired thrust/moments to individual motor RPMs via a propeller allocation matrix, applying first-order motor lag, and integrating the nonlinear equations of motion (translational and rotational) using RK45.
Two modules form the physics layer of the simulator:
[F, Mx, My, Mz] → desired motor RPMs → applies first-order lag → returns actual thrust and momentsThe 4×4 allocation matrix maps [F, Mx, My, Mz] to squared motor RPMs. For an X-frame with arm length d, thrust coefficient cT, and torque coefficient cQ:
motor: 1 2 3 4
Thrust: +cT +cT +cT +cT
Roll (Mx): 0 +d·cT 0 -d·cT
Pitch (My): -d·cT 0 +d·cT 0
Yaw (Mz): -cQ +cQ -cQ +cQ
prop_matrix from cT, cQ, and d.prop_matrix @ rpm_sq = [F, Mx, My, Mz] for rpm_sq (desired squared RPMs).sqrt of each element (clamp negatives to 0 first), then clip to [rpm_min, rpm_max].rpm_dot = km * (rpm_desired - rpm_current).npx skills add benchflow-ai/skillsbench --skill motor-model-dynamicsHow clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
Clear and well structured, with only minor parts that might need a second read.
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
Mostly actionable with clear steps; only a few small gaps remain.