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 implementing the outer control loop for a quadrotor — position PID control (position/velocity error → thrust and desired acceleration) and trajectory planning from flight-plan waypoints (takeoff, hover, fly, land segments → smooth 15-row state matrix).
Two cooperating modules form the outer loop:
(15 × max_iter) desired state matrix using cubic splines per segmentF and desired acceleration| Mode | Behaviour |
|---|---|
'hover' | Constant position, zero velocity and acceleration |
'takeoff' | Cubic spline from ground to target height |
'fly' | Cubic spline from start position to end position |
'land' | Cubic spline from current height to ground |
Build a callable object that steps through a cubic spline one sample at a time:
__init__: fit a CubicSpline over all waypoints vs. their arrival times; store dt = 1/sample_rate and initialise t_current to the first waypoint time.__call__: evaluate the spline at t_current for position, first derivative for velocity, and second derivative for acceleration; advance t_current by dt; return (pos, quaternion, vel, acc, zeros(3)).npx skills add benchflow-ai/skillsbench --skill position-controller-trajectory-plannerHow 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.