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 converting natural language flight commands into waypoints and timing for a drone simulator. Covers parsing commands like "Take off to X m height in Y seconds", "Hover at X m height for Y seconds", "Fly from (x,y,z) to (x',y',z') in T seconds", and "Land from X m height in Y seconds" into structured (4×n) waypoint arrays and segment mode lists.
Converts human-readable flight commands into structured waypoints compatible with the drone simulator's trajectory planner. Each command maps to one flight segment with a mode tag (takeoff, hover, fly, land).
waypoints : (4 x n) numpy array — rows are [x, y, z, yaw]
waypoint_times : (n,) numpy array — arrival time for each waypoint [seconds]
modes : list of (n-1) strings — one mode per segment between waypoints
| Command pattern | Mode |
|---|---|
Take off to <h> m height in <t> seconds | 'takeoff' |
Hover at <h> m height for <t> seconds | 'hover' |
Fly from (<x>,<y>,<z>) to (<x'>,<y'>,<z'>) in <t> seconds | 'fly' |
Land from <h> m height in <t> seconds | 'land' |
Use a stateful parser class that accumulates waypoints, times, and modes as it processes each command line:
t=0 if the list is empty.npx skills add benchflow-ai/skillsbench --skill flight-plan-parserHow 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.