Menu
Recover the target when it is lost or poorly centered. Use for navigation tasks where the agent must regain visibility without wandering indefinitely.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Fly around a visible target and station directly above it at a safe distance. Use for reposition tasks that must end overhead of the target rather than in front of it.
Always-on operational baseline for SpaceMind. Defines shared coordinates, action policy, safety guards, observability rules, and perception workflow for all tasks.
Image-first laboratory navigation policy for ground-robot experiments. Use when the task must be solved with raw current images, conservative motion, and no oracle geometry.
Recover a temporarily lost target in the laboratory with bounded planar search and no blind forward motion.
Safely approach a visible laboratory satellite target and stop in a conservative near-front hold using only current images and motion tools.
Diagnose the laboratory target from raw image evidence, conservative viewpoint changes, and optional code support.
Based on SOC occupation classification
| name | target-recovery |
| description | Recover the target when it is lost or poorly centered. Use for navigation tasks where the agent must regain visibility without wandering indefinitely. |
| metadata | {"skill_kind":"helper","routing_summary":"Add when the mission may lose the target or needs a structured visibility recovery policy.","routing_keywords":["recover","target lost","regain visibility","poorly centered","reacquire target"]} |
If the target was just lost after a specific action (e.g., a yaw or position change), first reverse that exact action to return to the state where the target was last visible. For example:
set_attitude(0, 0, +20) → try set_attitude(0, 0, -20)set_position(dx=1, dy=0, dz=0) → try set_position(dx=-1, dy=0, dz=0)After the reverse, re-check the image and the [Sensor] LiDAR block. If the target reappears, re-center it and resume the mission.
If reversal does not help or you do not know which action caused the loss, use the last known relative direction with small yaw or pitch corrections (10-15°):
set_attitude(0, 0, +15)set_attitude(0, 0, -15)set_attitude(-15, 0, 0)set_attitude(+15, 0, 0)If the target is still visible but merely off-center, prefer a small yaw correction to re-center it before any forward motion.
If there is no reliable last known direction and reversal did not work, sweep yaw from the loss heading to cover ±90°. First go one direction (e.g. right to +90°), then turn past the loss heading and continue to the opposite side (e.g. -90°). Remember that yaw deltas accumulate: from +90°, three steps of -30° only returns to 0°, not to -90° — you must keep going. Check the image and the [Sensor] LiDAR block after every step. After the yaw sweep, try pitch adjustments (±15°) before giving up.
After repeated failed recovery attempts, stop searching indefinitely and call terminate_navigation(...) with a target-lost reason.