Salient click probe
Skill secondorderai/ouroboros/benchmarks/arc-agi-3/kaggle/skills/salient-click-probe
Ouroboros is an Agent Harness, CLI and Desktop App with Self-Improvement layer
npx -y skills add secondorderai/ouroboros --skill salient-click-probeAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
When coordinate clicks are available but no board model is confident, probe visible compact non-HUD objects before raw fallback actions.
The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
0.9 KB, as published. Nobody here has run it
Salient Click Probe
Use this skill when coordinate clicks are legal but the frame does not yet have a confident regular-board model. Generate click probes from visible compact foreground objects, preferring non-HUD objects with stable centers.
Skip coordinates that are known duds, known dangerous edges, or already tried from the current state. This skill is for targeted probing only; it must not perform blind coordinate sweeps.
Keep the skill generic. Do not include public-game walkthroughs or exact target coordinates learned from previous public runs.