Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/excursion-departure
Leave the problem entirely and explore an unrelated domain. Produces excursion domain discoveries for later force-fitting.
Passed 6 of 17 test cases with the skill, and 4 of 17 without it.
and 1 more in the full report
3 fixed5 passed either way15 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
We have been banging our heads against a persistent memory leak in our C++ service for hours. We need to perform an excursion departure into radio astronomy to clear our minds. I might just start writing astronomy notes right here, but what is the required method to execute this excursion departure properly?
| Checked | Without skill | With skill |
|---|---|---|
| prescribes spawn-agent to execute the excursion | Missed | Passed |
| notes that fresh subagent context avoids contamination from problem-solving intent | Missed | Passed |
The instructions your model reads when the skill loads.
Leave the problem entirely and explore an unrelated domain.
Subagent — spawned via subagent-spawning/spawn-agent skill.
Excursion departure requires genuine cognitive distance from the problem. Benefits from a fresh context that is not contaminated by problem-solving intent, enabling true discovery in the excursion domain.
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use |
|---|---|
| spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. |
test cases passed, vs 4 / 17 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.