Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/false-gap-filtering
Detect false gaps — search failures, already-solved gaps, and inherently unanswerable questions masquerading as research gaps.
Passed 8 of 21 test cases with the skill, and 4 of 21 without it.
and 3 more in the full report
5 fixed3 passed either way13 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are screening four separate gap candidates in neuromorphic computing architectures for neuromorphic tactile sensing. Can we combine all four candidates into a single assessment unit to conserve resources?
| Checked | Without skill | With skill |
|---|---|---|
| Requires one distinct budget unit for each individual gap candidate. | Missed | Passed |
The instructions your model reads when the skill loads.
Distinguish genuine research gaps from artifacts of search failure.
Subagent — spawned via subagent-spawning/spawn-agent.
One unit = one false-gap assessment for a single gap candidate.
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 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.