Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate "How Might We" questions at different scope levels (narrow, medium, broad). Ensures each is actionable without being prescriptive.
.claude/skills/yogsoth-ai-hmw-formulation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-20 | ✓→✓ | ＝ Same ✓ | 12% | 0% |
| case-21 | ✓→✓ | ＝ Same ✓ | 36% | 0% |
| case-22 | ✓→✓ | ＝ Same ✓ | -3% | 0% |
| case-01 | ✗→✗ | ＝ Same ✗ | -30% | 0% |
| case-02 | ✗→✗ | ＝ Same ✗ | -21% | 0% |
Generate generative How Might We research questions.
Subagent — spawned via subagent-spawning/spawn-agent.
One unit = one HMW formulation pass.
<!-- BEGIN available-tables (generated) -->
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. |
<!-- END available-tables (generated) -->
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 13,266 | 39,974 | +201% | 1 | 1 | 0% | 2,085 | 1,456 | -30% | 0 | 0 | — |
case-02 | fail→fail | 14,280 | 11,776 | -18% | 1 | 1 | 0% | 2,264 | 1,781 | -21% | 0 | 0 | — |
case-03 | fail→fail | 11,080 | 6,907 | -38% | 1 | 1 | 0% | 1,830 | 1,243 | -32% | 0 | 0 | — |
case-04 | fail→fail | 12,250 | 11,650 | -5% | 1 | 1 | 0% | 2,002 | 1,920 | -4% | 0 | 0 | — |
case-05 | fail→fail | 13,330 | 11,817 | -11% | 1 | 1 | 0% | 2,033 | 1,996 | -2% | 0 | 0 | — |
case-06 | fail→fail | 13,933 | 11,420 | -18% | 1 | 1 | 0% | 2,130 | 1,950 | -8% | 0 | 0 | — |
case-07 | fail→fail | 17,299 | 11,076 | -36% | 1 | 1 | 0% | 2,430 | 1,891 | -22% | 0 | 0 | — |
case-08 | fail→fail | 16,171 | 10,788 | -33% | 1 | 1 | 0% | 2,349 | 1,732 | -26% | 0 | 0 | — |
case-09 | fail→fail | 11,678 | 9,564 | -18% | 1 | 1 | 0% | 1,795 | 1,555 | -13% | 0 | 0 | — |
case-10 | fail→fail | 14,695 | 10,976 | -25% | 1 | 1 | 0% | 2,133 | 1,816 | -15% | 0 | 0 | — |
case-11 | fail→fail | 12,244 | 10,900 | -11% | 1 | 1 | 0% | 1,914 | 1,664 | -13% | 0 | 0 | — |
case-12 | fail→fail | 12,114 | 9,288 | -23% | 1 | 1 | 0% | 1,793 | 1,526 | -15% | 0 | 0 | — |
case-13 | fail→fail | 16,938 | 12,357 | -27% | 1 | 1 | 0% | 2,446 | 1,983 | -19% | 0 | 0 | — |
case-14 | fail→fail | 13,696 | 11,055 | -19% | 1 | 1 | 0% | 2,061 | 1,740 | -16% | 0 | 0 | — |
case-15 | fail→fail | 14,891 | 9,079 | -39% | 1 | 1 | 0% | 2,037 | 1,323 | -35% | 0 | 0 | — |
case-16 | fail→fail | 11,221 | 13,236 | +18% | 1 | 1 | 0% | 1,788 | 1,931 | +8% | 0 | 0 | — |
case-17 | fail→fail | 12,680 | 9,622 | -24% | 1 | 1 | 0% | 1,924 | 1,661 | -14% | 0 | 0 | — |
case-18 | fail→fail | 15,997 | 18,646 | +17% | 1 | 1 | 0% | 2,262 | 2,793 | +23% | 0 | 0 | — |
case-19 | fail→fail | 17,063 | 12,247 | -28% | 1 | 1 | 0% | 2,305 | 1,733 | -25% | 0 | 0 | — |
case-20 | pass→pass | 14,304 | 14,423 | +1% | 1 | 1 | 0% | 2,383 | 2,675 | +12% | 0 | 0 | — |
case-21 | pass→pass | 3,584 | 4,109 | +15% | 1 | 1 | 0% | 512 | 697 | +36% | 0 | 0 | — |
case-22 | pass→pass | 10,602 | 9,509 | -10% | 1 | 1 | 0% | 2,124 | 2,059 | -3% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of 0 percentage points is the difference between those two pass rates over the 22 comparable cases.
Other measured skills in the registry, with their headline benchmark lift.