Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Apply Checkland's CATWOE analysis from a specific stakeholder perspective to reveal how the problem looks from that viewpoint.
.claude/skills/yogsoth-ai-catwoe-analysis/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✓→✓ | ＝ Same ✓ | 6% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 11% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | -18% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | 40% | 0% |
| case-16 | ✗→✗ | ＝ Same ✗ | -42% | 0% |
Subagent — spawned via subagent-spawning/spawn-agent.
One unit = one CATWOE analysis from one stakeholder perspective.
<!-- 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-07 | pass→pass | 18,991 | 19,600 | +3% | 1 | 1 | 0% | 2,894 | 3,080 | +6% | 0 | 0 | — |
case-16 | fail→fail | 15,139 | 7,640 | -50% | 1 | 1 | 0% | 2,453 | 1,413 | -42% | 0 | 0 | — |
case-01 | fail→fail | 14,076 | 6,051 | -57% | 1 | 1 | 0% | 2,314 | 422 | -82% | 0 | 0 | — |
case-02 | fail→fail | 13,567 | 20,707 | +53% | 1 | 1 | 0% | 2,203 | 2,374 | +8% | 0 | 0 | — |
case-03 | fail→fail | 14,775 | 17,810 | +21% | 1 | 1 | 0% | 2,383 | 2,818 | +18% | 0 | 0 | — |
case-04 | pass→pass | 16,057 | 17,133 | +7% | 1 | 1 | 0% | 2,628 | 2,929 | +11% | 0 | 0 | — |
case-05 | pass→pass | 12,500 | 9,976 | -20% | 1 | 1 | 0% | 2,054 | 1,679 | -18% | 0 | 0 | — |
case-06 | pass→pass | 3,635 | 4,381 | +21% | 1 | 1 | 0% | 627 | 880 | +40% | 0 | 0 | — |
case-08 | fail→fail | 16,231 | 14,644 | -10% | 1 | 1 | 0% | 2,451 | 2,368 | -3% | 0 | 0 | — |
case-09 | fail→fail | 15,627 | 11,883 | -24% | 1 | 1 | 0% | 2,477 | 1,839 | -26% | 0 | 0 | — |
case-10 | fail→fail | 14,694 | 18,100 | +23% | 1 | 1 | 0% | 2,213 | 2,811 | +27% | 0 | 0 | — |
case-11 | fail→fail | 15,186 | 15,164 | -0% | 1 | 1 | 0% | 2,370 | 2,346 | -1% | 0 | 0 | — |
case-12 | fail→fail | 14,479 | 12,256 | -15% | 1 | 1 | 0% | 2,208 | 2,001 | -9% | 0 | 0 | — |
case-13 | fail→fail | 16,540 | 18,589 | +12% | 1 | 1 | 0% | 2,604 | 2,943 | +13% | 0 | 0 | — |
case-14 | fail→fail | 16,017 | 18,761 | +17% | 1 | 1 | 0% | 2,387 | 2,903 | +22% | 0 | 0 | — |
case-15 | fail→fail | 13,306 | 9,667 | -27% | 1 | 1 | 0% | 2,157 | 1,668 | -23% | 0 | 0 | — |
case-17 | fail→fail | 15,590 | 17,556 | +13% | 1 | 1 | 0% | 2,381 | 2,795 | +17% | 0 | 0 | — |
case-18 | fail→fail | 14,561 | 17,255 | +19% | 1 | 1 | 0% | 2,205 | 2,846 | +29% | 0 | 0 | — |
case-19 | fail→fail | 15,870 | 17,050 | +7% | 1 | 1 | 0% | 2,384 | 2,744 | +15% | 0 | 0 | — |
case-20 | fail→fail | 14,166 | 12,367 | -13% | 1 | 1 | 0% | 2,183 | 1,891 | -13% | 0 | 0 | — |
case-21 | fail→fail | 14,822 | 17,439 | +18% | 1 | 1 | 0% | 2,303 | 2,689 | +17% | 0 | 0 | — |
case-22 | fail→fail | 14,285 | 8,380 | -41% | 1 | 1 | 0% | 2,527 | 1,447 | -43% | 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, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of 0 percentage points is the difference between those two pass rates over the 21 comparable cases.
Other measured skills in the registry, with their headline benchmark lift.