Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries. Use when the user wants market sizing, competitor comparisons, fund research, technology scans, or research that informs business decisions.
.claude/skills/affaan-m-market-research/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 100% | 20 |
| gemini-3.1-pro-preview | 100% | 1 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 33% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 31% | 0% |
产出支持决策的研究，而非研究表演。
收集：
收集：
使用：
收集：
默认结构：
在交付前检查：
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 23,267 | 24,741 | +6% | 1 | 1 | 0% | 3,792 | 4,493 | +18% | 0 | 0 | — |
case-02 | fail→fail | 22,430 | 26,351 | +17% | 1 | 1 | 0% | 3,571 | 4,599 | +29% | 0 | 0 | — |
case-03 | fail→fail | 23,599 | 28,421 | +20% | 1 | 1 | 0% | 3,819 | 5,104 | +34% | 0 | 0 | — |
case-04 | fail→pass | 31,651 | 28,472 | -10% | 1 | 1 | 0% | 5,091 | 5,010 | -2% | 0 | 0 | — |
case-05 | fail→pass | 30,285 | 26,747 | -12% | 1 | 1 | 0% | 5,080 | 5,088 | +0% | 0 | 0 | — |
case-06 | pass→pass | 24,616 | 19,722 | -20% | 1 | 1 | 0% | 3,655 | 3,575 | -2% | 0 | 0 | — |
case-07 | fail→pass | 22,476 | 23,714 | +6% | 1 | 1 | 0% | 3,561 | 4,108 | +15% | 0 | 0 | — |
case-08 | fail→pass | 23,094 | 25,232 | +9% | 1 | 1 | 0% | 3,348 | 4,456 | +33% | 0 | 0 | — |
case-09 | fail→pass | 29,567 | 27,822 | -6% | 1 | 1 | 0% | 3,812 | 5,002 | +31% | 0 | 0 | — |
case-10 | fail→pass | 22,609 | 25,935 | +15% | 1 | 1 | 0% | 3,773 | 4,595 | +22% | 0 | 0 | — |
case-11 | fail→pass | 26,868 | 30,531 | +14% | 1 | 1 | 0% | 3,994 | 4,959 | +24% | 0 | 0 | — |
case-12 | fail→pass | 33,936 | 25,655 | -24% | 1 | 1 | 0% | 3,766 | 4,836 | +28% | 0 | 0 | — |
case-13 | fail→pass | 23,345 | 22,461 | -4% | 1 | 1 | 0% | 3,574 | 4,112 | +15% | 0 | 0 | — |
case-14 | fail→fail | 28,126 | 31,630 | +12% | 1 | 1 | 0% | 4,762 | 5,739 | +21% | 0 | 0 | — |
case-15 | fail→pass | 25,885 | 28,106 | +9% | 1 | 1 | 0% | 4,071 | 5,146 | +26% | 0 | 0 | — |
case-16 | fail→pass | 25,670 | 27,642 | +8% | 1 | 1 | 0% | 3,908 | 5,003 | +28% | 0 | 0 | — |
case-17 | pass→pass | 21,975 | 27,166 | +24% | 1 | 1 | 0% | 3,487 | 4,774 | +37% | 0 | 0 | — |
case-18 | fail→pass | 24,733 | 27,465 | +11% | 1 | 1 | 0% | 3,701 | 4,576 | +24% | 0 | 0 | — |
case-19 | fail→pass | 32,020 | 32,633 | +2% | 1 | 1 | 0% | 4,842 | 5,401 | +12% | 0 | 0 | — |
case-20 | pass→pass | 15,527 | 20,754 | +34% | 1 | 1 | 0% | 3,325 | 5,141 | +55% | 0 | 0 | — |
case-21 | pass→pass | 12,291 | 16,463 | +34% | 1 | 1 | 0% | 1,964 | 3,239 | +65% | 0 | 0 | — |
case-22 | pass→pass | 21,617 | 21,119 | -2% | 1 | 1 | 0% | 3,439 | 3,765 | +9% | 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 +59 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.