Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Identify the best GTM motions and tools across 7 motion types: Inbound, Outbound, Paid Digital, Community, Partners, ABM, and PLG. Use when selecting marketing channels, choosing between inbound and outbound strategy, or planning cross-channel campaigns.
.claude/skills/phuryn-gtm-motions/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 47% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 70% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 69% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 71% | 0% |
Identify and evaluate the best go-to-market motions for your product. This skill analyzes seven proven GTM approaches with specific tools and tactics to help you build a balanced acquisition strategy.
Attract customers through valuable content and thought leadership.
Proactively reach target prospects through direct engagement.
Reach target audiences through paid channels with precision targeting.
Build engaged communities where customers help each other and spread the word.
Leverage partner networks to co-market and reach new audiences.
Treat high-value accounts as individual markets with personalized campaigns.
Drive adoption through the product experience itself with minimal sales friction.
Define product characteristics:
Assess your market dynamics:
Rate fit for your product (1-10 scale):
Select and prioritize 2-4 motions to execute:
Create 90-day implementation roadmap:
Use $ARGUMENTS to pass:
A comprehensive GTM motions analysis including:
Based on Product Compass GTM motion analysis. Provides a systematic approach to balancing customer acquisition across multiple channels.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-13 | pass→pass | 19,270 | 22,257 | +16% | 1 | 1 | 0% | 3,314 | 5,411 | +63% | 0 | 0 | — |
case-21 | pass→pass | 21,053 | 19,839 | -6% | 1 | 1 | 0% | 3,281 | 5,000 | +52% | 0 | 0 | — |
case-07 | pass→pass | 22,871 | 19,251 | -16% | 1 | 1 | 0% | 3,787 | 5,018 | +33% | 0 | 0 | — |
case-08 | fail→pass | 17,991 | 17,369 | -3% | 1 | 1 | 0% | 3,147 | 4,675 | +49% | 0 | 0 | — |
case-09 | fail→pass | 19,477 | 18,653 | -4% | 1 | 1 | 0% | 3,322 | 4,883 | +47% | 0 | 0 | — |
case-14 | fail→pass | 17,628 | 21,501 | +22% | 1 | 1 | 0% | 3,100 | 5,261 | +70% | 0 | 0 | — |
case-10 | fail→pass | 16,437 | 19,679 | +20% | 1 | 1 | 0% | 3,051 | 5,158 | +69% | 0 | 0 | — |
case-11 | fail→pass | 17,279 | 22,375 | +29% | 1 | 1 | 0% | 3,042 | 5,199 | +71% | 0 | 0 | — |
case-01 | fail→pass | 24,931 | 18,079 | -27% | 1 | 1 | 0% | 4,547 | 4,964 | +9% | 0 | 0 | — |
case-12 | pass→pass | 21,149 | 18,251 | -14% | 1 | 1 | 0% | 3,580 | 4,814 | +34% | 0 | 0 | — |
case-02 | fail→pass | 25,399 | 21,249 | -16% | 1 | 1 | 0% | 4,339 | 5,433 | +25% | 0 | 0 | — |
case-03 | pass→pass | 13,890 | 14,522 | +5% | 1 | 1 | 0% | 2,348 | 4,068 | +73% | 0 | 0 | — |
case-04 | pass→pass | 15,402 | 19,899 | +29% | 1 | 1 | 0% | 2,680 | 4,970 | +85% | 0 | 0 | — |
case-05 | pass→pass | 17,676 | 16,903 | -4% | 1 | 1 | 0% | 3,033 | 4,595 | +52% | 0 | 0 | — |
case-06 | pass→pass | 20,179 | 17,736 | -12% | 1 | 1 | 0% | 3,382 | 4,632 | +37% | 0 | 0 | — |
case-15 | pass→pass | 23,565 | 19,158 | -19% | 1 | 1 | 0% | 3,943 | 4,878 | +24% | 0 | 0 | — |
case-16 | fail→pass | 17,932 | 15,203 | -15% | 1 | 1 | 0% | 3,029 | 4,133 | +36% | 0 | 0 | — |
case-17 | fail→pass | 21,352 | 23,136 | +8% | 1 | 1 | 0% | 3,554 | 5,656 | +59% | 0 | 0 | — |
case-18 | fail→pass | 17,904 | 21,764 | +22% | 1 | 1 | 0% | 3,071 | 5,313 | +73% | 0 | 0 | — |
case-19 | fail→pass | 22,890 | 24,756 | +8% | 1 | 1 | 0% | 3,956 | 6,010 | +52% | 0 | 0 | — |
case-20 | fail→pass | 19,961 | 17,909 | -10% | 1 | 1 | 0% | 3,422 | 4,726 | +38% | 0 | 0 | — |
case-22 | pass→pass | 21,384 | 20,603 | -4% | 1 | 1 | 0% | 3,604 | 5,091 | +41% | 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 +55 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.