Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Analyze competitive landscape and market positioning. Use when user says 'competitive analysis', 'positioning', 'who are our competitors', 'benchmark', 'market analysis', or any reference to competitors, market positioning, or competitive advantages.
.claude/skills/evolution-foundation-sage-competitive-analysis/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -11% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 35% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -19% | 0% |
Skill to analyze the competitive landscape of Evolution Foundation and identify positioning opportunities.
Always respond in English.
Fetch current Evolution metrics:
/int-github-review)/int-stripe)Use WebSearch/WebFetch to research the main competitors in the space of:
For each competitor, gather:
Create positioning matrix:
| Dimension | Evolution | Concorrente A | Concorrente B | |----------|-----------|--------------|--------------| | Model | Open source + SaaS | SaaS only | Enterprise | | Price | Freemium + plans | R$X/mês | R$X/mês | | WhatsApp Unofficial | ✅ Baileys | ❌ | ❌ | | WhatsApp Cloud API | ✅ | ✅ | ✅ | | Integrated CRM | ✅ Evo CRM | ❌ | ✅ | | Community | ✅ Discord + open source | ❌ | ❌ | | IA/Agentes | ✅ Evo AI | Parcial | ❌ |
Save to workspace/strategy/analyses/[C] YYYY-MM-DD-competitive.md
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-09 | fail→fail | 15,830 | 17,618 | +11% | 1 | 1 | 0% | 2,307 | 3,286 | +42% | 0 | 0 | — |
case-07 | fail→pass | 19,217 | 20,814 | +8% | 1 | 1 | 0% | 2,779 | 3,538 | +27% | 0 | 0 | — |
case-06 | pass→pass | 20,167 | 17,128 | -15% | 1 | 1 | 0% | 2,864 | 2,944 | +3% | 0 | 0 | — |
case-01 | fail→fail | 24,109 | 30,446 | +26% | 1 | 1 | 0% | 3,758 | 5,335 | +42% | 0 | 0 | — |
case-02 | fail→fail | 36,017 | 8,278 | -77% | 1 | 1 | 0% | 5,455 | 967 | -82% | 0 | 0 | — |
case-03 | fail→fail | 19,329 | 6,884 | -64% | 1 | 1 | 0% | 2,981 | 906 | -70% | 0 | 0 | — |
case-04 | fail→pass | 19,007 | 13,017 | -32% | 1 | 1 | 0% | 2,853 | 2,526 | -11% | 0 | 0 | — |
case-05 | fail→fail | 11,638 | 17,111 | +47% | 1 | 1 | 0% | 1,740 | 2,555 | +47% | 0 | 0 | — |
case-08 | fail→pass | 16,935 | 25,018 | +48% | 1 | 1 | 0% | 2,649 | 3,567 | +35% | 0 | 0 | — |
case-10 | fail→fail | 14,278 | 14,540 | +2% | 1 | 1 | 0% | 2,134 | 2,739 | +28% | 0 | 0 | — |
case-11 | fail→pass | 23,883 | 24,585 | +3% | 1 | 1 | 0% | 3,645 | 3,750 | +3% | 0 | 0 | — |
case-12 | fail→fail | 15,681 | 12,269 | -22% | 1 | 1 | 0% | 2,384 | 2,478 | +4% | 0 | 0 | — |
case-13 | fail→pass | 10,986 | 4,889 | -55% | 1 | 1 | 0% | 1,491 | 1,202 | -19% | 0 | 0 | — |
case-14 | pass→pass | 10,576 | 4,649 | -56% | 1 | 1 | 0% | 1,588 | 1,189 | -25% | 0 | 0 | — |
case-15 | pass→pass | 25,244 | 23,535 | -7% | 1 | 1 | 0% | 3,674 | 4,266 | +16% | 0 | 0 | — |
case-16 | pass→pass | 15,580 | 11,861 | -24% | 1 | 1 | 0% | 2,671 | 2,411 | -10% | 0 | 0 | — |
case-17 | pass→pass | 13,483 | 13,064 | -3% | 1 | 1 | 0% | 2,120 | 2,507 | +18% | 0 | 0 | — |
case-18 | pass→pass | 17,753 | 12,625 | -29% | 1 | 1 | 0% | 2,819 | 2,565 | -9% | 0 | 0 | — |
case-19 | fail→pass | 11,993 | 4,975 | -59% | 1 | 1 | 0% | 1,793 | 1,293 | -28% | 0 | 0 | — |
case-20 | fail→fail | 15,868 | 8,391 | -47% | 1 | 1 | 0% | 2,467 | 1,792 | -27% | 0 | 0 | — |
case-21 | fail→pass | 17,757 | 18,449 | +4% | 1 | 1 | 0% | 2,655 | 3,279 | +24% | 0 | 0 | — |
case-22 | fail→pass | 15,662 | 14,819 | -5% | 1 | 1 | 0% | 2,289 | 2,844 | +24% | 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 20 counted toward the lift figure. The other 2 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 +36 percentage points is the difference between those two pass rates over the 20 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
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.