Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Analyse competitor moves and translate them into strategic implications for your product roadmap. Use when a competitor announces a new feature, pricing change, partnership, or strategic shift, or when producing a periodic competitive intelligence report. Produces a categorised signal analysis with reactive-vs-proactive assessment, threat ratings, specific roadmap implications, and recommended responses with owners. For a recurring whole-market briefing use competitive-intelligence-monitor inste
.claude/skills/mohitagw15856-competitor-signal-tracker/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 64% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 4% | 0% |
Turn scattered competitor information into structured strategic intelligence — not just "what they did" but "what it means for us."
Ask the user for these if not provided:
Signal: What they did] Signal Type: Product / Pricing / Hiring / Partnership / Messaging] Reactive or Proactive: assessment] Threat Level: High / Medium / Low / Watch] Implication for Us: Specific connection to our roadmap or strategy] Recommended Response: Action + owner + timeline]
2-3 sentences on the overall competitive landscape shift this period]
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 14,144 | 10,865 | -23% | 1 | 1 | 0% | 2,437 | 2,486 | +2% | 0 | 0 | — |
case-02 | fail→pass | 17,672 | 14,898 | -16% | 1 | 1 | 0% | 2,960 | 3,248 | +10% | 0 | 0 | — |
case-03 | fail→pass | 12,439 | 8,797 | -29% | 1 | 1 | 0% | 2,146 | 2,216 | +3% | 0 | 0 | — |
case-04 | fail→pass | 16,510 | 10,789 | -35% | 1 | 1 | 0% | 2,776 | 2,489 | -10% | 0 | 0 | — |
case-05 | pass→pass | 12,333 | 8,827 | -28% | 1 | 1 | 0% | 1,883 | 2,317 | +23% | 0 | 0 | — |
case-06 | fail→pass | 7,553 | 7,385 | -2% | 1 | 1 | 0% | 1,131 | 1,857 | +64% | 0 | 0 | — |
case-07 | pass→pass | 14,464 | 9,487 | -34% | 1 | 1 | 0% | 2,524 | 2,295 | -9% | 0 | 0 | — |
case-08 | pass→pass | 13,284 | 11,437 | -14% | 1 | 1 | 0% | 2,126 | 2,444 | +15% | 0 | 0 | — |
case-09 | fail→pass | 14,874 | 11,332 | -24% | 1 | 1 | 0% | 2,434 | 2,533 | +4% | 0 | 0 | — |
case-10 | fail→fail | 13,813 | 4,601 | -67% | 1 | 1 | 0% | 2,303 | 1,368 | -41% | 0 | 0 | — |
case-11 | fail→pass | 12,232 | 10,989 | -10% | 1 | 1 | 0% | 1,997 | 2,386 | +19% | 0 | 0 | — |
case-12 | fail→pass | 11,569 | 9,404 | -19% | 1 | 1 | 0% | 1,778 | 2,326 | +31% | 0 | 0 | — |
case-13 | pass→pass | 12,809 | 8,823 | -31% | 1 | 1 | 0% | 1,936 | 2,056 | +6% | 0 | 0 | — |
case-14 | pass→pass | 12,890 | 13,592 | +5% | 1 | 1 | 0% | 2,117 | 2,839 | +34% | 0 | 0 | — |
case-15 | fail→pass | 12,772 | 6,731 | -47% | 1 | 1 | 0% | 2,237 | 1,756 | -22% | 0 | 0 | — |
case-16 | pass→pass | 15,880 | 10,726 | -32% | 1 | 1 | 0% | 2,749 | 2,241 | -18% | 0 | 0 | — |
case-17 | pass→pass | 12,046 | 10,447 | -13% | 1 | 1 | 0% | 2,240 | 2,533 | +13% | 0 | 0 | — |
case-18 | fail→pass | 6,413 | 1,971 | -69% | 1 | 1 | 0% | 1,161 | 983 | -15% | 0 | 0 | — |
case-19 | fail→pass | 3,373 | 8,213 | +143% | 1 | 1 | 0% | 448 | 1,824 | +307% | 0 | 0 | — |
case-20 | fail→fail | 8,999 | 4,720 | -48% | 1 | 1 | 0% | 1,327 | 1,410 | +6% | 0 | 0 | — |
case-21 | pass→pass | 15,712 | 15,461 | -2% | 1 | 1 | 0% | 2,363 | 2,817 | +19% | 0 | 0 | — |
case-22 | fail→fail | 9,084 | 7,245 | -20% | 1 | 1 | 0% | 1,473 | 1,817 | +23% | 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 +45 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.