Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Monitor competitor signals and surface strategic implications for your roadmap. Use when asked to monitor competitors, track the competitive landscape, produce a competitive briefing, or understand what has changed in the market this week or month. Produces a structured intelligence brief with high/medium/low priority signals, roadmap implications, and a strategic landscape summary. For a single competitor announcement use competitor-signal-tracker; for a one-off deep dive use competitor-teardow
.claude/skills/mohitagw15856-competitive-intelligence-monitor/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 58% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 2% | 0% |
Turn scattered competitor updates into structured weekly intelligence — not just "what they did" but "what changed since last week and what it means for us."
Ask the user for these if not provided:
New Since Last Run: n signals]
Competitor]: Signal] → Implication] → Recommended action + owner]
Competitor]: Signal] → Why it matters now]
Competitors with no new signals this week]
This Week's Strategic Summary: 2 sentences max — what is the overall competitive landscape doing?]
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 17,734 | 7,166 | -60% | 1 | 1 | 0% | 3,139 | 2,247 | -28% | 0 | 0 | — |
case-02 | fail→pass | 7,920 | 8,791 | +11% | 1 | 1 | 0% | 1,400 | 2,213 | +58% | 0 | 0 | — |
case-08 | fail→pass | 17,053 | 10,612 | -38% | 1 | 1 | 0% | 2,636 | 2,451 | -7% | 0 | 0 | — |
case-03 | fail→pass | 26,074 | 10,408 | -60% | 1 | 1 | 0% | 4,439 | 2,615 | -41% | 0 | 0 | — |
case-04 | pass→pass | 13,705 | 9,174 | -33% | 1 | 1 | 0% | 2,295 | 2,226 | -3% | 0 | 0 | — |
case-05 | pass→pass | 14,314 | 8,934 | -38% | 1 | 1 | 0% | 2,306 | 2,155 | -7% | 0 | 0 | — |
case-06 | pass→pass | 6,011 | 6,749 | +12% | 1 | 1 | 0% | 933 | 1,962 | +110% | 0 | 0 | — |
case-07 | fail→pass | 15,150 | 10,421 | -31% | 1 | 1 | 0% | 2,477 | 2,681 | +8% | 0 | 0 | — |
case-09 | pass→pass | 9,955 | 8,047 | -19% | 1 | 1 | 0% | 1,766 | 2,061 | +17% | 0 | 0 | — |
case-10 | fail→pass | 15,221 | 11,318 | -26% | 1 | 1 | 0% | 2,713 | 2,771 | +2% | 0 | 0 | — |
case-11 | pass→pass | 10,624 | 7,281 | -31% | 1 | 1 | 0% | 1,781 | 2,001 | +12% | 0 | 0 | — |
case-12 | fail→pass | 14,247 | 2,345 | -84% | 1 | 1 | 0% | 2,226 | 985 | -56% | 0 | 0 | — |
case-13 | fail→pass | 12,855 | 6,521 | -49% | 1 | 1 | 0% | 1,989 | 1,824 | -8% | 0 | 0 | — |
case-14 | fail→pass | 10,988 | 7,646 | -30% | 1 | 1 | 0% | 1,749 | 2,038 | +17% | 0 | 0 | — |
case-15 | pass→pass | 15,768 | 8,476 | -46% | 1 | 1 | 0% | 2,437 | 2,339 | -4% | 0 | 0 | — |
case-16 | pass→pass | 14,661 | 8,716 | -41% | 1 | 1 | 0% | 2,441 | 2,234 | -8% | 0 | 0 | — |
case-17 | pass→pass | 11,836 | 8,226 | -31% | 1 | 1 | 0% | 2,007 | 1,906 | -5% | 0 | 0 | — |
case-18 | pass→pass | 12,046 | 10,273 | -15% | 1 | 1 | 0% | 2,077 | 2,273 | +9% | 0 | 0 | — |
case-19 | pass→pass | 20,278 | 15,382 | -24% | 1 | 1 | 0% | 3,595 | 3,565 | -1% | 0 | 0 | — |
case-20 | pass→fail | 20,277 | 13,759 | -32% | 1 | 1 | 0% | 3,475 | 3,068 | -12% | 0 | 0 | — |
case-21 | pass→pass | 14,068 | 9,887 | -30% | 1 | 1 | 0% | 2,216 | 2,240 | +1% | 0 | 0 | — |
case-22 | fail→pass | 13,433 | 7,723 | -43% | 1 | 1 | 0% | 2,229 | 2,019 | -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 +36 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.