Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Comprehensive market environment analysis and reporting tool. Analyzes global markets including US, European, Asian markets, forex, commodities, and economic indicators. Provides risk-on/risk-off assessment, sector analysis, and technical indicator interpretation. Triggers on keywords like market analysis, market environment, global markets, trading environment, market conditions, investment climate, market sentiment, forex analysis, stock market analysis, 相場環境, 市場分析, マーケット状況, 投資環境.
.claude/skills/nicepkg-market-environment-analysis/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-04 | ✓→✗ | ▼ Worse | -67% | 0% |
| case-08 | ✓→✗ | ▼ Worse | -41% | 0% |
| case-10 | ✓→✗ | ▼ Worse | -28% | 0% |
| case-11 | ✓→✗ | ▼ Worse | -48% | 0% |
Comprehensive analysis tool for understanding market conditions and creating professional market reports anytime.
Collect latest market data using web_search tool:
Evaluate the following from collected data:
1. Executive Summary (3-5 key points)
2. Global Market Overview
- US Markets
- Asian Markets
- European Markets
3. Forex & Commodities Trends
4. Key Events & Economic Indicators
5. Risk Factor Analysis
6. Investment Strategy ImplicationsProvides common functions for report creation:
bash# Generate report header python scripts/market_utils.py # Available functions: - format_market_report_header(): Create header - get_market_session_times(): Check trading hours - categorize_volatility(vix): Interpret VIX levels - format_percentage_change(value): Format price changes
Reference when you need:
Reference when analyzing:
📊 Market Summary [2025/01/15 14:00]
━━━━━━━━━━━━━━━━━━━━━
【US】S&P 500: 5,123.45 (+0.45%)
【JP】Nikkei 225: 38,456.78 (-0.23%)
【FX】USD/JPY: 149.85 (↑0.15)
【VIX】16.2 (Normal range)
⚡ Key Events
- Japan GDP Flash
- US Employment Report
📈 Environment: Risk-On ContinuesStart with executive summary, then analyze each section in detail. Key clarifications:
Categorize by importance:
Adjust based on user's investment style:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 27,371 | 14,281 | -48% | 1 | 1 | 0% | 4,283 | 1,381 | -68% | 0 | 0 | — |
case-02 | fail→fail | 14,687 | 6,160 | -58% | 1 | 1 | 0% | 2,306 | 1,319 | -43% | 0 | 0 | — |
case-03 | fail→fail | 9,203 | 6,663 | -28% | 1 | 1 | 0% | 497 | 1,262 | +154% | 0 | 0 | — |
case-04 | pass→fail | 22,392 | 7,902 | -65% | 1 | 1 | 0% | 4,314 | 1,441 | -67% | 0 | 0 | — |
case-05 | pass→pass | 22,658 | 22,792 | +1% | 1 | 1 | 0% | 4,424 | 5,231 | +18% | 0 | 0 | — |
case-06 | pass→pass | 20,744 | 20,592 | -1% | 1 | 1 | 0% | 3,332 | 4,587 | +38% | 0 | 0 | — |
case-07 | fail→fail | 3,987 | 11,931 | +199% | 1 | 1 | 0% | 532 | 1,187 | +123% | 0 | 0 | — |
case-08 | pass→fail | 16,125 | 7,816 | -52% | 1 | 1 | 0% | 2,223 | 1,312 | -41% | 0 | 0 | — |
case-09 | fail→pass | 12,833 | 12,016 | -6% | 1 | 1 | 0% | 1,943 | 2,781 | +43% | 0 | 0 | — |
case-10 | pass→fail | 15,361 | 8,203 | -47% | 1 | 1 | 0% | 2,272 | 1,633 | -28% | 0 | 0 | — |
case-11 | pass→fail | 21,762 | 50,593 | +132% | 1 | 1 | 0% | 3,007 | 1,573 | -48% | 0 | 0 | — |
case-12 | pass→pass | 11,278 | 7,160 | -37% | 1 | 1 | 0% | 1,750 | 2,014 | +15% | 0 | 0 | — |
case-18 | fail→fail | 6,633 | 5,226 | -21% | 1 | 1 | 0% | 948 | 1,139 | +20% | 0 | 0 | — |
case-13 | pass→pass | 16,290 | 11,855 | -27% | 1 | 1 | 0% | 2,894 | 3,325 | +15% | 0 | 0 | — |
case-14 | pass→pass | 9,594 | 5,305 | -45% | 1 | 1 | 0% | 1,500 | 1,761 | +17% | 0 | 0 | — |
case-15 | pass→pass | 13,835 | 9,876 | -29% | 1 | 1 | 0% | 2,001 | 2,438 | +22% | 0 | 0 | — |
case-16 | pass→fail | 16,438 | 8,936 | -46% | 1 | 1 | 0% | 2,325 | 1,369 | -41% | 0 | 0 | — |
case-17 | pass→fail | 11,828 | 18,482 | +56% | 1 | 1 | 0% | 1,792 | 1,546 | -14% | 0 | 0 | — |
case-19 | fail→fail | 13,264 | 20,385 | +54% | 1 | 1 | 0% | 1,832 | 1,254 | -32% | 0 | 0 | — |
case-20 | pass→pass | 11,145 | 4,263 | -62% | 1 | 1 | 0% | 1,674 | 1,602 | -4% | 0 | 0 | — |
case-21 | pass→pass | 4,592 | 4,945 | +8% | 1 | 1 | 0% | 672 | 1,750 | +160% | 0 | 0 | — |
case-22 | pass→pass | 18,384 | 15,024 | -18% | 1 | 1 | 0% | 2,851 | 3,282 | +15% | 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 10 counted toward the lift figure. The other 12 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 -23 percentage points is the difference between those two pass rates over the 10 comparable cases. 6 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.