Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Analyze cryptocurrency market sentiment using Fear & Greed Index, news analysis, and market momentum. Use when gauging overall market mood, checking if markets are fearful or greedy, or analyzing sentiment for specific coins. Trigger with phrases like "analyze crypto sentiment", "check market mood", "is the market fearful", "sentiment for Bitcoin", or "Fear and Greed index".
.claude/skills/jeremylongshore-analyzing-market-sentiment/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 65% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 258% | 0% |
Cryptocurrency market sentiment analysis combining Fear & Greed Index, news keyword analysis, and price/volume momentum into a composite 0-100 score.
pip install requestscrypto-news-aggregator skill for enhanced news analysisbash # Quick market sentiment check python ${CLAUDE_SKILL_DIR}/scripts/sentiment_analyzer.py
# Coin-specific sentiment python ${CLAUDE_SKILL_DIR}/scripts/sentiment_analyzer.py --coin BTC
# Detailed breakdown with all components python ${CLAUDE_SKILL_DIR}/scripts/sentiment_analyzer.py --detailed
# Custom time period python ${CLAUDE_SKILL_DIR}/scripts/sentiment_analyzer.py --period 7d --detailed
bash python ${CLAUDE_SKILL_DIR}/scripts/sentiment_analyzer.py --format json --output sentiment.json
Composite sentiment score (0-100) with classification and weighted component breakdown. Extreme readings serve as contrarian indicators:
==============================================================================
MARKET SENTIMENT ANALYZER Updated: 2026-01-14 15:30 # 2026 - current year timestamp
==============================================================================
COMPOSITE SENTIMENT
------------------------------------------------------------------------------
Score: 65.5 / 100 Classification: GREED
Component Breakdown:
- Fear & Greed Index: 72.0 (weight: 40%) -> 28.8 pts
- News Sentiment: 58.5 (weight: 40%) -> 23.4 pts
- Market Momentum: 66.5 (weight: 20%) -> 13.3 pts
Interpretation: Market is moderately greedy. Consider taking profits or
reducing position sizes. Watch for reversal signals.
==============================================================================| Error | Cause | Solution | |-------|-------|----------| | Fear & Greed unavailable | API down | Uses cached value with warning | | News fetch failed | Network issue | Reduces weight of news component | | Invalid coin | Unknown symbol | Proceeds with market-wide analysis |
See ${CLAUDE_SKILL_DIR}/references/errors.md for comprehensive error handling.
Sentiment analysis patterns from quick checks to custom-weighted deep analysis:
bash# Quick market sentiment python ${CLAUDE_SKILL_DIR}/scripts/sentiment_analyzer.py # Bitcoin-specific sentiment python ${CLAUDE_SKILL_DIR}/scripts/sentiment_analyzer.py --coin BTC # Detailed analysis with component breakdown python ${CLAUDE_SKILL_DIR}/scripts/sentiment_analyzer.py --detailed # Custom weights emphasizing news python ${CLAUDE_SKILL_DIR}/scripts/sentiment_analyzer.py --weights "news:0.5,fng:0.3,momentum:0.2" # Weekly sentiment trend python ${CLAUDE_SKILL_DIR}/scripts/sentiment_analyzer.py --period 7d --detailed
${CLAUDE_SKILL_DIR}/references/implementation.md - CLI options, classifications, JSON format, contrarian theory${CLAUDE_SKILL_DIR}/references/errors.md - Comprehensive error handling${CLAUDE_SKILL_DIR}/references/examples.md - Detailed usage examples${CLAUDE_SKILL_DIR}/config/settings.yaml - Configuration options| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-23 | fail→fail | 18,748 | 25,991 | +39% | 1 | 1 | 0% | 3,709 | 6,262 | +69% | 0 | 0 | — |
case-01 | fail→fail | 12,441 | 4,593 | -63% | 1 | 1 | 0% | 2,254 | 1,258 | -44% | 0 | 0 | — |
case-02 | fail→fail | 17,307 | 1,426 | -92% | 1 | 1 | 0% | 3,074 | 1,237 | -60% | 0 | 0 | — |
case-03 | fail→fail | 10,548 | 4,308 | -59% | 1 | 1 | 0% | 1,906 | 1,345 | -29% | 0 | 0 | — |
case-04 | fail→pass | 4,529 | 1,380 | -70% | 1 | 1 | 0% | 783 | 1,291 | +65% | 0 | 0 | — |
case-05 | pass→pass | 4,328 | 2,536 | -41% | 1 | 1 | 0% | 768 | 1,511 | +97% | 0 | 0 | — |
case-06 | fail→pass | 7,136 | 2,588 | -64% | 1 | 1 | 0% | 1,277 | 1,472 | +15% | 0 | 0 | — |
case-07 | pass→pass | 10,511 | 2,560 | -76% | 1 | 1 | 0% | 1,924 | 1,487 | -23% | 0 | 0 | — |
case-08 | pass→pass | 10,790 | 3,036 | -72% | 1 | 1 | 0% | 1,978 | 1,578 | -20% | 0 | 0 | — |
case-09 | fail→pass | 9,270 | 3,423 | -63% | 1 | 1 | 0% | 1,637 | 1,607 | -2% | 0 | 0 | — |
case-10 | fail→pass | 9,832 | 1,701 | -83% | 1 | 1 | 0% | 1,875 | 1,358 | -28% | 0 | 0 | — |
case-11 | pass→pass | 5,851 | 4,436 | -24% | 1 | 1 | 0% | 1,025 | 1,786 | +74% | 0 | 0 | — |
case-12 | fail→pass | 2,590 | 1,286 | -50% | 1 | 1 | 0% | 343 | 1,229 | +258% | 0 | 0 | — |
case-13 | fail→pass | 8,182 | 1,491 | -82% | 1 | 1 | 0% | 1,551 | 1,238 | -20% | 0 | 0 | — |
case-14 | fail→pass | 2,330 | 1,661 | -29% | 1 | 1 | 0% | 281 | 1,170 | +316% | 0 | 0 | — |
case-15 | fail→pass | 10,669 | 1,399 | -87% | 1 | 1 | 0% | 1,890 | 1,185 | -37% | 0 | 0 | — |
case-16 | pass→pass | 4,307 | 1,501 | -65% | 1 | 1 | 0% | 776 | 1,279 | +65% | 0 | 0 | — |
case-17 | fail→pass | 9,024 | 1,501 | -83% | 1 | 1 | 0% | 1,642 | 1,320 | -20% | 0 | 0 | — |
case-18 | fail→pass | 11,723 | 3,127 | -73% | 1 | 1 | 0% | 2,042 | 1,577 | -23% | 0 | 0 | — |
case-19 | fail→pass | 14,584 | 4,987 | -66% | 1 | 1 | 0% | 2,822 | 1,484 | -47% | 0 | 0 | — |
case-20 | fail→pass | 4,023 | 1,626 | -60% | 1 | 1 | 0% | 776 | 1,251 | +61% | 0 | 0 | — |
case-21 | fail→fail | 12,842 | 13,754 | +7% | 1 | 1 | 0% | 2,307 | 3,827 | +66% | 0 | 0 | — |
case-22 | fail→fail | 7,110 | 7,970 | +12% | 1 | 1 | 0% | 797 | 2,064 | +159% | 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. 23 cases were attempted, and 21 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 +52 percentage points is the difference between those two pass rates over the 21 comparable cases. 2 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.