Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Aggregate breaking cryptocurrency news from 50+ sources including CoinDesk, CoinTelegraph, The Block, and Decrypt. Use when needing to monitor crypto market news, track announcements, or find coin-specific updates. Trigger with phrases like "get crypto news", "latest Bitcoin headlines", "DeFi announcements", "scan for breaking news", or "check crypto updates".
.claude/skills/jeremylongshore-aggregating-crypto-news/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 121% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 188% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 3% | 0% |
Aggregate cryptocurrency news from 50+ authoritative sources via RSS feeds with real-time scanning, coin/category filtering, and relevance scoring.
pip install feedparser requestsbash # Default scan (top 20, past 24h, relevance sorted) python ${CLAUDE_SKILL_DIR}/scripts/news_aggregator.py
# Coin-specific scan python ${CLAUDE_SKILL_DIR}/scripts/news_aggregator.py --coin BTC --period 4h
# Category filter python ${CLAUDE_SKILL_DIR}/scripts/news_aggregator.py --category defi --top 30
# Multiple filters python ${CLAUDE_SKILL_DIR}/scripts/news_aggregator.py --coin ETH --category defi --period 24h --top 15
bash python ${CLAUDE_SKILL_DIR}/scripts/news_aggregator.py --format json --output news.json
Table showing articles ranked by relevance score (0-100) based on market-moving keyword detection, source authority, and recency:
==============================================================================
CRYPTO NEWS AGGREGATOR Updated: 2026-01-14 15:30 # 2026 - current year timestamp
==============================================================================
TOP CRYPTO NEWS (24h)
------------------------------------------------------------------------------
Rank Source Title Age Score
------------------------------------------------------------------------------
1 CoinDesk Bitcoin Breaks $100K ATH 2h 95.0
2 The Block SEC Approves ETH ETF 4h 92.5
3 Decrypt Solana DeFi TVL Surges 6h 78.3
------------------------------------------------------------------------------
Summary: 20 articles shown | Scanned: 50 sources | Matched: 187
==============================================================================| Error | Cause | Solution | |-------|-------|----------| | Network timeout | RSS feed unreachable | Uses cached data; skips unavailable sources | | Parse error | Malformed RSS | Skips entry; continues with valid articles | | No results | Filters too strict | Suggest relaxing filters | | Invalid coin | Unknown symbol | List similar valid symbols |
See ${CLAUDE_SKILL_DIR}/references/errors.md for comprehensive error handling.
Filtering patterns for common news monitoring scenarios:
bash# Latest crypto news (defaults) python ${CLAUDE_SKILL_DIR}/scripts/news_aggregator.py # Bitcoin news from past 4 hours python ${CLAUDE_SKILL_DIR}/scripts/news_aggregator.py --coin BTC --period 4h # DeFi category news python ${CLAUDE_SKILL_DIR}/scripts/news_aggregator.py --category defi # High-relevance news only python ${CLAUDE_SKILL_DIR}/scripts/news_aggregator.py --min-score 70 --top 10 # Multiple coins python ${CLAUDE_SKILL_DIR}/scripts/news_aggregator.py --coins BTC,ETH,SOL
${CLAUDE_SKILL_DIR}/references/implementation.md - CLI options, categories, JSON format, advanced filtering${CLAUDE_SKILL_DIR}/references/errors.md - Comprehensive error handling${CLAUDE_SKILL_DIR}/references/examples.md - Detailed usage examples${CLAUDE_SKILL_DIR}/config/sources.yaml - Full source registry| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 4,499 | 8,159 | +81% | 1 | 1 | 0% | 746 | 1,389 | +86% | 0 | 0 | — |
case-02 | fail→fail | 16,037 | 8,093 | -50% | 1 | 1 | 0% | 3,553 | 1,617 | -54% | 0 | 0 | — |
case-03 | fail→fail | 10,523 | 6,454 | -39% | 1 | 1 | 0% | 1,479 | 1,462 | -1% | 0 | 0 | — |
case-04 | pass→pass | 4,408 | 3,769 | -14% | 1 | 1 | 0% | 948 | 1,831 | +93% | 0 | 0 | — |
case-05 | fail→fail | 7,019 | 9,252 | +32% | 1 | 1 | 0% | 1,524 | 2,968 | +95% | 0 | 0 | — |
case-06 | pass→pass | 5,314 | 7,332 | +38% | 1 | 1 | 0% | 1,189 | 2,679 | +125% | 0 | 0 | — |
case-07 | pass→pass | 8,739 | 4,165 | -52% | 1 | 1 | 0% | 1,841 | 1,285 | -30% | 0 | 0 | — |
case-08 | fail→pass | 16,598 | 8,193 | -51% | 1 | 1 | 0% | 2,863 | 2,517 | -12% | 0 | 0 | — |
case-09 | fail→fail | 13,344 | 5,363 | -60% | 1 | 1 | 0% | 2,265 | 1,340 | -41% | 0 | 0 | — |
case-10 | fail→fail | 9,897 | 5,262 | -47% | 1 | 1 | 0% | 2,185 | 1,411 | -35% | 0 | 0 | — |
case-11 | fail→pass | 7,280 | 9,279 | +27% | 1 | 1 | 0% | 1,271 | 2,813 | +121% | 0 | 0 | — |
case-12 | fail→pass | 6,994 | 14,597 | +109% | 1 | 1 | 0% | 1,133 | 3,265 | +188% | 0 | 0 | — |
case-13 | pass→pass | 10,688 | 3,636 | -66% | 1 | 1 | 0% | 1,899 | 1,660 | -13% | 0 | 0 | — |
case-14 | pass→pass | 11,811 | 4,121 | -65% | 1 | 1 | 0% | 2,064 | 1,745 | -15% | 0 | 0 | — |
case-15 | pass→pass | 10,989 | 1,814 | -83% | 1 | 1 | 0% | 1,857 | 1,353 | -27% | 0 | 0 | — |
case-16 | pass→pass | 10,649 | 4,267 | -60% | 1 | 1 | 0% | 1,810 | 1,792 | -1% | 0 | 0 | — |
case-17 | fail→fail | 6,764 | 5,257 | -22% | 1 | 1 | 0% | 825 | 1,559 | +89% | 0 | 0 | — |
case-18 | fail→pass | 8,466 | 2,542 | -70% | 1 | 1 | 0% | 1,432 | 1,344 | -6% | 0 | 0 | — |
case-19 | fail→pass | 12,709 | 7,685 | -40% | 1 | 1 | 0% | 2,477 | 2,556 | +3% | 0 | 0 | — |
case-20 | fail→pass | 7,528 | 9,918 | +32% | 1 | 1 | 0% | 1,294 | 2,203 | +70% | 0 | 0 | — |
case-21 | pass→pass | 11,105 | 2,464 | -78% | 1 | 1 | 0% | 1,861 | 1,497 | -20% | 0 | 0 | — |
case-22 | fail→pass | 12,266 | 1,712 | -86% | 1 | 1 | 0% | 2,087 | 1,322 | -37% | 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 16 counted toward the lift figure. The other 6 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 +32 percentage points is the difference between those two pass rates over the 16 comparable cases.
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.