Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Fetch hot finance news, unified trends, and prediction financial market data. Use when the user needs real-time financial news, trend reports from multiple finance sources (Weibo, Zhihu, WallstreetCN, etc.), or Polymarket finance market prediction data.
.claude/skills/rkiding-alphaear-news/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 95% | 19 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-14 | ✗→✓ | ▲ Improved | -69% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -55% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -73% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -61% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -67% | 0% |
Fetch real-time hot news, generate unified trend reports, and retrieve Polymarket prediction data.
Use scripts/news_tools.py via NewsNowTools.
fetch_hot_news(source_id, count)source_ids (e.g., cls, weibo).get_unified_trends(sources)Use scripts/news_tools.py via PolymarketTools.
get_market_summary(limit)requests, loguruscripts/database_manager.py (Local DB)| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-13 | pass→pass | 5,006 | 1,907 | -62% | 1 | 1 | 0% | 892 | 536 | -40% | 0 | 0 | — |
case-14 | fail→pass | 8,208 | 1,525 | -81% | 1 | 1 | 0% | 1,518 | 470 | -69% | 0 | 0 | — |
case-01 | fail→fail | 8,423 | 7,174 | -15% | 1 | 1 | 0% | 1,459 | 687 | -53% | 0 | 0 | — |
case-02 | fail→pass | 12,384 | 7,086 | -43% | 1 | 1 | 0% | 1,982 | 896 | -55% | 0 | 0 | — |
case-03 | fail→fail | 10,122 | 6,348 | -37% | 1 | 1 | 0% | 1,925 | 624 | -68% | 0 | 0 | — |
case-04 | fail→pass | 12,937 | 2,383 | -82% | 1 | 1 | 0% | 2,540 | 682 | -73% | 0 | 0 | — |
case-05 | fail→pass | 9,449 | 2,599 | -72% | 1 | 1 | 0% | 1,821 | 716 | -61% | 0 | 0 | — |
case-06 | fail→pass | 6,856 | 1,831 | -73% | 1 | 1 | 0% | 1,208 | 402 | -67% | 0 | 0 | — |
case-07 | fail→pass | 5,930 | 1,592 | -73% | 1 | 1 | 0% | 1,008 | 477 | -53% | 0 | 0 | — |
case-08 | fail→pass | 5,764 | 1,662 | -71% | 1 | 1 | 0% | 1,023 | 428 | -58% | 0 | 0 | — |
case-09 | fail→pass | 8,706 | 1,820 | -79% | 1 | 1 | 0% | 1,721 | 518 | -70% | 0 | 0 | — |
case-10 | fail→pass | 8,475 | 1,572 | -81% | 1 | 1 | 0% | 1,571 | 458 | -71% | 0 | 0 | — |
case-11 | fail→pass | 5,093 | 1,887 | -63% | 1 | 1 | 0% | 727 | 474 | -35% | 0 | 0 | — |
case-12 | fail→pass | 3,272 | 1,292 | -61% | 1 | 1 | 0% | 521 | 403 | -23% | 0 | 0 | — |
case-15 | fail→pass | 6,475 | 1,867 | -71% | 1 | 1 | 0% | 1,101 | 534 | -51% | 0 | 0 | — |
case-16 | fail→pass | 9,886 | 1,608 | -84% | 1 | 1 | 0% | 1,754 | 422 | -76% | 0 | 0 | — |
case-17 | pass→pass | 6,516 | 1,303 | -80% | 1 | 1 | 0% | 1,302 | 412 | -68% | 0 | 0 | — |
case-18 | fail→pass | 6,436 | 2,045 | -68% | 1 | 1 | 0% | 1,251 | 574 | -54% | 0 | 0 | — |
case-19 | pass→pass | 4,406 | 1,216 | -72% | 1 | 1 | 0% | 784 | 407 | -48% | 0 | 0 | — |
case-20 | fail→pass | 7,397 | 2,454 | -67% | 1 | 1 | 0% | 1,429 | 610 | -57% | 0 | 0 | — |
case-21 | fail→fail | 13,457 | 10,844 | -19% | 1 | 1 | 0% | 2,901 | 2,507 | -14% | 0 | 0 | — |
case-22 | fail→fail | 10,323 | 5,532 | -46% | 1 | 1 | 0% | 2,517 | 363 | -86% | 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 19 counted toward the lift figure. The other 3 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 +68 percentage points is the difference between those two pass rates over the 19 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.