Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Summarize what's moving in the market right now using the AlphaAI MCP. Use when the user asks "what's moving?", "what's the big story today?", "anything breaking?", "market pulse", or wants a fast read on the current tape rather than one specific ticker.
.claude/skills/ccplugins-market-pulse/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | -31% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -23% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 1% | 0% |
Answer "what's happening right now?" from AlphaAI's feed. Two tools cover two different questions — pick the right one:
alphai_actionable_now — breaking, decision-grade news from the last fewhours. The gate is strict: by default only actionability='high' (something to act on TODAY — guidance cut, halted trading, breaking M&A, surprise print).
alphai_trending — top stories of the last 48h by relevance. The "bigpicture", not necessarily urgent.
alphai_actionable_now() (defaults: last 6h,high-actionability). This is the real "is anything breaking" signal.
weekends — crypto trades 24/7, but high-actionability prints still cluster in US/European/Asian sessions) an empty list is expected — it means no high-actionability prints in the window, not that the tool failed. Before concluding "nothing happened", widen once: alphai_actionable_now(hours=24, min_actionability='medium').
alphai_trending(limit=10). Use this for the"bigger stories shaping the week" layer even when nothing is breaking.
tickers (alphai_tickers(q=...) or your own knowledge), then alphai_news_search(tickers=[...], min_relevance=7) — there is no free-text news search; match themes client-side on the returned titles/summaries.
ticker(s) · one clause on the decision it forces. If none, say so in one line and note the window you checked.
focus, an event everyone's positioning around).
(trending) without being something to act on today (actionable). Label which layer each item came from if it matters.
"breaking".
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 8,537 | 6,474 | -24% | 1 | 1 | 0% | 409 | 1,115 | +173% | 0 | 0 | — |
case-02 | fail→fail | 12,002 | 12,399 | +3% | 1 | 1 | 0% | 1,573 | 1,395 | -11% | 0 | 0 | — |
case-03 | fail→fail | 13,448 | 5,142 | -62% | 1 | 1 | 0% | 1,827 | 1,010 | -45% | 0 | 0 | — |
case-04 | pass→pass | 34,779 | 38,115 | +10% | 1 | 1 | 0% | 7,055 | 8,847 | +25% | 0 | 0 | — |
case-05 | pass→pass | 14,122 | 17,422 | +23% | 1 | 1 | 0% | 2,844 | 4,525 | +59% | 0 | 0 | — |
case-06 | pass→pass | 17,372 | 19,411 | +12% | 1 | 1 | 0% | 2,662 | 3,731 | +40% | 0 | 0 | — |
case-07 | fail→fail | 6,847 | 4,626 | -32% | 1 | 1 | 0% | 239 | 924 | +287% | 0 | 0 | — |
case-08 | fail→pass | 12,591 | 3,729 | -70% | 1 | 1 | 0% | 1,691 | 1,159 | -31% | 0 | 0 | — |
case-09 | fail→pass | 16,013 | 2,516 | -84% | 1 | 1 | 0% | 1,213 | 940 | -23% | 0 | 0 | — |
case-10 | fail→pass | 9,467 | 5,016 | -47% | 1 | 1 | 0% | 1,383 | 1,338 | -3% | 0 | 0 | — |
case-11 | fail→pass | 12,699 | 6,889 | -46% | 1 | 1 | 0% | 2,082 | 1,618 | -22% | 0 | 0 | — |
case-12 | pass→pass | 13,049 | 4,347 | -67% | 1 | 1 | 0% | 1,684 | 1,165 | -31% | 0 | 0 | — |
case-13 | fail→pass | 11,398 | 6,044 | -47% | 1 | 1 | 0% | 1,546 | 1,560 | +1% | 0 | 0 | — |
case-14 | fail→pass | 5,452 | 9,357 | +72% | 1 | 1 | 0% | 902 | 2,255 | +150% | 0 | 0 | — |
case-15 | fail→pass | 14,683 | 8,896 | -39% | 1 | 1 | 0% | 2,036 | 2,118 | +4% | 0 | 0 | — |
case-16 | pass→pass | 12,868 | 8,164 | -37% | 1 | 1 | 0% | 1,715 | 1,614 | -6% | 0 | 0 | — |
case-17 | fail→pass | 12,065 | 2,961 | -75% | 1 | 1 | 0% | 1,784 | 996 | -44% | 0 | 0 | — |
case-18 | pass→pass | 10,690 | 3,514 | -67% | 1 | 1 | 0% | 1,292 | 1,122 | -13% | 0 | 0 | — |
case-19 | pass→pass | 14,936 | 7,984 | -47% | 1 | 1 | 0% | 2,436 | 1,818 | -25% | 0 | 0 | — |
case-20 | fail→fail | 12,401 | 4,004 | -68% | 1 | 1 | 0% | 1,700 | 1,145 | -33% | 0 | 0 | — |
case-21 | fail→fail | 10,589 | 2,458 | -77% | 1 | 1 | 0% | 1,441 | 862 | -40% | 0 | 0 | — |
case-22 | fail→fail | 11,805 | 2,439 | -79% | 1 | 1 | 0% | 1,589 | 917 | -42% | 0 | 0 | — |
case-23 | fail→fail | 6,205 | 2,644 | -57% | 1 | 1 | 0% | 810 | 842 | +4% | 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 19 counted toward the lift figure. The other 4 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 +35 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.