Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Produce a situational brief on a single stock/ticker — its recent high-relevance news, insider activity, and what to watch next — using the AlphaAI MCP. Use when the user asks to "brief me on <ticker>", "what's going on with <company>", "catch me up on NVDA", or wants a quick read on one name.
.claude/skills/ccplugins-stock-brief/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✓→✗ | ▼ Worse | -34% | 0% |
| case-13 | ✓→✗ | ▼ Worse | -33% | 0% |
| case-15 | ✓→✗ | ▼ Worse | -41% | 0% |
| case-17 | ✓→✓ | ＝ Same ✓ | -66% | 0% |
| case-01 | ✗→✗ | ＝ Same ✗ | -60% | 0% |
Give a tight, decision-useful read on one ticker from AlphaAI's enriched feed. Not a price quote — a news brief: what's been happening, who's buying or selling, and what to keep an eye on.
alphai_tickers(q=...) to find it. If alphai_ticker_news returns unknown_ticker=true, tell the user and stop — don't invent coverage.
alphai_ticker_news(ticker, collapse_stories=true).collapse_stories folds syndicated reprints into one row each and adds a sources_count corroboration signal — prefer it for a clean brief. Insider news is included by default; keep it.
alphai_trending(limit=5) and note any market-level story that touches this name or its sector.
wants detail, fetch it with alphai_article(uid) for the full enrichment (ticker analysis, key entities). The article body is not served — work from the enrichment and summary.
Keep it to a screen. Structure:
"why it matters". Lead with the highest relevance_score.
size if given. "No notable insider activity in the window" is a valid line.
relevance_score; lead with the high ones and saythe score so the user can calibrate.
summarize what the reporting says and let the user decide.
beats a long speculative one.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 14,401 | 6,145 | -57% | 1 | 1 | 0% | 2,051 | 816 | -60% | 0 | 0 | — |
case-02 | fail→fail | 14,802 | 6,721 | -55% | 1 | 1 | 0% | 2,278 | 776 | -66% | 0 | 0 | — |
case-03 | fail→fail | 14,219 | 7,242 | -49% | 1 | 1 | 0% | 2,107 | 867 | -59% | 0 | 0 | — |
case-04 | fail→fail | 10,811 | 9,637 | -11% | 1 | 1 | 0% | 1,410 | 922 | -35% | 0 | 0 | — |
case-05 | fail→fail | 10,114 | 7,862 | -22% | 1 | 1 | 0% | 1,551 | 850 | -45% | 0 | 0 | — |
case-06 | fail→fail | 9,429 | 6,752 | -28% | 1 | 1 | 0% | 1,143 | 826 | -28% | 0 | 0 | — |
case-07 | fail→fail | 16,472 | 8,106 | -51% | 1 | 1 | 0% | 2,114 | 910 | -57% | 0 | 0 | — |
case-08 | fail→fail | 16,726 | 6,638 | -60% | 1 | 1 | 0% | 1,836 | 869 | -53% | 0 | 0 | — |
case-09 | fail→fail | 11,488 | 8,407 | -27% | 1 | 1 | 0% | 1,624 | 876 | -46% | 0 | 0 | — |
case-10 | pass→fail | 11,553 | 8,492 | -26% | 1 | 1 | 0% | 1,526 | 1,011 | -34% | 0 | 0 | — |
case-11 | fail→fail | 14,770 | 7,957 | -46% | 1 | 1 | 0% | 2,057 | 815 | -60% | 0 | 0 | — |
case-12 | fail→fail | 14,378 | 9,053 | -37% | 1 | 1 | 0% | 1,905 | 898 | -53% | 0 | 0 | — |
case-13 | pass→fail | 9,687 | 7,352 | -24% | 1 | 1 | 0% | 1,336 | 895 | -33% | 0 | 0 | — |
case-14 | fail→fail | 16,855 | 7,655 | -55% | 1 | 1 | 0% | 2,328 | 979 | -58% | 0 | 0 | — |
case-15 | pass→fail | 11,218 | 8,147 | -27% | 1 | 1 | 0% | 1,639 | 969 | -41% | 0 | 0 | — |
case-16 | fail→fail | 12,238 | 7,822 | -36% | 1 | 1 | 0% | 1,833 | 915 | -50% | 0 | 0 | — |
case-17 | pass→pass | 16,224 | 3,347 | -79% | 1 | 1 | 0% | 2,784 | 948 | -66% | 0 | 0 | — |
case-18 | fail→fail | 31,590 | 8,580 | -73% | 1 | 1 | 0% | 1,600 | 923 | -42% | 0 | 0 | — |
case-19 | fail→fail | 24,595 | 9,827 | -60% | 1 | 1 | 0% | 5,009 | 1,141 | -77% | 0 | 0 | — |
case-20 | fail→fail | 12,017 | 10,458 | -13% | 1 | 1 | 0% | 1,994 | 1,083 | -46% | 0 | 0 | — |
case-21 | fail→fail | 18,627 | 13,109 | -30% | 1 | 1 | 0% | 2,851 | 1,384 | -51% | 0 | 0 | — |
case-22 | fail→fail | 21,719 | 18,564 | -15% | 1 | 1 | 0% | 4,320 | 1,156 | -73% | 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 1 counted toward the lift figure. The other 21 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. A headline lift is not published for this run.
Other measured skills in the registry, with their headline benchmark lift.