Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →List, add, or remove the user's ticker news-alert subscriptions through the AlphaAI MCP. Use when the user asks to "alert me on <ticker>", "subscribe me to <ticker> earnings news", "what alerts do I have?", "stop alerts for <ticker>", or to manage their AlphaAI alert inventory. Requires a paid (Basic/Pro) AlphaAI plan.
.claude/skills/ccplugins-manage-alerts/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -49% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 44% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-20 | ✗→✓ | ▲ Improved | -45% | 0% |
| case-22 | ✗→✓ | ▲ Improved | -55% | 0% |
Let the user manage their own AlphaAI ticker news-alert subscriptions from the chat. Identity comes from the OAuth login — these tools act on the caller's own account.
> Tier-gated. alphai_alerts_* require a Basic or Pro plan. On the Free > tier they return tier_not_paid — relay that and point to > <https://alphai.io/pricing> instead of retrying.
alphai_alerts_list()up front so you (and the user) can see existing subscriptions, the per-alert filters, and the tier limit (current / limit).
min_relevance_score?).
preserves its current value. A brand-new subscription defaults min_relevance_score to 6.
category_filter is an optional whitelist from the 14 categories (e.g.["earnings", "insider"]) — only those categories trigger the alert.
alphai_tickers); the toolraises unknown_ticker / limit_reached otherwise.
alphai_alerts_unsubscribe(ticker) — idempotent; returns{removed: false} if it was already inactive.
categories trigger it, and the minimum relevance — so the user sees exactly what they'll be alerted on.
categories · min relevance · delivery mode) and note current/limit.
remove before calling the write tool, especially for bulk changes.
tier_not_paid → suggest upgrading; limit_reached →list current alerts so the user can free a slot; unknown_ticker → don't guess a substitute.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 6,709 | 6,462 | -4% | 1 | 1 | 0% | 816 | 1,083 | +33% | 0 | 0 | — |
case-02 | fail→fail | 11,350 | 5,359 | -53% | 1 | 1 | 0% | 2,039 | 834 | -59% | 0 | 0 | — |
case-03 | fail→fail | 6,524 | 7,777 | +19% | 1 | 1 | 0% | 313 | 992 | +217% | 0 | 0 | — |
case-04 | fail→pass | 13,862 | 3,236 | -77% | 1 | 1 | 0% | 1,731 | 888 | -49% | 0 | 0 | — |
case-05 | fail→pass | 5,871 | 3,833 | -35% | 1 | 1 | 0% | 739 | 1,067 | +44% | 0 | 0 | — |
case-06 | fail→fail | 10,174 | 7,170 | -30% | 1 | 1 | 0% | 1,410 | 968 | -31% | 0 | 0 | — |
case-07 | pass→pass | 7,649 | 4,698 | -39% | 1 | 1 | 0% | 1,071 | 932 | -13% | 0 | 0 | — |
case-08 | fail→fail | 3,182 | 3,296 | +4% | 1 | 1 | 0% | 417 | 686 | +65% | 0 | 0 | — |
case-09 | fail→fail | 8,268 | 4,730 | -43% | 1 | 1 | 0% | 1,130 | 1,202 | +6% | 0 | 0 | — |
case-10 | fail→fail | 7,587 | 6,357 | -16% | 1 | 1 | 0% | 785 | 773 | -2% | 0 | 0 | — |
case-11 | pass→pass | 14,475 | 16,541 | +14% | 1 | 1 | 0% | 2,253 | 2,274 | +1% | 0 | 0 | — |
case-12 | fail→pass | 9,368 | 8,046 | -14% | 1 | 1 | 0% | 1,492 | 1,866 | +25% | 0 | 0 | — |
case-13 | fail→fail | 2,744 | 14,165 | +416% | 1 | 1 | 0% | 345 | 1,122 | +225% | 0 | 0 | — |
case-14 | pass→pass | 9,064 | 5,727 | -37% | 1 | 1 | 0% | 1,353 | 1,353 | 0% | 0 | 0 | — |
case-15 | pass→pass | 4,556 | 4,748 | +4% | 1 | 1 | 0% | 526 | 1,009 | +92% | 0 | 0 | — |
case-16 | fail→fail | 3,749 | 17,086 | +356% | 1 | 1 | 0% | 462 | 1,784 | +286% | 0 | 0 | — |
case-17 | pass→fail | 25,132 | 7,072 | -72% | 1 | 1 | 0% | 1,930 | 1,076 | -44% | 0 | 0 | — |
case-18 | fail→fail | 8,439 | 5,723 | -32% | 1 | 1 | 0% | 1,292 | 840 | -35% | 0 | 0 | — |
case-19 | fail→fail | 6,504 | 6,590 | +1% | 1 | 1 | 0% | 848 | 979 | +15% | 0 | 0 | — |
case-20 | fail→pass | 12,823 | 4,258 | -67% | 1 | 1 | 0% | 1,812 | 1,001 | -45% | 0 | 0 | — |
case-21 | fail→fail | 11,696 | 8,288 | -29% | 1 | 1 | 0% | 1,709 | 1,080 | -37% | 0 | 0 | — |
case-22 | fail→pass | 12,077 | 2,742 | -77% | 1 | 1 | 0% | 1,940 | 864 | -55% | 0 | 0 | — |
case-23 | fail→fail | 5,101 | 6,037 | +18% | 1 | 1 | 0% | 569 | 977 | +72% | 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 14 counted toward the lift figure. The other 9 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 +17 percentage points is the difference between those two pass rates over the 14 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.