Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Watches Bitcoin dominance (BTC's share of total crypto market cap) and alerts the user on Telegram only when it crosses a key threshold: below 60% reads as a possible altcoin-season signal, above 65% as BTC dominance expanding. Between 60% and 65% it stays silent. Each check is logged to memory as an audit trail, and it only alerts on an actual threshold crossing, never on every run.
.claude/skills/nearai-btc-dominance-alert/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | 2% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -54% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -58% | 0% |
You watch Bitcoin dominance and alert the user only when it crosses a key threshold.
btc-dominance/last-check.md with memory_read before writing, then write the full updated file back with memory_write. Never overwrite from scratch. Log every check (timestamp, value, whether an alert was sent) regardless of outcome.HEARTBEAT_OK and stop — send no message.Create a routine that runs every 5 hours. The routine goal must contain these full steps as a self-contained prompt, because a routine does not keep any context from this conversation when it runs:
http tool: https://api.coingecko.com/api/v3/global. Take data.market_cap_percentage.btc — that's the current BTC dominance %.btc-dominance/last-check.md with memory_read to see the previous value and whether it was already past a threshold.HEARTBEAT_OK and stop.Alert format:
[if below 60%:]
🔴 BTC Dominance Alert
BTC dominance dropped to [X]% — below 60%. Possible altcoin-season signal.
[if above 65%:]
🟡 BTC Dominance Alert
BTC dominance rose to [X]% — above 65%. BTC dominance expanding.
🕐 [timestamp]show btc dominance — fetch the current dominance now and show it with the last logged value| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-09 | fail→pass | 7,343 | 2,279 | -69% | 1 | 1 | 0% | 1,102 | 1,127 | +2% | 0 | 0 | — |
case-01 | fail→fail | 14,094 | 8,496 | -40% | 1 | 1 | 0% | 2,891 | 1,257 | -57% | 0 | 0 | — |
case-02 | fail→fail | 3,851 | 5,214 | +35% | 1 | 1 | 0% | 620 | 978 | +58% | 0 | 0 | — |
case-03 | fail→fail | 17,567 | 10,827 | -38% | 1 | 1 | 0% | 3,836 | 1,510 | -61% | 0 | 0 | — |
case-04 | fail→pass | 13,028 | 2,177 | -83% | 1 | 1 | 0% | 2,291 | 1,049 | -54% | 0 | 0 | — |
case-23 | fail→fail | 19,703 | 13,521 | -31% | 1 | 1 | 0% | 3,102 | 3,223 | +4% | 0 | 0 | — |
case-05 | pass→pass | 13,516 | 1,975 | -85% | 1 | 1 | 0% | 2,323 | 1,067 | -54% | 0 | 0 | — |
case-06 | fail→pass | 7,096 | 1,826 | -74% | 1 | 1 | 0% | 1,160 | 1,043 | -10% | 0 | 0 | — |
case-07 | fail→pass | 8,726 | 3,823 | -56% | 1 | 1 | 0% | 1,280 | 1,386 | +8% | 0 | 0 | — |
case-08 | fail→pass | 14,937 | 2,037 | -86% | 1 | 1 | 0% | 2,512 | 1,051 | -58% | 0 | 0 | — |
case-10 | fail→pass | 4,557 | 1,158 | -75% | 1 | 1 | 0% | 959 | 861 | -10% | 0 | 0 | — |
case-11 | pass→fail | 6,206 | 1,766 | -72% | 1 | 1 | 0% | 970 | 972 | +0% | 0 | 0 | — |
case-12 | fail→pass | 7,751 | 2,085 | -73% | 1 | 1 | 0% | 1,393 | 1,108 | -20% | 0 | 0 | — |
case-13 | fail→pass | 6,950 | 2,069 | -70% | 1 | 1 | 0% | 1,390 | 1,056 | -24% | 0 | 0 | — |
case-14 | pass→pass | 8,528 | 3,122 | -63% | 1 | 1 | 0% | 1,547 | 1,198 | -23% | 0 | 0 | — |
case-15 | fail→pass | 8,748 | 1,303 | -85% | 1 | 1 | 0% | 1,584 | 866 | -45% | 0 | 0 | — |
case-16 | pass→pass | 10,606 | 4,375 | -59% | 1 | 1 | 0% | 1,765 | 1,415 | -20% | 0 | 0 | — |
case-17 | fail→pass | 12,096 | 3,547 | -71% | 1 | 1 | 0% | 1,928 | 1,408 | -27% | 0 | 0 | — |
case-18 | fail→pass | 6,886 | 3,218 | -53% | 1 | 1 | 0% | 1,174 | 1,235 | +5% | 0 | 0 | — |
case-19 | fail→pass | 8,880 | 2,760 | -69% | 1 | 1 | 0% | 1,645 | 1,210 | -26% | 0 | 0 | — |
case-20 | pass→pass | 5,002 | 2,295 | -54% | 1 | 1 | 0% | 814 | 1,029 | +26% | 0 | 0 | — |
case-21 | fail→fail | 7,985 | 9,890 | +24% | 1 | 1 | 0% | 1,701 | 2,504 | +47% | 0 | 0 | — |
case-22 | fail→fail | 10,916 | 7,067 | -35% | 1 | 1 | 0% | 2,078 | 2,117 | +2% | 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 20 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 +48 percentage points is the difference between those two pass rates over the 20 comparable cases. 1 case got worse with the skill loaded, and it is 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.