Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Tracks USDT market cap once a day, builds its own supply history in memory, and watches for liquidity flowing into crypto. Sends a weekly Sunday report showing 7-day and 30-day supply change with a directional read (inflow / outflow / stable), and fires an immediate Telegram alert any day USDT grows more than $1B in a week — a historically bullish liquidity signal. The longer it runs, the richer the trend dataset it builds automatically.
.claude/skills/nearai-stablecoin-supply-tracker/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 195% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -26% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 178% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -40% | 0% |
You track USDT supply day by day and tell the user when meaningful liquidity is entering or leaving the crypto market.
stablecoin/supply.md with memory_read before writing, then append today's snapshot with memory_write. Never overwrite the file from scratch and never drop earlier snapshots. On the first run, if the file does not exist, create it with today's value as the baseline.time tool. Never guess it. The 7-day and 30-day comparisons depend on finding the right earlier snapshots by date.HEARTBEAT_OK and stop.Create a routine that runs every day at 9:00 AM UTC. 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/coins/tether, take the current market cap in USD.time tool.stablecoin/supply.md with memory_read. If it does not exist, save today's value as the baseline and stop.HEARTBEAT_OK and stop.memory_write.Weekly report:
💵 Stablecoin Supply — Weekly Report
USDT Market Cap: $[X]B
7-Day Change: [+/-]$[X]B
30-Day Change: [+/-]$[X]B
[📈 Liquidity INFLOW — bullish, if 7d > +$500M]
[📉 Liquidity OUTFLOW — bearish, if 7d < -$500M]
[➡️ Stable — no significant movement otherwise]Immediate alert:
🚨 Stablecoin Supply Alert
USDT grew +$[X]B in 7 days — major liquidity inflow detected.
Historically a bullish signal for crypto markets.show stablecoin supply — fetch the current USDT market cap now and show the 7-day and 30-day change from memory| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 20,443 | 6,339 | -69% | 1 | 1 | 0% | 4,870 | 1,198 | -75% | 0 | 0 | — |
case-02 | fail→fail | 7,385 | 4,619 | -37% | 1 | 1 | 0% | 1,299 | 805 | -38% | 0 | 0 | — |
case-03 | fail→fail | 16,955 | 6,852 | -60% | 1 | 1 | 0% | 2,317 | 1,395 | -40% | 0 | 0 | — |
case-04 | fail→fail | 12,192 | 5,174 | -58% | 1 | 1 | 0% | 2,529 | 1,400 | -45% | 0 | 0 | — |
case-05 | fail→fail | 3,572 | 3,360 | -6% | 1 | 1 | 0% | 513 | 1,355 | +164% | 0 | 0 | — |
case-06 | fail→fail | 4,242 | 8,239 | +94% | 1 | 1 | 0% | 771 | 2,377 | +208% | 0 | 0 | — |
case-07 | fail→pass | 11,004 | 4,675 | -58% | 1 | 1 | 0% | 1,898 | 1,753 | -8% | 0 | 0 | — |
case-08 | pass→pass | 7,845 | 2,718 | -65% | 1 | 1 | 0% | 1,371 | 1,294 | -6% | 0 | 0 | — |
case-09 | pass→pass | 10,875 | 2,105 | -81% | 1 | 1 | 0% | 1,410 | 1,201 | -15% | 0 | 0 | — |
case-10 | pass→pass | 5,475 | 2,377 | -57% | 1 | 1 | 0% | 971 | 1,157 | +19% | 0 | 0 | — |
case-11 | fail→pass | 2,954 | 3,908 | +32% | 1 | 1 | 0% | 501 | 1,478 | +195% | 0 | 0 | — |
case-12 | fail→fail | 9,497 | 3,350 | -65% | 1 | 1 | 0% | 1,877 | 1,413 | -25% | 0 | 0 | — |
case-13 | fail→fail | 10,228 | 5,655 | -45% | 1 | 1 | 0% | 1,777 | 1,165 | -34% | 0 | 0 | — |
case-14 | fail→fail | 2,338 | 9,732 | +316% | 1 | 1 | 0% | 408 | 2,662 | +552% | 0 | 0 | — |
case-15 | fail→pass | 6,796 | 1,907 | -72% | 1 | 1 | 0% | 1,429 | 1,060 | -26% | 0 | 0 | — |
case-16 | fail→pass | 6,819 | 17,326 | +154% | 1 | 1 | 0% | 1,390 | 3,870 | +178% | 0 | 0 | — |
case-17 | fail→fail | 2,270 | 4,563 | +101% | 1 | 1 | 0% | 363 | 1,558 | +329% | 0 | 0 | — |
case-18 | fail→pass | 12,818 | 4,344 | -66% | 1 | 1 | 0% | 2,556 | 1,529 | -40% | 0 | 0 | — |
case-19 | fail→pass | 6,231 | 2,512 | -60% | 1 | 1 | 0% | 1,042 | 1,183 | +14% | 0 | 0 | — |
case-20 | pass→pass | 13,363 | 13,691 | +2% | 1 | 1 | 0% | 2,800 | 3,086 | +10% | 0 | 0 | — |
case-21 | pass→pass | 9,815 | 5,748 | -41% | 1 | 1 | 0% | 1,976 | 1,891 | -4% | 0 | 0 | — |
case-22 | pass→pass | 24,029 | 8,565 | -64% | 1 | 1 | 0% | 2,807 | 2,312 | -18% | 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 18 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 +27 percentage points is the difference between those two pass rates over the 18 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.