Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Track crypto prices, set alerts, and search coins via CoinGecko API.
.claude/skills/sundial-org-crypto-tracker/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -30% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 312% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -62% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 85% | 0% |
Track cryptocurrency prices, set price/percentage alerts, and search coins using the free CoinGecko API (no API key required).
bash# Single coin uv run {baseDir}/scripts/crypto.py price bitcoin # Multiple coins uv run {baseDir}/scripts/crypto.py price bitcoin ethereum solana # With more details (market cap, volume) uv run {baseDir}/scripts/crypto.py price bitcoin --detailed
bash# Find coin ID by name/symbol uv run {baseDir}/scripts/crypto.py search doge uv run {baseDir}/scripts/crypto.py search cardano
bash# Set price threshold alert uv run {baseDir}/scripts/crypto.py alert <user_id> bitcoin above 100000 uv run {baseDir}/scripts/crypto.py alert <user_id> ethereum below 3000 # Set percentage change alert (24h) uv run {baseDir}/scripts/crypto.py alert <user_id> bitcoin change 5 # ±5% uv run {baseDir}/scripts/crypto.py alert <user_id> solana drop 10 # -10% uv run {baseDir}/scripts/crypto.py alert <user_id> ethereum rise 15 # +15% # List user's alerts uv run {baseDir}/scripts/crypto.py alerts <user_id> # Remove an alert uv run {baseDir}/scripts/crypto.py alert-rm <alert_id> # Check all alerts (for cron/heartbeat) uv run {baseDir}/scripts/crypto.py check-alerts
Common symbols are automatically resolved:
btc → bitcoineth → ethereum sol → solanadoge → dogecoinada → cardanoxrp → rippledot → polkadotmatic → polygonlink → chainlinkavax → avalanche-2ltc → litecoin| Type | Example | Triggers When | |------|---------|---------------| | above | alert user btc above 100000 | Price >= $100,000 | | below | alert user eth below 3000 | Price <= $3,000 | | change | alert user btc change 5 | 24h change >= ±5% | | drop | alert user sol drop 10 | 24h change <= -10% | | rise | alert user eth rise 15 | 24h change >= +15% |
Check alerts periodically (e.g., every 15 minutes):
bashuv run {baseDir}/scripts/crypto.py check-alerts --json-output
Returns triggered alerts with user IDs for notification.
Alerts stored in {baseDir}/data/alerts.json with:
--json-output flag for machine-readable output| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 4,421 | 7,567 | +71% | 1 | 1 | 0% | 645 | 1,020 | +58% | 0 | 0 | — |
case-02 | fail→fail | 3,259 | 5,125 | +57% | 1 | 1 | 0% | 420 | 1,050 | +150% | 0 | 0 | — |
case-03 | fail→fail | 15,225 | 6,051 | -60% | 1 | 1 | 0% | 2,829 | 1,055 | -63% | 0 | 0 | — |
case-04 | pass→pass | 13,236 | 9,882 | -25% | 1 | 1 | 0% | 2,321 | 2,402 | +3% | 0 | 0 | — |
case-05 | pass→pass | 12,947 | 8,625 | -33% | 1 | 1 | 0% | 2,297 | 2,274 | -1% | 0 | 0 | — |
case-06 | pass→pass | 8,898 | 7,089 | -20% | 1 | 1 | 0% | 1,568 | 1,855 | +18% | 0 | 0 | — |
case-07 | fail→fail | 9,204 | 2,437 | -74% | 1 | 1 | 0% | 1,566 | 1,187 | -24% | 0 | 0 | — |
case-08 | fail→pass | 5,325 | 1,434 | -73% | 1 | 1 | 0% | 769 | 977 | +27% | 0 | 0 | — |
case-09 | fail→pass | 9,787 | 1,486 | -85% | 1 | 1 | 0% | 1,441 | 1,005 | -30% | 0 | 0 | — |
case-10 | fail→pass | 4,440 | 13,156 | +196% | 1 | 1 | 0% | 660 | 2,717 | +312% | 0 | 0 | — |
case-11 | fail→pass | 16,159 | 1,870 | -88% | 1 | 1 | 0% | 2,771 | 1,046 | -62% | 0 | 0 | — |
case-12 | fail→fail | 11,957 | 6,973 | -42% | 1 | 1 | 0% | 1,979 | 1,012 | -49% | 0 | 0 | — |
case-13 | fail→fail | 3,615 | 5,833 | +61% | 1 | 1 | 0% | 454 | 1,043 | +130% | 0 | 0 | — |
case-14 | fail→pass | 4,556 | 2,039 | -55% | 1 | 1 | 0% | 566 | 1,048 | +85% | 0 | 0 | — |
case-15 | fail→pass | 8,196 | 1,646 | -80% | 1 | 1 | 0% | 1,388 | 1,035 | -25% | 0 | 0 | — |
case-16 | fail→fail | 6,209 | 8,428 | +36% | 1 | 1 | 0% | 914 | 1,396 | +53% | 0 | 0 | — |
case-17 | pass→pass | 2,714 | 1,336 | -51% | 1 | 1 | 0% | 400 | 960 | +140% | 0 | 0 | — |
case-18 | pass→pass | 2,608 | 1,517 | -42% | 1 | 1 | 0% | 312 | 1,002 | +221% | 0 | 0 | — |
case-19 | fail→pass | 5,130 | 1,684 | -67% | 1 | 1 | 0% | 691 | 993 | +44% | 0 | 0 | — |
case-20 | fail→pass | 10,733 | 1,339 | -88% | 1 | 1 | 0% | 1,577 | 965 | -39% | 0 | 0 | — |
case-21 | fail→pass | 7,701 | 1,198 | -84% | 1 | 1 | 0% | 1,107 | 898 | -19% | 0 | 0 | — |
case-22 | pass→pass | 3,562 | 18,516 | +420% | 1 | 1 | 0% | 440 | 1,007 | +129% | 0 | 0 | — |
case-23 | pass→pass | 3,438 | 1,644 | -52% | 1 | 1 | 0% | 452 | 1,024 | +127% | 0 | 0 | — |
case-24 | pass→pass | 3,413 | 1,930 | -43% | 1 | 1 | 0% | 433 | 1,029 | +138% | 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. 24 cases were attempted, and 18 counted toward the lift figure. The other 6 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 +38 percentage points is the difference between those two pass rates over the 18 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.