Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Access cryptocurrency market data from CoinPaprika: prices, tickers, OHLCV, exchanges, contract lookups for 12,000+ coins and 350+ exchanges. Free tier, no API key needed. Install MCP: add https://mcp.coinpaprika.com/sse as SSE server, or install plugin: /plugin marketplace add coinpaprika/claude-marketplace
.claude/skills/davepoon-coinpaprika-api/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -47% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -44% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -47% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -27% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -25% | 0% |
Access cryptocurrency market data for 12,000+ coins and 350+ exchanges via the CoinPaprika MCP server.
Add the MCP server to your Claude Code config:
json{ "mcpServers": { "coinpaprika": { "url": "https://mcp.coinpaprika.com/sse" } } }
Or install the full plugin (includes agent + skill):
/plugin marketplace add coinpaprika/claude-marketplace
/plugin install coinpaprika@coinpaprika-pluginsgetGlobal — Total market cap, BTC dominance, 24h volumegetTickers / getTickersById — Price, market cap, volume for coinsgetTickersHistoricalById — Historical price ticksgetCoins / getCoinById — Coin details, descriptions, links, teamsgetCoinEvents / getCoinExchanges / getCoinMarkets — Events, exchange listings, trading pairsgetCoinOHLCVHistorical / getCoinOHLCVLatest / getCoinOHLCVToday — Candlestick datagetExchanges / getExchangeByID / getExchangeMarkets — Exchange datagetPlatforms / getContracts / getTickerByContract / getHistoricalTickerByContract — Contract lookupssearch / resolveId — Find coins, exchanges, people, tagspriceConverter — Convert between currenciesgetTags / getTagById / getPeopleById — Categories and team infokeyInfo / getMappings / getChangelogIDs / status — Account and metadataPattern: {symbol}-{name} lowercase. Examples: btc-bitcoin, eth-ethereum, sol-solana.
Use search or resolveId if unsure of the correct ID.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 4,610 | 2,659 | -42% | 1 | 1 | 0% | 704 | 720 | +2% | 0 | 0 | — |
case-02 | fail→fail | 4,476 | 5,119 | +14% | 1 | 1 | 0% | 874 | 910 | +4% | 0 | 0 | — |
case-03 | fail→fail | 4,151 | 4,936 | +19% | 1 | 1 | 0% | 750 | 833 | +11% | 0 | 0 | — |
case-04 | pass→pass | 5,273 | 8,087 | +53% | 1 | 1 | 0% | 866 | 1,041 | +20% | 0 | 0 | — |
case-05 | pass→pass | 13,424 | 9,658 | -28% | 1 | 1 | 0% | 2,782 | 2,565 | -8% | 0 | 0 | — |
case-06 | pass→pass | 5,718 | 8,408 | +47% | 1 | 1 | 0% | 1,330 | 2,237 | +68% | 0 | 0 | — |
case-07 | fail→pass | 10,175 | 2,789 | -73% | 1 | 1 | 0% | 1,997 | 1,056 | -47% | 0 | 0 | — |
case-08 | fail→fail | 18,029 | 7,759 | -57% | 1 | 1 | 0% | 4,264 | 1,091 | -74% | 0 | 0 | — |
case-09 | fail→pass | 11,432 | 3,492 | -69% | 1 | 1 | 0% | 2,044 | 1,146 | -44% | 0 | 0 | — |
case-10 | fail→fail | 4,816 | 4,659 | -3% | 1 | 1 | 0% | 938 | 712 | -24% | 0 | 0 | — |
case-11 | fail→pass | 10,693 | 2,830 | -74% | 1 | 1 | 0% | 1,993 | 1,062 | -47% | 0 | 0 | — |
case-12 | fail→pass | 5,297 | 1,265 | -76% | 1 | 1 | 0% | 983 | 714 | -27% | 0 | 0 | — |
case-13 | fail→pass | 5,870 | 2,017 | -66% | 1 | 1 | 0% | 1,170 | 879 | -25% | 0 | 0 | — |
case-14 | fail→fail | 10,427 | 7,260 | -30% | 1 | 1 | 0% | 2,164 | 1,591 | -26% | 0 | 0 | — |
case-15 | fail→fail | 9,165 | 2,945 | -68% | 1 | 1 | 0% | 1,692 | 711 | -58% | 0 | 0 | — |
case-16 | fail→fail | 11,944 | 5,623 | -53% | 1 | 1 | 0% | 2,146 | 800 | -63% | 0 | 0 | — |
case-17 | fail→fail | 14,037 | 4,464 | -68% | 1 | 1 | 0% | 2,361 | 741 | -69% | 0 | 0 | — |
case-18 | fail→fail | 7,875 | 4,008 | -49% | 1 | 1 | 0% | 1,520 | 739 | -51% | 0 | 0 | — |
case-19 | fail→fail | 7,834 | 4,154 | -47% | 1 | 1 | 0% | 1,672 | 758 | -55% | 0 | 0 | — |
case-20 | fail→fail | 3,677 | 4,009 | +9% | 1 | 1 | 0% | 681 | 752 | +10% | 0 | 0 | — |
case-21 | fail→fail | 10,773 | 3,577 | -67% | 1 | 1 | 0% | 1,935 | 678 | -65% | 0 | 0 | — |
case-22 | fail→pass | 12,799 | 2,495 | -81% | 1 | 1 | 0% | 2,389 | 943 | -61% | 0 | 0 | — |
case-23 | fail→pass | 11,920 | 1,639 | -86% | 1 | 1 | 0% | 2,117 | 787 | -63% | 0 | 0 | — |
case-24 | fail→pass | 4,508 | 1,369 | -70% | 1 | 1 | 0% | 782 | 709 | -9% | 0 | 0 | — |
case-25 | fail→fail | 9,043 | 5,231 | -42% | 1 | 1 | 0% | 1,809 | 826 | -54% | 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. 25 cases were attempted, and 12 counted toward the lift figure. The other 13 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 +32 percentage points is the difference between those two pass rates over the 12 comparable cases. 3 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.