Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Real-time crypto market data, wallet portfolio tracking, and token analytics across 88+ blockchains. Use when the user wants to check any token price (by name, symbol, or contract address), look up wallet balances and holdings across all chains, get historical price data, track portfolio PnL, monitor whale wallets, find new tokens, or get oracle-grade pricing. Requires free API key from mobula.io.
.claude/skills/leoyeai-mobula/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 448% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 681% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 215% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 147% | 0% |
Real-time crypto market data, wallet tracking, and on-chain analytics across 88+ blockchains. Oracle-grade pricing trusted by Chainlink, Supra, and API3.
USE WHEN the user:
DON'T USE WHEN:
mobula_market_data)Endpoint: GET https://api.mobula.io/api/1/market/data
Get real-time price, volume, market cap, and liquidity for any token across all supported chains.
Parameters:
asset (required): Token name, symbol, or contract addressblockchain (optional): Specific chain to queryReturns:
Usage examples:
When to use:
mobula_wallet_portfolio)Endpoint: GET https://api.mobula.io/api/1/wallet/portfolio
Get complete portfolio for any wallet across all 88 chains in a single call.
Parameters:
wallet (required): Wallet addressblockchains (optional): Comma-separated list to filter specific chainscache (optional): Use cached data (faster, slightly less fresh)Returns:
Usage examples:
When to use:
mobula_market_history)Endpoint: GET https://api.mobula.io/api/1/market/history
Get historical price data for any token with flexible timeframes.
Parameters:
asset (required): Token name, symbol, or addressfrom (optional): Start timestamp (Unix seconds)to (optional): End timestamp (Unix seconds)period (optional): Data granularityReturns:
Usage examples:
When to use:
mobula_market_trades)Endpoint: GET https://api.mobula.io/api/1/market/trades
Live trade feed for any token across all DEXs and chains.
Parameters:
asset (required): Token name, symbol, or addresslimit (optional): Number of trades to return (default: 50, max: 300)Returns:
Usage examples:
When to use:
mobula_wallet_transactions)Endpoint: GET https://api.mobula.io/api/1/wallet/transactions
Full transaction history for any wallet across all chains.
Parameters:
wallet (required): Wallet addressfrom (optional): Start timestampto (optional): End timestampasset (optional): Filter by specific tokenlimit (optional): Number of transactions (default: 100)Returns:
Usage examples:
When to use:
mobula_market_multi)Endpoint: GET https://api.mobula.io/api/1/market/multi-data
Get market data for multiple tokens in a single request (batch endpoint).
Parameters:
assets (required): Comma-separated list of token names/symbols/addressesReturns:
mobula_market_data but for multiple tokensUsage examples:
When to use:
mobula_metadata)Endpoint: GET https://api.mobula.io/api/1/metadata
Get detailed metadata for any token.
Parameters:
asset (required): Token name, symbol, or addressReturns:
Usage examples:
When to use:
Required: All API requests require authentication via API key.
Setup:
bash export MOBULA_API_KEY="your_key_here"
Header format:
Authorization: ${MOBULA_API_KEY}If authentication fails (401/403):
echo $MOBULA_API_KEYIMPORTANT - Read Before Using:
OpenClaw's heartbeat system checks conditions every ~30 minutes. Use this for proactive monitoring.
Every heartbeat:
mobula_wallet_portfolioEvery heartbeat:
mobula_wallet_transactionsmobula_market_datamobula_market_tradesEvery 4-6 hours on heartbeat:
mobula_market_data queriesmobula_market_historymobula_metadataInstead of simple "price > X" alerts, create contextual ones:
Example: "Alert me if Bitcoin moves >5% in 1 hour BUT only if volume is 2x above 24h average"
Every heartbeat:
mobula_market_dataUser asks: "Should I buy this token?"
mobula_market_data → current price, mcap, volume, liquiditymobula_market_history → 7d and 30d trendmobula_market_trades → recent activity (accumulation or distribution?)mobula_metadata → project info, socials, contract verificationResponse format:
TOKEN Analysis
Price: $0.042 (down 8% 24h, up 156% 7d)
- Near 7d high, down from $0.051
- Still up 400% from 30d low
Fundamentals:
- Mcap: $2.1M (small cap, high risk/reward)
- Liquidity: $280K (decent for size)
- Volume: $1.2M 24h (healthy)
On-chain:
- Recent trades show buying pressure (3:1 buy/sell ratio)
- 2 large buys ($50K+) in last 2h
Project:
- Contract verified
- Active Twitter (12K followers)
Risk: Small cap, high volatility. Don't ape more than you can lose.Don't just say "price is $0.003" Say: "Price $0.003 (down 8% 24h, down 65% from ATH of $0.089 on Dec 1st, but up 12% from 7d low)"
mobula_market_multiexport MOBULA_API_KEY='your_key'"mobula_market_multi for batch queries instead of multiple mobula_market_data calls88+ chains including: Ethereum, Base, Arbitrum, Optimism, Polygon, BNB Chain, Avalanche, Solana, Fantom, Cronos, and many more.
Full list: https://docs.mobula.io/blockchains
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-14 | fail→fail | 23,885 | 15,666 | -34% | 1 | 1 | 0% | 4,295 | 7,264 | +69% | 0 | 0 | — |
case-01 | fail→fail | 15,644 | 9,250 | -41% | 1 | 1 | 0% | 2,835 | 5,251 | +85% | 0 | 0 | — |
case-02 | fail→pass | 8,220 | 13,380 | +63% | 1 | 1 | 0% | 1,265 | 6,937 | +448% | 0 | 0 | — |
case-03 | fail→fail | 11,760 | 8,520 | -28% | 1 | 1 | 0% | 2,346 | 6,150 | +162% | 0 | 0 | — |
case-04 | pass→pass | 9,396 | 2,818 | -70% | 1 | 1 | 0% | 1,667 | 5,067 | +204% | 0 | 0 | — |
case-05 | fail→pass | 21,692 | 3,446 | -84% | 1 | 1 | 0% | 4,108 | 5,131 | +25% | 0 | 0 | — |
case-06 | pass→pass | 10,585 | 5,903 | -44% | 1 | 1 | 0% | 2,173 | 5,610 | +158% | 0 | 0 | — |
case-07 | pass→pass | 12,389 | 8,136 | -34% | 1 | 1 | 0% | 2,319 | 5,951 | +157% | 0 | 0 | — |
case-08 | fail→pass | 5,290 | 9,753 | +84% | 1 | 1 | 0% | 802 | 6,260 | +681% | 0 | 0 | — |
case-09 | fail→fail | 6,207 | 12,354 | +99% | 1 | 1 | 0% | 989 | 5,969 | +504% | 0 | 0 | — |
case-10 | fail→pass | 10,006 | 10,391 | +4% | 1 | 1 | 0% | 2,090 | 6,592 | +215% | 0 | 0 | — |
case-11 | pass→pass | 11,486 | 12,274 | +7% | 1 | 1 | 0% | 2,228 | 7,013 | +215% | 0 | 0 | — |
case-12 | pass→pass | 20,111 | 8,615 | -57% | 1 | 1 | 0% | 3,810 | 6,195 | +63% | 0 | 0 | — |
case-13 | pass→pass | 22,368 | 14,992 | -33% | 1 | 1 | 0% | 3,653 | 7,495 | +105% | 0 | 0 | — |
case-15 | fail→pass | 14,033 | 6,749 | -52% | 1 | 1 | 0% | 2,355 | 5,826 | +147% | 0 | 0 | — |
case-16 | pass→pass | 13,118 | 4,282 | -67% | 1 | 1 | 0% | 1,962 | 5,204 | +165% | 0 | 0 | — |
case-17 | fail→pass | 14,427 | 5,902 | -59% | 1 | 1 | 0% | 2,622 | 5,670 | +116% | 0 | 0 | — |
case-18 | fail→fail | 9,570 | 3,413 | -64% | 1 | 1 | 0% | 1,523 | 5,128 | +237% | 0 | 0 | — |
case-19 | fail→fail | 16,711 | 15,940 | -5% | 1 | 1 | 0% | 2,912 | 7,547 | +159% | 0 | 0 | — |
case-20 | pass→pass | 4,980 | 3,064 | -38% | 1 | 1 | 0% | 846 | 5,036 | +495% | 0 | 0 | — |
case-21 | pass→pass | 3,319 | 4,124 | +24% | 1 | 1 | 0% | 470 | 5,203 | +1007% | 0 | 0 | — |
case-22 | pass→pass | 14,351 | 9,497 | -34% | 1 | 1 | 0% | 2,414 | 6,221 | +158% | 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 21 counted toward the lift figure. The other 1 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 21 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.