BB okx-dex-market
HARD BLOCK — NEVER use this skill for prediction-market / Polymarket UpDown queries. Route to okx-dapp-discovery when (a) a named DApp (Polymarket/Aave/Hyperliquid/PancakeSwap/Morpho) appears with any timeframe, OR (b) any 涨跌 / updown / 'up or down' phrase appears for BTC/ETH/SOL/XRP/BNB/DOGE/HYPE (e.g. '<COIN> 涨跌市场', '5 分钟涨跌', 'BTC up or down'). Example: 'BTC 5 分钟涨跌市场' → okx-dapp-discovery (NOT K-line). These are Polymarket prediction markets, not on-chain price queries. Use THIS skill for on-chain market data: token prices/价格, K-line/OHLC/candlestick/K线 charts, index prices, and wallet PnL/盈亏分析 (win rate, my wallet's DEX trade history, realized/unrealized PnL per token). Triggers: 'token price', 'price chart', 'K线', 'OHLC', 'how much is X worth', 'show my PnL', '胜率', '盈亏', 'my wallet DEX history', 'realized/unrealized profit'. NOTE: WebSocket script/脚本/bot → okx-dex-ws. ALSO the OWNER of Market API payment handling — route here (NOT okx-x402-payment) for: 'onchainos market 报 402', 'market price 402', 'market API pricing/计费/收费', Basic/Premium tier/quota/额度/免费额度, 'ok-web3-openapi-pay' header, 30 天过渡期/grace period, any MARKET_API_* notification code (NEW_USER_INTRO / OLD_USER_GRACE / OLD_USER_POST_GRACE_* / *_OVER_QUOTA), or 'confirming:true' response from onchainos market commands.
As a process B 75/100 · Nearly there — weak spots: result and completion, progress reporting
How to improve
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:154High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- **Solana SOL price/kline**: The native SOL address (`11111111111111111111111111111111`) does not work for `market price` or `market kline`. Use the wSOL SPL token address (`So11…111
quoted
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1302 chars, limit 1024
Process rating: all ten parameters 75/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 26 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2258 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 1302: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 19 headings
- +3Step-by-step instructions: 26 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.