AB okx-wallet-portfolio
Use this skill when the user provides a specific wallet address and wants to check its balance, token holdings, portfolio value, or DeFi positions. Typical triggers: 'check balance of 0xAbc...', 'show tokens in this address', 'what tokens does 0xAbc hold', 'portfolio value of this address', address portfolio value, multi-chain balance lookup for a given address. Supports XLayer, Solana, Ethereum, Base, BSC, Arbitrum, Polygon, and 20+ other chains. Do NOT use when the user asks about their own wallet without providing an address (e.g., 'check my wallet balance', 'show my assets', '查看我的余额') — use okx-agentic-wallet instead, which queries the logged-in wallet. Do NOT use for PnL analysis, DEX history, realized/unrealized profit — use okx-dex-market. Do NOT use for signal tracking — use okx-dex-signal. Do NOT use for meme scanning — use okx-dex-trenches. Do NOT use for programming questions about balance APIs or integration.
As a process B 70/100 · Nearly there — weak spots: result and completion, running it twice
How to improve
- 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 · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 70/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 60 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 7 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3725 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 tags): a typed call is more reliable
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 934: 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: 20 headings
- +3Step-by-step instructions: 60 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.