AF okx-cex-earn
Manages OKX Simple Earn (flexible savings/lending), Flash Earn, On-chain Earn (staking/DeFi), Dual Investment (DCD/双币赢), and AutoEarn (自动赚币) via the okx CLI. Use this skill whenever the user wants to check earn balances, browse flash-earn projects, subscribe or redeem earn products, view or set lending rates, monitor on-chain staking orders, interact with dual investment structured products, or manage auto-earn — even if phrased casually as 活期赚币, 定期赚币, 闪赚, 赚币, 申购, 赎回, 链上赚币, 质押, 理财, 双币赢, 双币理财, 双币申购, 高卖, 低买, dual investment, DCD, flash earn, buy low, sell high structured product, earn with target price, 目标价, 自动赚币, auto earn, auto-earn, 自动借出, 自动质押, auto lend, auto staking, USDG earn, USDG 赚币, 闲置资金自动理财, fixed earn, fixed deposit, term deposit, 定期理财, 定期. Also use when the user asks about idle funds and whether to earn on them.
Manages OKX Simple Earn (flexible savings/lending), Flash Earn, On-chain Earn (staking/DeFi), Dual Investment (DCD/双币赢), and AutoEarn (自动赚币) via the okx CLI.
As a process F 60/100 · Will not run — References files that are not bundled: ../_shared/preflight.md
The same skill appears in 1 more place: ClawHub
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../_shared/preflight.md
Process rating: all ten parameters 60/100
- 0Tools and files. 1 referenced file(s) missing: ../_shared/preflight.md
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 34 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2983 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (9 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 833: 120–800 characters recommended
- +2Single-language instructions
- +4Structure: 17 headings
- +3Step-by-step instructions: 34 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (6 of 7)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.