AC money-never-sleep
MNS (Money Never Sleeps) CLI operations manual for autonomous agents. Tracks an investment portfolio in a local ledger, reads market sentiment (CNN Fear & Greed Index), and generates target-weight rebalancing suggestions. Use when the user asks to view holdings, record a trade they already executed, generate a daily strategy report, inspect or tune strategy parameters, or run a backtest. CRITICAL: MNS connects to NO broker and executes NO trades. `mns buy` / `mns sell` are bookkeeping entries that record trades the human has ALREADY executed elsewhere. Never call them to "act on" a suggestion — doing so silently corrupts every downstream number. Triggers: "查看持仓", "记录买入", "记录卖出", "生成策略报告", "调仓建议", "再平衡", "恐贪指数", "更新价格", "现金余额", "交易历史", "回测策略", "调整策略参数", "MNS"
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 2. 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 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1516 tokens
- low 10 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 770: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (8 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.