AC token-router
智能模型路由与Token成本优化顾问 / Smart LLM Router & Token Cost Optimizer. 帮助用户为不同复杂度的AI任务选择最合适的模型层级（从极致性价比到旗舰级）， 通过任务复杂度评估、模型分级推荐、安全强制升级规则，在保证质量的前提下节省70-90%的Token成本。 同时提供Trae、OpenClaw、Hermes Agent等平台的多模型路由配置方案。 必须在以下场景触发此技能——即使用户没有直接说"帮我选模型"，只要核心诉求涉及成本或模型选择： 用户觉得API费用太贵想省钱；用户想知道某个具体任务该用哪个模型；用户要配置Hermes或OpenClaw的多模型路由； 用户讨论Token消耗、API成本、模型价格对比；用户问"用GPT-4o还是Haiku""Sonnet和Opus选哪个"； 用户提到一人公司/独立开发者的AI工具成本问题；用户要搭建需要不同模型处理不同任务的Agent工作流； 用户说"帮我省钱""Token太贵""成本太高""怎么降本""API账单""模型路由""智能调度""模型分级"。 Also trigger when the user discusses: "which model should I use", "reduce API costs", "token cost optimization", "LLM routing", "model selection", "save money on AI", "cheaper model", "cost vs quality", "configure Hermes/OpenClaw multi-model routing", "model tier", "intelligent scheduling".
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting
How to improve
- 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: 6. 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 64/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 55 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1673 tokens
- 100Running it twice. No mutating operations
- low 10 top-level sections: this looks like several domains in one skill
- medium 4 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
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
- +1No license
- +2Single-language instructions
- +5Description quotes 14 example trigger phrases
- +3Description length 770: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 55 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.