AF 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". Do NOT trigger for: 纯技术架构设计（无模型选择需求）、招聘/人事管理、纯社交聊天、不涉及AI工具使用的财务管理。
智能模型路由与Token成本优化顾问 / Smart LLM Router & Token Cost Optimizer.
As a process F 42/100 · Will not run — References files that are not bundled: references/config-templates.md, references/model-tiers.md, references/routing-strategies.md
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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/config-templates.md - warning
missing-refreference to a missing file: references/model-tiers.md - warning
missing-refreference to a missing file: references/routing-strategies.md
Process rating: all ten parameters 42/100
- 0Tools and files. 3 referenced file(s) missing: references/config-templates.md, references/model-tiers.md, references/routing-strategies.md
- 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
- 40Consistency. Frontmatter name (token-router) differs from the folder (tokenrouter)
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 100Steps. 78 steps
- 100Execution cost. Instruction body is 3673 tokens
- 100Running it twice. No mutating operations
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 837: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 14 example trigger phrases
- +4Structure: 41 headings
- +3Step-by-step instructions: 78 items
- +4Has examples (18 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.