AD model_router
Model Router - Parallel multi-LLM invocation with result merging. Use when: need better answers, compare model outputs, or get best result from multiple LLMs. / 并行调用多模型 - 并行调用多个大模型，结果智能合并。
As a process D 46/100 · Unfinished process — weak spots: steps, when it triggers, inputs and preconditions
How to improve
For the model run — optional
- 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
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens)
Process rating: all ten parameters 46/100
- 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
- 20When it triggers. No condition that starts the skill
- 25Steps. 1 steps
- 40Consistency. Frontmatter name (model_router) differs from the folder (model-router-waai)
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Execution cost. Instruction body is 450 tokens
- 100Running it twice. No mutating operations
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)
- +3No numbered steps or checklist
- +1No license
- +2Single-language instructions
- +3Description length 188: enough signal without eating the budget
- +4Structure: 9 headings
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.
External checks
ClawHub: clean
This is a disclosed multi-model routing prototype with privacy caveats, but the provided code does not actually transmit data or show hidden behavior.
LLM: benign (high) · VirusTotal: · 29 May 2026