AC smart-router
Intelligent task routing between local and cloud Ollama LLM instances. Use when the user wants cost-efficient AI responses by routing simple tasks to a local Ollama model and complex tasks to a more powerful remote/cloud Ollama instance. Automatically classifies task complexity, detects system capabilities, and delegates to the appropriate model tier. Use for any request where you want to balance latency vs capability, or when explicitly asked to use smart routing, local-first routing, or Ollama model selection.
As a process C 62/100 · Has gaps — weak spots: result and completion, consistency, running it twice
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: 15. 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 62/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (smart-router) differs from the folder (ollama-smart-router)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 35 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Execution cost. Instruction body is 1823 tokens
- low 13 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- -33 of 8 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 517: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 35 items
- +4Has examples (15 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.