BC ollama-herd
Ollama multimodal model router for Llama, Qwen, DeepSeek, Phi, and Mistral — plus mflux image generation, speech-to-text, and embeddings. Self-hosted Ollama local AI (macOS, Linux, Windows) with 7-signal scoring, Ollama queue management, real-time dashboard, and Ollama health monitoring. Routes Ollama LLM, image, STT, and embedding requests across macOS, Linux, and Windows devices. Ollama本地推理路由 | Ollama enrutador IA local. Use when the user asks about their Ollama fleet, Ollama inference routing, Ollama node status, or Ollama fleet performance.
Ollama multimodal model router for Llama, Qwen, DeepSeek, Phi, and Mistral — plus mflux image generation, speech-to-text, and embeddings.
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions
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
- note
frontmatter-keyunknown frontmatter key "homepage"
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
- 60Tools and files. Uses tools (web, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 42 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2557 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
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
- +1No license
- +2Single-language instructions
- +3Description length 550: enough signal without eating the budget
- +4Structure: 29 headings
- +3Step-by-step instructions: 42 items
- +4Has examples (16 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.