AC local-model-optimizer
Auto-detect hardware (GPU VRAM, system RAM, CPU), recommend optimal local models from Ollama registry, configure Ollama with tuned parameters, and set up hybrid cloud/local routing in OpenClaw. Supports Gemma 4, Llama, Mistral, Qwen, Phi, and other Ollama-compatible models. Calculates cost savings vs cloud API. Use when asked to "set up local model", "optimize local AI", "reduce API costs", "configure Ollama", "hardware check for AI", "hybrid routing", "cloud local routing", "run AI locally", "free AI", "zero cost model", "which model fits my hardware", "auto-config Ollama", or when users mention high API costs and want a local alternative.
As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Dangerous commands
cmd-pipe-to-shellscripts/local-model-optimizer.py:232Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; the skill's own vendor host)['sh', '-c', 'curl -fsSL https://ollama.com/install.sh | sh'],
code literalvendor-host
Files scanned: 4. 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 58/100
- 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
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 100Tools and files. No external tools needed
- 100Steps. 23 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 767 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
- +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 12 example trigger phrases
- +3Description length 648: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.