AD adaptive-routing
Routes LLM requests to a local model first (Ollama, LM Studio, llamafile), validates the response quality, and escalates to cloud only when the local result fails. Tracks local vs escalated vs cloud outcomes in a persistent dashboard. Use when: (1) user asks to run a task with a local model first, (2) user wants to reduce cloud API costs or keep requests private, (3) user wants post-outcome quality validation before committing to a local result, (4) user asks to see token savings or the routing dashboard, (5) any request where local-vs-cloud routing should be decided automatically with a quality gate. Supports Ollama, LM Studio, and llamafile as local providers.
As a process D 44/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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
-
medium Dangerous commands
cmd-pipe-to-shellreferences/local-providers.md:12Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)curl -fsSL https://ollama.ai/install.sh | sh
vendor-host
Files scanned: 10. 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 44/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 75Steps. 3 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1515 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 670: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 3 items
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 5 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.