AC aa-benchmarking-framework
Composite scoring and efficiency frontier analysis for LLM evaluation — combines multiple quality dimensions (accuracy, latency, cost, consistency) into a single Pareto-optimal ranking. Use when comparing models or agent configurations across competing objectives, building evaluation dashboards, or identifying the efficiency frontier for model selection. Implements weighted composite scores, Pareto frontier detection, and radar chart visualisation for multi-dimensional LLM benchmarking.
As a process C 53/100 · 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 · 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 "status" - note
frontmatter-keyunknown frontmatter key "requires"
Process rating: all ten parameters 53/100
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 10 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 352 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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 491: enough signal without eating the budget
- +4Structure: 4 headings
- +3Step-by-step instructions: 10 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.