AB prompt-optimizer
Iterative prompt optimizer for complex tasks. Strictly implements ACON's two-stage iterative optimization + APE automatic prompt engineering. Only triggers when user explicitly requests it, actively collects feedback after optimization, supports multi-round iteration until satisfied.
As a process B 72/100 · Nearly there — weak spots: inputs and preconditions, 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "usage"
Process rating: all ten parameters 72/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (prompt-optimizer) differs from the folder (prompt-optimizer-en)
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 58 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Execution cost. Instruction body is 1224 tokens
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)
- -221 emoji in the instructions: noise for the model
- +2Single-language instructions
- +3Description length 284: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 58 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.