AB loop-polish
Fully automated iterative polishing: start project → full-stack integration verification → browser automation → scoring → auto-fix → loop until perfect → generate report. Invoke ONLY when user explicitly asks for loop polish, full verification with auto-fix loop, or automated acceptance with code changes. NOT for routine QA or quick reviews.
Fully automated iterative polishing: start project → full-stack integration verification → browser automation → scoring → auto-fix → loop until perfect →…
As a process B 71/100 · Nearly there — weak spots: failures and branches, 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: 1. 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 71/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (loop-polish) differs from the folder (loop-polish-skills)
- 50When it triggers. No condition that starts the skill
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 9 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Execution cost. Instruction body is 3449 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
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 343: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 9 items
- +3Output format is stated explicitly
- +4Has examples (16 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.