AB skill-optimizer
Analyze the current conversation history and local installed skills to identify missed skill triggers, overlapping or duplicate skills, weak metadata, stale or risky skills, and workflow gaps. Generate a detailed audit report with evidence and present actionable items that the user can choose to fix, merge, delete, or keep and skip. Use this whenever the user wants to audit, optimize, clean up, consolidate, or improve skill triggering quality, skill metadata, skill safety, or skill installation workflow.
As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, consistency, running it twice
How to improve
- 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: 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 70/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 8 mutating operations with no state check
- 40Consistency. Frontmatter name (skill-optimizer) differs from the folder (skill-optimizer-2)
- 60Result and completion. Output format stated, no completion criterion
- 65Failures and branches. 3 branches
- 100Tools and files. No external tools needed
- 100Steps. 59 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 1431 tokens
- medium 3 test cases, all positive: not one "should refuse" or "should ask first"
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)
- +1No license
- +2Single-language instructions
- +3Description length 509: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 59 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.