AB parallel-code-review
Use when reviewing PRs, diffs, or completed work—covers both runtime bugs (resource leaks, edge cases, race conditions) and architecture concerns (design alignment, API contracts, consistency). Triggers when user says "review", "code review", "PR review", "审查", or after completing a feature. NOT for linter-only checks or quick syntax scans.
Use when reviewing PRs, diffs, or completed work—covers both runtime bugs (resource leaks, edge cases, race conditions) and architecture concerns (design…
As a process B 74/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
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: 3. 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 74/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 7 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 27 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1528 tokens
- low The response is described with custom markup (4 tags): a typed call is more reliable
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
- -224 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 342: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 27 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.