AA remote-skill-test
Use when the user wants to test an agent skill on a remote jump host after updating it locally. Triggers on "test skill remotely", "remote test", "远程测试 skill", "到跳板机上测试", "验证 skill 更新效果". Does NOT run the target skill locally — only orchestrates remote execution and report comparison.
As a process A 80/100 · Runs to the end — no weak spots found
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: 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 80/100
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 23 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2999 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 285: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 23 items
- +3Output format is stated explicitly
- +4Has examples (14 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.