BC adaptive-eta
Give the user an honest time estimate before long-running work, re-estimate when it runs over, and ask before blowing far past it. Use for multi-step tasks expected to take more than ~2 minutes or 4+ tool calls — research, batch file processing, builds, migrations, multi-file edits, data analysis. Skip for quick answers and single-step edits. 长任务时间预估：预计超过约 2 分钟或需 4 次以上工具调用的多步任务，先报预估时间，超时主动更新，严重超时先征得同意。
Give the user an honest time estimate before long-running work, re-estimate when it runs over, and ask before blowing far past it.
As a process C 54/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 54/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 100Steps. 5 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 817 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- low The response is described with custom markup (5 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 405: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 5 items
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.