AC idea-to-prompt
Convert the user's raw, unstructured, possibly disorganized thoughts (rambling, out-of-order, half-finished ideas) into a clear, structured, actionable prompt. Use whenever the user dumps a stream-of-consciousness input and wants it turned into something usable — whether a coding/dev task, a content task (scripts, product descriptions), or any general request. If critical information is missing or ambiguous in a way that would send the output in a fundamentally wrong direction, ask 1-3 targeted clarifying questions before producing the final structured prompt. Trigger on phrases like "我有一堆想法", "帮我整理一下", "转成提示词", "我想说的是", or when the user's message is clearly unstructured brainstorming rather than a direct request.
Convert the user's raw, unstructured, possibly disorganized thoughts (rambling, out-of-order, half-finished ideas) into a clear, structured, actionable prompt.
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 15 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 483 tokens
- 100Running it twice. No mutating operations
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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 723: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (3 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.