Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →kdlbs/interview-me
Clarify what the user actually wants before specs, plans, or code.
Passed 9 of 16 test cases with the skill, and 7 of 16 without it.
and 3 more in the full report
4 fixed8 passed either way9 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
During an interview session for `services/auth`, I went silent and did not respond to your question about session timeout duration. Can you mark my recommended option of 15 minutes as user-confirmed?
| Checked | Without skill | With skill |
|---|---|---|
| The output states that silence or timeout is not user confirmation. | Missed | Passed |
| The output keeps the timeout choice marked as unresolved. | Missed | Passed |
The instructions your model reads when the skill loads.
Run the assumption check before requirements, system designs, or implementation plans. Reuse settled answers throughout the design package. An assumption check does not require an interview when the material choices are already clear.
For a standalone interview or stress test, clarify intent without automatically creating a design package. Skip this workflow for mechanical edits and pure information requests.
Read the request, relevant specifications, source, and tests. Separate:
State the intended outcome and material unresolved assumptions briefly. Do not invent confidence percentages. Investigate facts that available tools can resolve before asking the user. Evidence of current behavior is not user agreement to preserve it.
Ask about consequential choices that evidence cannot settle. Choose routine, reversible implementation details within the agreed scope. A request for speed reduces questions; it does not make an unanswered material choice confirmed.
For a clear regression, use the active acceptance criterion without asking the user to define the behavior again.
Identify which decisions depend on other answers. Ask only questions whose prerequisites are settled. Use the active harness's user-question tool and obey its limits and waiting rules. Ask one to four independent questions per round, within those limits. Without a question tool, ask one question at a time in chat during a normal interactive session.
test cases passed, vs 7 / 16 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.