Install any skill in seconds. Free to start, no credit card required.
Get Started Free →open-gsd/grill-me
Relentless sequential interview that stress-tests a plan or design until every decision branch is resolved.
Passed 17 of 23 test cases with the skill, and 5 of 23 without it.
and 23 more in the full report
16 fixed1 passed either way2 still failing4 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 16 test cases the skill fixed. Same model, same prompt, with and without the skill.
For our search feature, I answered Q1: we will use Elasticsearch instead of Postgres full-text search. What is the next question in our interview?
| Checked | Without skill | With skill |
|---|---|---|
| Formats the next question with the header **Q2:**. | Passed | Passed |
| Includes a **Recommendation:** header with a single sentence reason for Q2. | Missed | Passed |
The instructions your model reads when the skill loads.
Use this skill when:
<core_principle> ONE QUESTION AT A TIME. Parallel questions destroy dependency order — the answer to Q2 is often contingent on the answer to Q1, and asking both at once forces the user to reason about a combinatoric space instead of a single fork. Ask, wait, absorb, ask the next.
RECOMMEND AN ANSWER. Every question ships with your recommendation and a one-line reason. The user's job is to confirm, override, or redirect — not to generate answers from scratch.
CODEBASE BEFORE QUESTION. If the answer exists in the repo — a convention, an existing pattern, a prior decision — find it and cite it rather than asking. </core_principle>
Before asking anything, read what the user has already said in this conversation plus any existing M###-CONTEXT.md, S##-CONTEXT.md, and .gsd/DECISIONS.md. Build a private list of every decision the plan depends on, in dependency order. Do not show this list — it is scaffolding.
If the plan touches unfamiliar code, spawn Agent(subagent_type=Explore) in parallel to map the relevant modules while you prepare Question 1. Do not wait for it to finish before starting the interview.
Pick the root decision — the one that the most other decisions depend on. Format:
**Q1:** <precise question>.
**Recommendation:** <your pick>, because <one sentence>.
test cases passed, vs 5 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.