MichelRojo86WPP/copilot-config / skills/grill-me
grill-me
VerifiedRelentless sequential interview that stress-tests a plan or design until every decision branch is resolved. Use when the user wants to "grill me", "stress-test the plan", "interrogate my design", "resolve the decision tree", or whenever a plan feels hand-wavy, under-specified, or carries hidden coupling that planning phases must surface before execution. Pairs with the discuss phase and blocks execution until alignment is reached.
<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 confirms, overrides, or redirects — not generates 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>
Step 1: Map the decision tree silently
Read what the user has said plus any existing context files. Build a private list of every decision the plan depends on, in dependency order. Do not show this list.
Step 2: Ask Question 1
Pick the root decision — the one most other decisions depend on. Format:
**Q1:** <precise question>.
**Recommendation:** <your pick>, because <one sentence>.
Alternatives: <A | B | C>.
Stop. Wait for the answer.
Step 3: Absorb and branch
Take the answer. Cross off resolved branches. Add new ones. If the answer is ambiguous, ask ONE clarifying follow-up — not three.
Step 4: Continue until the tree is closed
Repeat in dependency order. Stop when:
- Every open decision is resolved or explicitly deferred
- The user says to stop
- Nothing remaining would materially change the plan
Step 5: Offer to capture decisions
Options: append to a decisions file, update context docs, or leave as conversation context. Ask which — do not auto-write.
<anti_patterns>
- Parallel questions: ask one at a time
- Yes/no railroading: offer options, not binary
- Recommendation-free questions: always include your pick
- Asking what the codebase already answers
- Grilling past useful horizon (implementation details = stop) </anti_patterns>
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |