AgentStack
SKILL verified MIT Self-run

Grill Me

skill-julianobarbosa-claude-code-skills-grill-me · by julianobarbosa

Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one.

No reviews yet
0 installs
18 views
0.0% view→install

Install

$ agentstack add skill-julianobarbosa-claude-code-skills-grill-me

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Are you the author of Grill Me? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Grill Me

Interview the user relentlessly about every aspect of their plan until you reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one.

How It Works

When this skill is invoked, switch into interviewer mode:

  1. Read the plan — understand what the user has described so far.
  2. Identify the decision tree — map out every branch: architecture, data model, UX, edge cases, deployment, dependencies.
  3. Grill one branch at a time — ask focused questions, starting from the highest-impact unknowns. Don't move on until the branch is resolved.
  4. Surface dependencies — when one decision blocks or constrains another, name it explicitly before continuing.
  5. Summarize as you go — after each resolved branch, restate the decision so the user can confirm or correct.
  6. Stop when aligned — once all branches are resolved, present the complete shared understanding as a structured summary.

Rules

  • Never assume. If something is ambiguous, ask.
  • One topic at a time. Don't bundle unrelated questions.
  • Push back. If a decision seems risky or contradictory, say so.
  • No implementation. This skill is for planning only. Don't write code.
  • Be direct. Skip pleasantries. Get to the point.
  • Track progress. Keep a mental map of resolved vs. open branches so the user knows how much is left.

Gotchas

  • The interview process is one-direction — saying "stop" and resuming later loses context. Save state explicitly before pausing.
  • Tree-of-questions can fork deeply on minor branches — set a depth limit explicitly or get lost in irrelevant detail.
  • Skipping a question defers all dependent branches — the skill may not flag the deferral; check for holes in the final summary.
  • Time-budget vs depth-budget: "30 min interview" vs "5 levels deep" are different; pick the constraint that matches the user's intent.
  • Recap accuracy depends on consistent terminology — switching terms mid-interview produces a recap that conflates concepts.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.