paulrberg/dot-agents

grill-me

Interview the user relentlessly about a plan or design until every branch of the decision tree has an explicit recorded decision and no open questions remain. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

First seen Aug 4, 2026

Installation

$ npx skills add paulrberg/dot-agents --skill grill-me

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from paulrberg/dot-agents · top by installs.

npx skills add paulrberg/dot-agents

Browse all from paulrberg/dot-agents

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 6
License LICENSE
Default branch main
Open issues 5
Status Active

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 2,048 B
  • docs SUMMARY.md 270 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 3 installs

SKILL.md

Grill Me

This skill is coordination-exempt: skip the ai-coord gate for its declared work.

Stress-test the plan one decision at a time until every material branch is resolved.

Workflow

  1. Extract the current objective, constraints, assumptions, and already-made decisions. Investigate any answer

discoverable from the codebase or supplied evidence instead of asking the user.

  1. Maintain a running decision record with: decision, chosen option, rationale, dependencies, and consequences. Update

it after every answer; do not reopen a recorded decision unless new evidence conflicts with it.

  1. Ask exactly one question at a time. Format the turn as ### 🔥 Decision <N> — <topic>, then Recommended, Why,

Tradeoff, and Question. Choose the highest-leverage unresolved branch whose answer constrains the most downstream decisions. After each answer, acknowledge ✅ Recorded: <choice> — <consequence> before the next card. Show settled and currently open counts when useful; never show a percentage because the decision tree can grow.

  1. Continue through scope, users, interfaces, data/state, failure modes, security, operations, migration, testing,

rollout, ownership, and stopping criteria only where they are material to this design.

  1. When no material open branches remain, return ### ✅ Decision record with a decision/choice/rationale/consequence

table, then ### ⚠️ Risks, accepted unknowns with owner/resolution point, rejected alternatives that matter, and ### 🏁 Completion criteria. Do not end with another question.

Completion requires every material branch to have a recorded decision or an explicitly accepted unknown with an owner and resolution point.