Grill me
PRB's collection of agent skillsFrom the repository description
npx -y skills add PaulRBerg/agent-skills --skill grill-meAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
1.9 KB, 347 tokens by cl100k_base, as published. Nobody here has run it
Grill Me
Stress-test the plan one decision at a time until every material branch is resolved.
Workflow
- 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.
- 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.
- Ask exactly one question at a time. Format the turn as
### 🔥 Decision <N> — <topic>, thenRecommended,Why,Tradeoff, andQuestion. 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. - 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.
- When no material open branches remain, return
### ✅ Decision recordwith 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.
What ships with it: 1 file
42 B alongside SKILL.md
agents/
- openai.yaml42 B