agent planning skill risk: low
Relentless Design Plan Interviewer
Interview the user relentlessly about every aspect of their plan, walking down each branch of the design tree one question at a time while providing a recommended answer for each a…
SKILL 1 file
SKILL.md
--- name: grill-me description: "Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions \"grill me\"." --- 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. For each question, provide your recommended answer. Ask the questions one at a time. If a question can be answered by exploring the codebase, explore the codebase instead.
REQUIRED CONTEXT
- the plan or design to be interviewed about
ROLES & RULES
- 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.
- For each question, provide your recommended answer.
- Ask the questions one at a time.
- If a question can be answered by exploring the codebase, explore the codebase instead.
EXPECTED OUTPUT
- Format
- chat_message
- Constraints
- ask questions one at a time
- provide recommended answer for each question
- explore codebase instead of asking if possible
SUCCESS CRITERIA
- Reach shared understanding
- Resolve each branch of the decision tree one-by-one
- Provide recommended answer for each question
- Ask questions one at a time
- Explore codebase instead of asking when possible
CAVEATS
- Dependencies
- Requires the plan
- Requires codebase access
- Missing context
- The plan or design content to analyze
- Whether a codebase is available and how it should be accessed
- Ambiguities
- The prompt refers to 'this plan' without specifying how or where the plan input is provided.
QUALITY
- OVERALL
- 0.70
- CLARITY
- 0.80
- SPECIFICITY
- 0.75
- REUSABILITY
- 0.70
- COMPLETENESS
- 0.60
IMPROVEMENT SUGGESTIONS
- Add an explicit input placeholder such as {{plan}} after the instruction text.
- Clarify what 'explore the codebase' means by specifying tools or access method.
USAGE
Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.
MORE FOR AGENT
- Consciousness Council Multi-Perspective Deliberationagentplanning
- Multi-Agent Architecture Patterns Guideagentplanning
- TDD Implementation Plan Writeragentplanning
- A/B Test Design and Analysis Guideagentplanning
- Autonomous EDA Design Space Exploreragentplanning
- Autonomous Design Space Exploration Loopagentplanning
- Website Architecture Planning Expertagentplanning
- BDI RDF Mental State Modeleragentplanning
- Collaborative Software Design Brainstorming Processagentplanning
- WWA Product Backlog Item Creatoragentplanning
- Structured Development Plan Outlineragentplanning
- ML Ablation Study Planneragentplanning
- Ansoff Matrix Growth Strategy Analyzeragentplanning
- Team OKR Brainstorming Product Leaderagentplanning
- Context Engineering Fundamentalsagentplanning
- Product Monetization Strategy Developeragentplanning
- LLM Project Pipeline Development Methodologyagentplanning
- What-If Scenario Analysis Oracleagentplanning
- Business Model Canvas Generatoragentplanning
- Implementation Plan Execution Workflowagentplanning
- Concise Coding Task Planneragentplanning
- Domain Model Plan Grilling Intervieweragentplanning
- Latent Briefing KV Cache Compactionagentplanning
- Product Roadmap Outcome Transformeragentplanning
- Puzzle Activity Planner with Generator Linksagentplanning