grill-me
Forces convergence on project decisions by challenging assumptions and dependencies one step at a time.
Install
mkdir -p .claude/skills/grill-me-slingr-stack && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15947" && unzip -o skill.zip -d .claude/skills/grill-me-slingr-stack && rm skill.zipInstalls to .claude/skills/grill-me-slingr-stack
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Stress-test a plan or design by interviewing the user one question at a time, walking the decision tree branch by branch, resolving dependencies, surfacing assumptions, and recommending answers. Use only when the user explicitly asks to be grilled, says "grill me", or asks to stress-test a design.Key capabilities
- →Interview the user one question at a time
- →Walk decision tree branches to resolve dependencies
- →Surface assumptions in a plan or design
- →Recommend answers for each question
- →Identify weak assumptions, edge cases, or tradeoffs
- →Converge on decisions rather than open-ended brainstorming
How it works
This skill stress-tests a plan by asking one question at a time, providing recommended answers, and resolving dependencies until no material ambiguity remains.
Inputs & outputs
When to use grill-me
- →Reviewing architectural proposals
- →Stress-testing implementation plans
- →Challenging design assumptions
About this skill
Grill Me
Pressure-test a plan until there is a shared understanding of the design, dependencies, tradeoffs, and remaining risks.
When to Use
- The user says "grill me"
- The user explicitly asks for a plan, architecture, proposal, or implementation strategy to be stress-tested
- The user wants weak assumptions, edge cases, or tradeoffs challenged directly
- The user wants convergence on decisions rather than open-ended brainstorming
Do not use this skill for routine design reviews unless the user clearly opts into an interrogation-style review.
Operating Rules
- Ask exactly one question at a time.
- For every question, provide a recommended answer using the built-in VS Code
#askQuestionstool. - If a question can be answered by inspecting the codebase, docs, tests, configuration, or existing behavior, inspect first and ask only if ambiguity remains.
- Resolve upstream decisions before downstream details. If a branch depends on another decision, settle the dependency first.
- State assumptions plainly when the user cannot or does not want to decide yet.
- Keep pushing until each material branch is decided, rejected, or explicitly deferred.
- Stay rigorous and direct without becoming hostile or theatrical.
Procedure
- Restate the plan being reviewed in one short paragraph.
- Identify the highest-leverage unresolved branches, such as goals, constraints, interfaces, data flow, failure modes, rollout, and testing.
- Pick the next blocking branch.
- If the branch can be resolved from repository context, inspect the repository and report the finding instead of asking.
- Otherwise ask one sharp question and include:
- the question
- the recommended answer
- why that answer is the default recommendation
- what downstream decision this unlocks
- Wait for the user's answer before asking the next question.
- After each answer, update the working model of the design and move to the next dependent branch.
- If a contradiction, risk, or hidden dependency appears, pause and resolve that blocker before continuing deeper.
- Continue until no material ambiguity remains.
Decision Branches To Walk
- Outcome: what problem is being solved, for whom, and how success is measured
- Scope: what is in scope, out of scope, and explicitly a non-goal
- Constraints: time, compatibility, performance, security, compliance, staffing, and migration limits
- Interfaces: APIs, UI contracts, schemas, events, commands, and integration boundaries
- Data: ownership, lifecycle, validation, storage, migrations, permissions, and observability
- Behavior: happy path, edge cases, failures, retries, concurrency, idempotency, and rollback
- Delivery: implementation sequence, rollout strategy, fallback plan, and testing approach
Completion Criteria
Stop only when:
- every major branch has been decided, rejected, or explicitly deferred
- the dependencies between decisions are clear
- each unresolved branch has a recommended default answer
- the remaining risks and assumptions are listed plainly
- there is a concise shared summary of the resulting plan
Final Output
End with:
- a short decision log
- the remaining assumptions and risks
- the next implementation or validation steps
When not to use it
- →For routine design reviews unless an interrogation-style review is explicitly requested
Limitations
- →It only asks one question at a time
- →It requires the user to explicitly ask to be grilled
- →It does not perform routine design reviews
How it compares
This skill uses an interrogation-style review to pressure-test a plan and converge on decisions, unlike open-ended brainstorming sessions.
Compared to similar skills
grill-me side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| grill-me (this skill) | 0 | 1mo | No flags | Intermediate |
| create-plan | 36 | 8mo | Review | Beginner |
| project-planner | 32 | 10mo | Review | Intermediate |
| system-design | 19 | 9mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
create-plan
antinomyhq
Generate detailed implementation plans for complex tasks. Creates comprehensive strategic plans in Markdown format with objectives, step-by-step implementation tasks using checkbox format, verification criteria, risk assessments, and alternative approaches. Use when users need thorough analysis and structured planning before implementation, when breaking down complex features into actionable steps, or when they explicitly ask for a plan, roadmap, or strategy. Strictly planning-focused with no code modifications.
project-planner
adrianpuiu
Comprehensive project planning and documentation generator for software projects. Creates structured requirements documents, system design documents, and task breakdown plans with implementation tracking. Use when starting a new project, defining specifications, creating technical designs, or breaking down complex systems into implementable tasks. Supports user story format, acceptance criteria, component design, API specifications, and hierarchical task decomposition with requirement traceability.
system-design
lagz0ne
Use when designing, architecting, or planning a new system from requirements or ideas - transforms concepts into navigable design catalog using EventStorming methodology, Mermaid diagrams, and progressive elaboration through 5 phases (Requirements, Big Picture, Processes, Data/Flows, Integration)
spec-kit-workflow
jmanhype
Guides specification-driven development workflow. Automatically invoked when discussing new features, specifications, technical planning, or implementation tasks. Ensures proper workflow phases (specify → clarify → plan → checklist → tasks → analyze → implement).
sparc-methodology
ruvnet
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration
spec-workflow
TencentCloudBase
Standard software engineering workflow for requirement analysis, technical design, and task planning. Use this skill when developing new features, complex architecture designs, multi-module integrations, or projects involving database/UI design.