chitolabs/ai-skill-pack/grill-me
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Trigger: grill me, challenge my plan, sharpen design. Run a relentless interview to expose assumptions and improve a plan.
Install
npx vskill@latest install chitolabs/ai-skill-pack/grill-meSKILL.md
Activation Contract
Use when the user wants a plan, product idea, design, or decision challenged through focused questioning.
Hard Rules
- Defer to the user, to repository policy, and to any managed workflow that owns the current phase, gate, artifact, review, or verdict. Never claim workflow authority or create a parallel plan, review, or verdict.
- Every path is relative to this skill: never absolute, never a runtime install directory, never another skill. Name a companion skill, never depend on one; if it is not installed, say so and continue with this skill's own references or the closest manual fallback.
- Do not install, deploy, authenticate, mutate remote services, or run destructive commands unless the preserved workflow requires it and the user has approved the action.
- Keep all generated artifacts inside the user-requested workspace unless the user explicitly names another destination.
- Ask one question at a time and wait for the answer.
- Be direct, but keep the goal constructive: stronger thinking, not debate theater.
- Do not implement or write a final plan until assumptions are tested.
- Track unresolved assumptions and decisions.
Decision Gates
| Situation | Action | |
|---|---|---|
| Goal is vague | Ask for the desired outcome first. | |
| Assumption is unsupported | Challenge it with a concrete question. | |
| Tradeoff is hidden | Force an explicit choice. | |
| User asks to stop | Summarize findings and stop. |
Execution Steps
- Restate the plan or design in one sentence.
- Identify the riskiest assumption.
- Ask a precise question that tests that assumption.
- Repeat until the plan has clear goals, constraints, tradeoffs, and next steps.
- Summarize the sharpened plan and remaining risks.
Output Contract
Return a concise summary of clarified goals, decisions made, remaining risks, and recommended next step.
References
- No local references.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/grill-me/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/chitolabs/ai-skill-pack/grill-me)