karlorz/agent-skills/grilling
- community
Checking that the SKILL.md file is still in the repository.
Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
Install
npx vskill@latest install karlorz/agent-skills/grillingSKILL.md
Grilling
Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Map the work as a design tree: every decision branches into the decisions that depend on it.
The frontier is the set of decisions whose prerequisites are already settled: the questions that can be asked now without guessing at answers that have not been heard yet. Work through the frontier one question at a time. For each question, provide your recommended answer and wait for feedback. Recompute the frontier after every answer. Do not ask the whole frontier in one round.
Finding facts is the agent's job, not the user's. If a question needs a fact from the filesystem, codebase, tools, or other environment, explore it before asking the user.
In an attended main session, subagents may research only factual or environment prerequisites. They must not choose design decisions, run the interview, ask user questions, or act on the user's behalf. Treat an in-flight fact lookup as an unsettled prerequisite: independent frontier questions may proceed, but dependent questions wait for the result.
Ask Style
The interview and all design decisions remain in the attended main session. Only the factual or environment research described above may be delegated.
Ask open-ended grilling questions conversationally.
For concrete decision points with 2-4 choices, use whichever structured question tool exists in the current surface:
- Claude Code:
AskUserQuestion - Codex CLI/App:
ask_user_question - Antigravity CLI:
ask_question
If no structured question tool exists, ask conversationally with numbered options. Do not add an explicit "Other" option for Antigravity; its UI already supplies one.
The session is done when the frontier is empty: every branch has been visited and nothing remains silently assumed. Do not act on the plan until the user confirms shared understanding.
Under /goal, codex exec, scheduled runs, or other unattended contexts, skip the interview and state that grilling requires an attended main session.
Security
- Security scanPassed, 95 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/skills/grilling/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/karlorz/agent-skills/grilling)