mcpField
G
grilling

grilling

github.com/anorthProductivity110 installsUpdated today
Repository

About grilling

grilling is a skill for clarifying project requirements through structured, iterative interviews. It maps decisions into a dependency tree, asks all currently answerable questions in rounds, and challenges unclear or conflicting scope.

Key features

  1. 01Dependency-based decision tree
  2. 02Questions grouped by round
  3. 03Recommended answers with trade-offs
  4. 04Challenges scope and contradictions
  5. 05Explores facts without asking the user

Use cases

  1. 01Clarifying requirements before implementation
  2. 02Unblocking dependent design decisions
  3. 03Surfacing unnecessary or conflicting requirements

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/anorth/agent-skills --skill grilling

After installing, type/grillingin Claude Code to confirm it loaded.

Details

From the project README

Interview the user relentlessly until you reach a shared understanding. Map this as a design tree: every decision branches into the decisions that hang off it.

Work the tree in rounds. The frontier is every decision whose prerequisites are already settled: the questions you can ask now without guessing at answers you haven't heard yet. Ask the whole frontier in one round: number each question and give your recommended answer. Then wait for the user's answers before the next round.

Format a round like so:

❓ **Q1** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>

➡️ <your recommended answer>

---

❓ **Q2** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>

➡️ <your recommended answer>

Word each question so "yes" accepts your recommended answer. In each question body, say why the decision matters, and give the trade-offs of each choice.

Challenge as you go: requirements that look unnecessary or overcomplicated, implied scope, and contradictions with earlier answers or with the code.

Each round the user answers reshapes the tree: settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. A question whose answer depends on another question still open in this round belongs to a later round, not this one.

Finding facts is your job, never the user's. When a frontier question needs a fact from the environment (filesystem, tools, etc.), dispatch a sub-agent with a fresh context window to find it; don't ask the user for anything you could look up yourself. Don't block on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait for the sub-agent to report; ask the rest of the frontier now. The decisions are the user's: put each to them and wait.

Terms and lasting decisions

When a term is fuzzy, overloaded, or conflicts with the project's glossary, or a decision is hard to reverse and would surprise a future reader, use the /domain-modeling skill. Everything else stays in the conversation.

Finishing

The session is done when the frontier is empty: every branch of the design tree visited, nothing left silently assumed. Do not act on it until the user confirms you have reached a shared understanding.

Comments

Markdown supported