agentleFS
Sign inStart free
daichi-0818daichi-0818/claude-code-ops-kit/skills/grilling/SKILL.md

grilling

Skill0 starsChanged 49 days agoMITView on GitHub

Pre-build requirements grill (an exhaustive interview). Before writing any plan, design, or deliverable, interrogate one question at a time until you and the requester share a common understanding. Triggers on "grill me", "nail down the requirements", "pin this down before building", "check before starting". Also auto-fires when a sizable implementation, document, or automation request arrives with fuzzy requirements.

193 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use capture-learning-tools, design-frontend-dev and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • The-Vibe-CompanySkill

    capture-learning-tools

    Turn technical conversations, bugs, CI failures, review comments,

    Also in 5 projects that use this

  • The-Vibe-CompanySkill

    design-frontend-dev

    Clean Impeccable frontend design skill. Use when the user wants to

    Also in 5 projects that use this

  • RoentekSkill

    loop-me

    Grill me about specs for the workflows I want to build, within this workspace.

    Also in 58 projects that use this

  • liufeng1976Skill

    setup-ts-deep-modules

    Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

    Also in 42 projects that use this

  • FabienDehopreSkill

    decision-mapping

    Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.

    Also in 8 projects that use this

  • AWSSkill

    wizard

    Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.

    Also in 136 projects that use this

  • +3 more from The-Vibe-Company

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 71 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before you start building, interview the requester about every side of the plan until you reach shared understanding.

    line 7

“Common” is measured: kept by at least 6 in 10 of the 71 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Pre-Build Grill (Exhaustive Requirements Interview)

Before you start building, interview the requester about every side of the plan until you reach shared understanding. Walk down each branch of the design tree one at a time, resolving the dependencies between decisions one by one.

Rules

  1. One question at a time. Batching several questions confuses the requester. Wait for the answer before the next one.
  2. Attach your own recommended answer to each question ("my recommendation is A, because ..."). Never dump a blank slate on the requester.
  3. Anything you can answer from the codebase, memory, or real data, answer yourself — do not ask. Only ask the human about things that genuinely need their judgment.
  4. Before the first question, verify the current state: is this request actually still unsolved? Spend one minute confirming via git log, memory, and real data. (A real failure mode: re-dispatching an already-solved task off a stale note.)
  5. Exit condition: once inputs, processing, outputs, human decision points, and out-of-scope items (what you will NOT do) are all articulated, read back the agreed requirements as a bullet list before you start.

Why this works

Rework from "discovered a requirements mismatch after building" always costs more than the five questions up front. This is the entry-side gate, paired with the self-audit skill (the exit-side guess check).

<!-- Derived from the grilling skill in mattpocock/skills (MIT, Copyright (c) 2026 Matt Pocock), condensed and adjusted. See THIRD_PARTY_NOTICES.md. -->

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free