agentleFS
tejastn10tejastn10/workbench/skills/planning/grill/SKILL.md

grill

Skill1 starsChanged 2 months agoMITView on GitHub

A relentless interview that sharpens a plan, design, or decision before any code is written — map the open decisions as a tree, ask the whole frontier one round at a time with a recommended answer for each, look up facts yourself, stop only when nothing is left silently assumed. Use when the user says "grill me", wants to stress-test their thinking, or is about to start something under-specified.

87 other projects use a version of this, 7 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use root-cause, prove-it and 9 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.
  • Ingramradical235Skill

    root-cause

    Structured root cause analysis using WHERE (MECE decomposition) then WHY (causal structure diagrams) pipeline. Includes coin-flip detection, logical-leap detection, and vicious cycle intervention. Use when buffer enters YELLOW/RED, when metrics stall, or when Actions execute but don't produce results.

    Also in 4 projects that use this

  • Neko-Catpital-LabsSkill

    prove-it

    Shared evidence rule for investigating, diagnosing, debugging, proving, or explaining what happened or why for any problem or situation: do not assert something is fixed, working, passing, merged, or running unless you personally observed it this turn and can show what you saw; do not assert it was caused by X until a repro and controlled isolation prove that cause.

    Also in 4 projects that use this

  • sahinSkill

    execute

    Also in 5 projects that use this

  • assisjpSkill

    file-pr

    Prepare and open or update an authorized pull request with a concise problem-first description and verifiable evidence. Use when the user asks to create, file, open, or update a PR. Do not use merely to review a diff or when publication is not authorized.

    Also in 3 projects that use this

  • Arman-KudaibergenovSkill

    write-plan

    Этот скилл MUST быть вызван когда есть design.md и нужно разбить доработку на атомарные задачи (2-5 мин) с точными путями файлов и критериями проверки в tasks.md. SHOULD также вызывать как промежуточный шаг между brainstorm и subagent-dev. Do NOT использовать для обсуждения идеи — используй brainstorm; для выполнения задач — используй subagent-dev.

    Also in 3 projects that use this

  • JkudjoSkill

    incident

    Production incident response — structured triage, hypothesis tree, safe remediation, incident record

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 69 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run this before planning/phased-delivery, before planning/write-prd, before implementing anything non-trivial.

    line 12
  2. Distinctive:

    Ask the whole frontier in one round.

    line 25
  3. Distinctive:

    Wait for the user's answers before the next round.

    line 27
  4. Very specific:

    Facts are your job, never the user's: If a frontier question needs a fact from the repo, the filesystem, gh, or docs — go find it (dispatch …

    line 50
  5. Distinctive:

    Decisions are the user's: Put each one to them and wait.

    line 54
  6. Distinctive:

    One round at a time: Don't run ahead and answer round three's questions in round one.

    line 55
  7. Distinctive:

    Done = empty frontier: Every branch visited, nothing silently assumed.

    line 57

“Common” is measured: kept by at least 6 in 10 of the 69 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

Grill

Adapted from mattpocock/skills grill-me / grilling (MIT). The point: the most common failure is the agent starting to build before it understands the problem. This closes that gap first.

Run this before planning/phased-delivery, before planning/write-prd, before implementing anything non-trivial.

How it works

Interview the user until you reach a shared understanding. Model the open questions as a decision 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.
  • Ask the whole frontier in one round. Number each question, give a short title, and state your recommended answer.
  • Wait for the user's answers before the next round.

Format:

❓ **Q1 — <title>**: <question, with options if there are any>

➡️ <your recommended answer, and why in one line>

---

❓ **Q2 — <title>**: <question>

➡️ <your recommended answer>

Each round's answers reshape the tree: settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier, ask the next round. A question whose answer depends on another still-open question belongs to a later round.

Rules

  • Facts are your job, never the user's. If a frontier question needs a fact from the repo, the filesystem, gh, or docs — go find it (dispatch a sub-agent if it's a big search). Don't block the whole round on it: only the questions downstream of that fact wait; ask the rest now.
  • Decisions are the user's. Put each one to them and wait.
  • One round at a time. Don't run ahead and answer round three's questions in round one.
  • Done = empty frontier. Every branch visited, nothing silently assumed. Do not start work until the user confirms the understanding is shared.

After grilling

Hand off to the right next step:

  • Multi-session build → planning/phased-delivery.
  • Needs a written spec → planning/write-prd.
  • A decision worth recording → planning/write-adr.
  • Want the interview to also draft CONTEXT.md + ADRs as it goes → use Matt's grill-with-docs (install via the plugin, see .agents/external-skills.md).

Anti-patterns

  • ❌ Asking one question at a time when five are on the frontier.
  • ❌ Asking the user something you could look up.
  • ❌ Skipping the recommended answer — it's what makes the round fast to work.
  • ❌ Starting to build while questions are still open.

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.