agentleFS
Sign inStart free
agoopintsaiagoopintsai/shipright/skills/grilling/SKILL.md

grilling

Skill2 starsChanged 16 days agoApache-2.0View on GitHub

Round-based questioning engine. Turns a plan, decision or idea into a decision tree and questions you round by round until you and Claude share the same understanding. Use to stress-test your own thinking ("grill me", "question this plan"). Conversation only, no question banks, no documents. For banks, the red-zone gate and a consensus document use /shipright:grill.

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

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

  • 0

    Common

    Most of the 70 edited versions we read keep these.

  • 2

    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:

    Treat the user's statement as a hypothesis.

    line 13
  2. Distinctive:

    Re-root rule: if questioning shows the real problem differs from the stated topic, replace the root with the restated problem and redo the …

    line 15

“Common” is measured: kept by at least 6 in 10 of the 70 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

grilling: a round-based questioning engine

What will happen: Claude lays your topic out as a tree of decisions, then asks you questions in rounds. Each round holds every question that can be asked right now. You answer; your answers unlock the next round. It ends when no open question is left and you confirm "we understand each other". Nothing is written to disk.

The topic is the root of the tree, not a given

Treat the user's statement as a hypothesis. The real problem may be a symptom, or the mirror image of a preselected solution. Make "what problem are we actually solving?" the root node.

Re-root rule: if questioning shows the real problem differs from the stated topic, replace the root with the restated problem and redo the affected subtrees.

Rounds and the frontier

The frontier is every question whose prerequisite decisions are settled, so it can be asked now without guessing. Each round, ask the whole frontier at once. Number the questions and give a suggested answer for each, then stop and wait.

Q1 <title>: <question text, options if useful>
Suggested answer: <your answer plus one-sentence reason>

Answers reshape the tree. Recompute the frontier and ask the next round. A question that depends on another question in the same round belongs to the next round.

Facts versus decisions

Looking up facts is Claude's job, never the user's. If a question needs facts from the codebase, files or documents, look them up (a read-only subagent is fine) rather than asking the user. Do not stall on it: a fact still being checked counts as an unsettled prerequisite, so only questions that depend on it wait. Decisions always belong to the user: put each one to them and wait; never answer your own question.

Finishing

The session ends when the frontier is empty: every branch walked, nothing silently assumed. Do not act on the result until the user confirms they share the understanding.

Relation to /shipright:grill

/shipright:grill is a separate skill with question banks, a hard gate for red-zone work and a consensus document. It deliberately asks one question at a time and lets Claude answer the low-risk nodes, because there the plan's author is Claude. Here the author is the user, so "Claude answers for you" does not apply. If you change tree mechanics (building the tree, frontier, re-rooting, facts versus decisions) in one skill, review the other.

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