agentleFS
elxecutorelxecutor/skills/grilling/SKILL.md

grilling

Skill3 starsChanged yesterdayMITView on GitHub

Stress-test a plan, decision, or idea through structured rounds of dependency-aware questions until its assumptions and trade-offs are explicit. Use when the user asks to be grilled, challenged, or helped to think through a choice.

194 other projects use a version of this, 123 of them edited.

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

3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 72 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Use the fields of the question tool for their intended roles.

    line 12
  2. Very specific:

    Put the recommended option first and label it … (Recommended).

    line 17
  3. Very specific:

    Use plain text in all tool fields.

    line 18

“Common” is measured: kept by at least 6 in 10 of the 72 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

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 using the ask tool (the question tool in this environment): include every frontier question in a single tool call and wait for the user's answers before the next round. Do not ask these questions only as plain chat text.

Question-tool presentation

Use the fields of the question tool for their intended roles. The tool is already an interactive form; do not simulate one with Markdown, emoji, arrows, option lists, or a "Submit" question inside the prompt.

  • header: a short, scannable title (30 characters or fewer), such as Primary outcome.
  • question: a direct, self-contained decision question. Start with its round number in plain text, for example Q1. What is the most important problem to solve at launch? Add only the context needed to make the choice; use short plain-text paragraphs if needed.
  • options: provide mutually distinct decisions. Keep each label short and action-oriented; put the implication or rationale in description.
  • Put the recommended option first and label it … (Recommended). State why it is recommended in that option's description, rather than as a separate pseudo-option or a line in the prompt.
  • Use plain text in all tool fields. Avoid Markdown syntax (**, headings, lists), decorative symbols, and repeating the question in an option.
  • Include an Other option only when a genuinely open-ended answer is useful. Do not add a separate confirm/submit question: the tool handles submission.

Example shape:

header: "Primary outcome"
question: "Q1. What is the most important problem to solve at launch?"
options:
  - label: "Trusted campus trading (Recommended)"
    description: "Focuses the MVP on fast, safer exchanges among verified community members."
  - label: "Broad marketplace"
    description: "Launch with many categories and audiences from day one."
  - label: "Student income"
    description: "Prioritize services and tools that help students earn money."

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 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.

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.

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.