agentleFS
Sign inStart free
pabloleonalcaidepabloleonalcaide/development-skills/skills/grilling/SKILL.md

grilling

Skill1 starsChanged 36 days agoMITView on GitHub

Grill the user relentlessly about a plan or design until shared understanding — interview one decision at a time, no code until confirmed. Use when the user wants to stress-test a plan or design before building, or uses any 'grill' trigger phrase.

193 other projects use a version of this, 38 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

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 71 edited versions we read keep these.

  • 4

    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:

    Open with your hypothesis: Before the first question, state in two lines what you think I want and how sure you are, so I can correct the …

    line 8
  2. Distinctive:

    Ask the questions one at a time, waiting for feedback on each question before continuing.

    line 15
  3. Distinctive:

    If a *fact* can be found in the codebase, look it up.

    line 17
  4. Distinctive:

    Do not enact the plan until I confirm we have reached a shared understanding.

    line 32

“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

Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.

Open with your hypothesis. Before the first question, state in two lines what you think I want and how sure you are, so I can correct the premise before we spend ten questions on it:

HYPOTHESIS: <what you think the outcome is, in one sentence>
CONFIDENCE: ~N% — missing: <the biggest unknowns>

Ask the questions one at a time, waiting for feedback on each question before continuing. Asking multiple questions at once is bewildering.

If a fact can be found in the codebase, look it up. The decisions are mine — put each one to me and wait.

Stop when you can predict me. The grilling is done when you could predict my answers to the next three questions you would ask. Until then, keep going; once there, stop — more questions are noise.

Close with a restate and let me correct it:

Outcome:      <what will exist when this is done>
User:         <who it is for>
Why now:      <the trigger>
Success:      <how we will know it worked — observable>
Constraint:   <the hard limits>
Out of scope: <what we deliberately won't do>

Do not enact the plan until I confirm we have reached a shared understanding.

Common Rationalizations

RationalizationReality
"I'll ask all the questions at once to save time"Batched questions get shallow answers and hide dependencies between decisions.
"I can decide this one myself"If it is a decision, not a fact in the code, it's mine. Recommend, then ask.
"We've covered enough"If you can't predict my next three answers, we haven't.

Red Flags

  • A question whose answer was findable in the code.
  • A question without a recommended answer.
  • Code or files written before I confirmed the restate.
  • The restate has no "Out of scope" line.

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