agentleFS
Sign inStart free
SnoozleStudioSnoozleStudio/opencode-wp-settings/skills/grill-me/SKILL.md

grill-me

Skill4 starsChanged 3 days agoMITView on GitHub

Alignment session — interview the user relentlessly about a plan, feature, or idea until every branch of the decision tree is resolved. Use before starting ambiguous work ("I want a booking form", "add a careers section", "make the site faster"). Prevents building the wrong thing.

193 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use brief-to-tasks, writing-beats 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.
  • julianoczkowskiSkill

    brief-to-tasks

    Break a design brief into an ordered checklist of independently buildable tasks using vertical slices. Saves as a markdown checklist. Use when user wants to break down work, create tasks from a brief, plan implementation order, or mentions "tasks" or "breakdown".

    Also in 7 projects that use this

  • LesaniSkill

    writing-beats

    Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.

    Also in 66 projects that use this

  • simo97Skill

    request-refactor-plan

    Use this skill when user wants to create a refactor plan.

    Also in 43 projects that use this

  • simo97Skill

    migrate-to-shoehorn

    Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.

    Also in 71 projects that use this

  • LesaniSkill

    writing-shape

    Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.

    Also in 65 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

  • +2 more from simo97

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 177 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:

    When the grilling is done, state the aligned summary (goal, scope, non-goals, verification) and begin

    line 28
  2. Distinctive:

    Never start implementation on an ambiguous ask — grilling is mandatory for features/sections.

    line 33
  3. Distinctive:

    Never grill for grilling's sake — questions must be decision-relevant

    line 35
  4. Distinctive:

    If the user wants speed over completeness, honor that — grilling scales down to 2-3 questions for a one-file change

    line 37

“Common” is measured: kept by at least 6 in 10 of the 177 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-Me — Alignment Before Work

The most common failure mode in AI-assisted development is misalignment: you think the agent understood, then it built the wrong thing. The fix is a grilling session — detailed questions BEFORE code.

How to run

  1. State your understanding of the request in one sentence. If the user refines it, adopt their language
  2. Interview until every branch is resolved. Ask one question at a time, concrete, in the user's domain language. Branches to cover for WordPress work:
    • Scope: what page/template/section exactly? Is it ACF-driven (which fields) or hardcoded? Both?
    • Data: where does content come from (post types, options pages, repeaters)?
    • Behavior: interactions (accordion, hover, scroll-triggered?), required on mobile/reduced-motion?
    • Design constraints: house patterns (grid, tokens), existing components to match
    • Edge cases: empty states, no-JS, slow devices, logged-out vs logged-in
    • Non-goals: what is explicitly out of scope?
  3. Question limits: stop when answers are predictable or the user says "you decide" — respect the user's time; ~6-12 questions is typical for a section, fewer for a bug
  4. When the grilling is done, state the aligned summary (goal, scope, non-goals, verification) and begin

Rules

  • Never start implementation on an ambiguous ask — grilling is mandatory for features/sections; skip it only for bug reports (fix immediately) and trivial asks
  • Never grill for grilling's sake — questions must be decision-relevant
  • Record the aligned summary in the session so implementation doesn't drift
  • If the user wants speed over completeness, honor that — grilling scales down to 2-3 questions for a one-file change

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