agentleFS
L-X-TL-X-T/ng-agentic-skills/.agents/skills/grill-with-style/SKILL.md

grill-with-style

Skill13 starsChanged 44 days agoMITView on GitHub

Grilling session that challenges your plan against the code's actual domain model and project style guide, and sharpens terminology. Use when the user wants to stress-test a plan against their project's language and style guide. For a plain design grilling without that lens use grill-me instead.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    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:

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

    line 16
  2. Distinctive:

    If a question can be answered by exploring the codebase, explore the codebase instead.

    line 18
  3. Distinctive:

    Do not quote or restate the full style guide.

    line 39
  4. Distinctive:

    When the user uses vague or overloaded terms, propose a precise canonical term.

    line 45
  5. Distinctive:

    When domain relationships are being discussed, stress-test them with specific scenarios.

    line 49
  6. Distinctive:

    When the user states how something works, check whether the code agrees.

    line 53

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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 with style

<what-to-do>

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.

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

If a question can be answered by exploring the codebase, explore the codebase instead.

</what-to-do><supporting-info>

Style guide awareness

Also look for a project style guide at style-guide/style-guide.md. If it exists, read it before asking implementation-facing questions. Load the specific guide files only when the plan touches that area:

  • TypeScript or Angular component/service design: style-guide/style-guide.ts.md
  • Angular templates, control flow, forms, or accessibility markup: style-guide/style-guide.html.md
  • SCSS, design tokens, selectors, or component styling: style-guide/style-guide.scss.md
  • NPM package choices or dependencies: style-guide/style-guide.npm.md
  • Markdown documentation edits: style-guide/style-guide.md.md
  • Git or commit planning: style-guide/style-guide.git.md
  • Accessibility requirements or ARIA behaviour: style-guide/style-guide.a11y.md
  • Unit or e2e test design: style-guide/style-guide.spec.md

When the user's plan conflicts with the style guide, call it out as a design constraint and ask for a decision. For example: "The style guide prefers signal inputs and the default OnPush change detection; does this plan require an exception, or should we reshape the component boundary?"

Do not quote or restate the full style guide. Use it to sharpen questions, identify constraints, and recommend project-consistent answers.

During the session

Sharpen fuzzy language

When the user uses vague or overloaded terms, propose a precise canonical term. "You're saying 'account' – do you mean the Customer or the User? Those are different things."

Discuss concrete scenarios

When domain relationships are being discussed, stress-test them with specific scenarios. Invent scenarios that probe edge cases and force the user to be precise about the boundaries between concepts.

Cross-reference with code

When the user states how something works, check whether the code agrees. If you find a contradiction, surface it: "Your code cancels entire Orders, but you just said partial cancellation is possible – which is right?"

</supporting-info>

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.