Stacks Documentation
SkillsChangelog
TeamSponsorsPartnersPostcardwareAwesome StacksContributing

Grilling

Copy page
Copy page as Markdown for LLMs
View as Markdown
View this page as plain text
Open in ChatGPT
Copy content and open ChatGPT
Open in Claude
Copy content and open Claude
Open in Perplexity
Search with Perplexity AI
On this page 4

stacks-grilling · Engineering craft · model-invoked

A relentless interview that stress-tests a plan before any code exists. It works the decision tree in rounds: ask every question whose prerequisites are settled, recommend an answer to each, then wait. Finding facts is the agent's job and the decisions are yours, and the session ends when nothing is left silently assumed.

Inside the skill

The sections an agent reads once the skill loads.

  • Rounds and the frontier
  • Facts are your job, decisions are the user's
  • Done
  • Do not build

Using it

This one is model-invoked. Your agent reaches for it on its own when the task matches, and you can also call it by name:

/stacks-grilling

Source: stacks-grilling/SKILL.md. Shadow it for one project with app/Skills/stacks-grilling/SKILL.md, then re-run buddy setup:ai. See Writing your own.

Native source verification

The skill has been checked against current source and retained tests. Read its entrypoint and linked references for the actual contract; summaries here are discovery pointers. Native capabilities maps every core package and records driver evidence without claiming universal parity.