Stacks Documentation
SkillsChangelog
TeamSponsorsPartnersPostcardwareAwesome StacksContributing

Design: full output

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-design-output · Design · model-invoked

An enforcement layer for when an agent keeps truncating. It bans placeholder comments and elisions so you get whole, runnable stx files rather than skeletons with "rest of the component here" in them.

When to reach for it

  • Banning placeholder comments and truncation so you ship whole
  • Runnable stx files instead of skeletons

Inside the skill

The sections an agent reads once the skill loads.

  • Baseline
  • Banned Output Patterns
  • Execution Process
  • Handling Long Outputs
  • Quick Check

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-design-output

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