Skip to content
Design Systems

Create DESIGN.md

ibelick

Document the governing design language from actual product code and evidence.

SKILL.md

---
name: knoveya-create-design-md
description: "Document the governing design language from actual product code and evidence. Use for matching design systems work."
---

# Create DESIGN.md

## Scope

Apply this guidance when the requested task matches the description. Honor the user's chosen outcome, repository rules, and existing authorization.

## Workflow

Document the governing design language from actual product code and evidence.

Before acting, inspect the relevant artifact and ask only for information that materially changes the result. Use existing tools and conventions; do not install dependencies, publish, send messages, deploy, or mutate external data unless the user has authorized that operation.

## Acceptance check

Observed tokens and proposed changes remain clearly separated.

## Example task

Record existing theme roles without silently redesigning the palette.

## Report

State what changed, the evidence checked, and what remains unverified. Do not claim a successful operation or completed test without observing it.

How to use

Copy the full block, including its frontmatter, into a new folder named knoveya-create-design-md as SKILL.md. Review the instructions before enabling them. For Codex, a user skill normally lives in ~/.codex/skills/knoveya-create-design-md/SKILL.md; check the current documentation for another agent's supported location. Do not overwrite an existing skill.

This is an independent Knoveya skill. No files are installed by this website.

Example

Record existing theme roles without silently redesigning the palette.

Verify

Observed tokens and proposed changes remain clearly separated.

Test the skill on a small, authorized example. File validation alone does not prove that an agent will make good decisions.

Limits

The skill supplies instructions, not tool access or expertise guarantees. Inspect generated work and preserve the user's approval boundaries.