Skip to main content
skill CX Codex

build-my-designer-brain — Claude Code skill: features and setup

The build-my-designer-brain Claude Code skill builds a designer’s personal collection of methods, preferences, and lessons. It runs to create or revise that collection, or to apply it while working on a feature.

MIT ★ 107 updated 2026-11-08

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add thedesignproject/agent-skills --skill build-my-designer-brain -a claude-code
Open on GitHub

What build-my-designer-brain does

The skill helps create a designer’s personal Markdown knowledge base, continue its setup, or draw on it while working on a feature. The material can cover critique methods, preferences for collaborating with AI, visual references, and lessons. For setup, the skill interviews the designer two unanswered questions at a time, then presents a draft for correction.

Changes to an existing brain follow its chosen update policy. Until one is selected, the agent suggests durable edits instead of saving them; a temporary exception does not replace a standing preference. Personal methods do not override company requirements, and restricted company material stays out of the personal brain.

Files are written only with authorization and file access. Without access, the agent can return Markdown for the user to save. The skill does not watch the brain in the background; updates need active instructions and access to its files.

What it helps with

  • create a personal record of design preferences
  • resume an interview from unanswered questions
  • save a correction or lesson to the brain
  • apply personal methods to a feature decision

Example prompts for the agent

  • Create my personal design brain and start the interview.
  • Resume setting up my brain with questions I have not answered yet.
  • Save this correction as a lesson in my design brain.

How to install build-my-designer-brain

1Skills CLI (Vercel)

npx skills add thedesignproject/agent-skills --skill build-my-designer-brain -a claude-code

2Manually: put the files in place

~/.claude/skills/build-my-designer-brain/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/build-my-designer-brain/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about build-my-designer-brain

How do I install build-my-designer-brain in Claude Code?

Run npx skills add thedesignproject/agent-skills --skill build-my-designer-brain -a claude-code. The skill file is at ~/.claude/skills/build-my-designer-brain/SKILL.md.

What does build-my-designer-brain do?

It helps create and maintain a personal Markdown brain for design methods, AI collaboration preferences, and lessons, then use that material while working on a feature.

Does build-my-designer-brain update the brain automatically?

No. It is not a background watcher: updates require active instructions and access to the brain. Until an update policy is chosen, the agent suggests durable changes rather than saving them.

Source text

SKILL.md · MIT
---
name: build-my-designer-brain
description: Use when a designer wants to create, resume, use, or evolve a personal design brain containing critique methods, AI collaboration preferences, optional references and visual taste, and reusable lessons. Also use for corrections explicitly intended to update that brain. Not for building a company knowledge base or ordinary design work without a personal-brain connection.
---

# Build My Designer Brain

Create portable, user-owned Markdown knowledge. The skill supplies the process; the person's brain is a separate output, never written into this installed skill.

## Choose the activity

| Request | Read next | Result |
| --- | --- | --- |
| Create, interview, or resume setup | [Interview](references/interview.md) | Personalized draft, then saved brain |
| Remember a correction, evolve, or review learning | [Updates](references/updates.md) | Scoped changes under the chosen policy |
| Use an existing brain in a feature | Read that brain's README and relevant files | Apply personal methods alongside company context |

For output structure, read [Brain format](references/brain-format.md). Consult [Sources](references/sources.md) for attribution or framework explanations; the interview works offline.

## Start from what is known

Use the brain location supplied by the user or established in this session. Otherwise inspect the current workspace's README and likely personal-brain folders narrowly. Do not search unrelated personal directories. Read an existing brain before changing it. Preserve prior answers and resume at unanswered questions.

For a new brain without a specified location, use `my-designer-brain/` under the current workspace and state the location. Explain that a separate personal repo can hold the same files later. Do not initialize Git, change global instructions, install integrations, or publish anything unless requested.

## Interview behavior

Order: critique methods → working with AI → optional references and taste → lessons and evolution. Ask two unanswered questions per round, then wait. All choice questions accept a written answer. Ranking accepts an ordered text response; do not convert it to single selection. Explain examples without treating them as the person's beliefs.

Use a host's question UI only if it preserves the question's answer type, write-in, and skip behavior. Otherwise ask in chat. Do not require a screenshot, company project, named framework, Mobbin access, or a particular app.

Skip already answered questions. Honor explicit requests to skip, shorten, or use proposed defaults; label defaults unconfirmed and leave unprovided rankings unset. Show a concise draft for correction before treating it as confirmed. Explicit instructions to save a draft authorize a draft save. Save partial progress when requested, with unanswered items visible.

## Scope and persistence

Personal methods and taste do not silently override company requirements. Feature-specific decisions remain local. Do not copy restricted company material into the personal brain.

During use, follow the existing evolution policy. Until selected, suggest durable updates rather than silently writing them. A temporary exception never replaces a standing preference. Ambiguous frustration does not establish a new rule.

Write files when authorized and supported. Without file access, return downloadable files if possible, otherwise labeled Markdown for the user to save. Never claim an unsaved change persisted. A skill is not a background watcher: updates require active instructions and access to the brain. Verify written files and report exact paths and changes.

© thedesignproject · MIT · thedesignproject/agent-skills

Similar skills

All skills for Design →

From the same set13

The whole set →
performance-review-self-assessment The performance-review-self-assessment Claude Code skill guides employees through a quarterly self-assessment. It covers accomplishments, challenges, leadership principles, and progress on development goals. CX Codex +1 ★ 107repo stars performance-review-manager The performance-review-manager Claude Code skill guides a manager through a quarterly employee review. It gathers peer feedback and helps assess performance, potential, and development. CX Codex +1 ★ 107repo stars performance-review-360-peer The performance-review-360-peer Claude Code skill guides a colleague through peer feedback using Nonviolent Communication. It asks about strengths, growth areas, leadership principles, and future collaboration. CX Codex +1 ★ 107repo stars create-skill This Claude Code skill helps create Cursor skills and explains the structure of SKILL.md. It applies to requests for a new skill or questions about its instruction file. CX Codex +1 ★ 107repo stars create-prd create-prd is a Claude Code skill that turns a feature request or transcript into a PRD. It examines the codebase and can create a Linear project with issues. CX Codex +1 ★ 107repo stars business-kickoff-workshop The business-kickoff-workshop Claude Code skill prepares a Business Model Canvas workshop and turns call notes into a completed canvas. It activates for kickoff planning, customer discovery questions, or post-call canvas work. CX Codex +1 ★ 107repo stars ai-component-metadata The ai-component-metadata Claude Code skill creates structured metadata for design system components used in AI-generated interfaces. It runs during component analysis and records how each component should be composed and used. CX Codex +1 ★ 107repo stars agentic-design-systems The agentic-design-systems Claude Code skill guides the design and review of component libraries built for AI agents. It activates for AI-readable design systems, component metadata work, and library audits. CX Codex +1 ★ 107repo stars

Project sponsors

Companies that keep this analytics open