playbooks

home / skills / pbakaus / impeccable / teach-impeccable

teach-impeccable skill

/source/skills/teach-impeccable

This skill gathers project design context and persists it in your AI config to enforce consistent design guidelines across sessions.

npx playbooks add skill pbakaus/impeccable --skill teach-impeccable

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
2.7 KB
---
name: teach-impeccable
description: One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.
user-invokable: true
---

Gather design context for this project, then persist it for all future sessions.

## Step 1: Explore the Codebase

Before asking questions, thoroughly scan the project to discover what you can:

- **README and docs**: Project purpose, target audience, any stated goals
- **Package.json / config files**: Tech stack, dependencies, existing design libraries
- **Existing components**: Current design patterns, spacing, typography in use
- **Brand assets**: Logos, favicons, color values already defined
- **Design tokens / CSS variables**: Existing color palettes, font stacks, spacing scales
- **Any style guides or brand documentation**

Note what you've learned and what remains unclear.

## Step 2: Ask UX-Focused Questions

{{ask_instruction}} Focus only on what you couldn't infer from the codebase:

### Users & Purpose
- Who uses this? What's their context when using it?
- What job are they trying to get done?
- What emotions should the interface evoke? (confidence, delight, calm, urgency, etc.)

### Brand & Personality
- How would you describe the brand personality in 3 words?
- Any reference sites or apps that capture the right feel? What specifically about them?
- What should this explicitly NOT look like? Any anti-references?

### Aesthetic Preferences
- Any strong preferences for visual direction? (minimal, bold, elegant, playful, technical, organic, etc.)
- Light mode, dark mode, or both?
- Any colors that must be used or avoided?

### Accessibility & Inclusion
- Specific accessibility requirements? (WCAG level, known user needs)
- Considerations for reduced motion, color blindness, or other accommodations?

Skip questions where the answer is already clear from the codebase exploration.

## Step 3: Write Design Context

Synthesize your findings and the user's answers into a `## Design Context` section:

```markdown
## Design Context

### Users
[Who they are, their context, the job to be done]

### Brand Personality
[Voice, tone, 3-word personality, emotional goals]

### Aesthetic Direction
[Visual tone, references, anti-references, theme]

### Design Principles
[3-5 principles derived from the conversation that should guide all design decisions]
```

Write this section to `.impeccable.md` in the project root. If the file already exists, update the Design Context section in place.

Then {{ask_instruction}} whether they'd also like the Design Context appended to {{config_file}}. If yes, append or update the section there as well.

Confirm completion and summarize the key design principles that will now guide all future work.

Overview

This skill performs a one-time design-context capture for your project and persists it to the project's AI config. It scans the codebase, asks targeted UX and brand questions, and writes a consolidated Design Context to .impeccable.md. The goal is to create a persistent, machine-readable design language that guides every future AI session.

How this skill works

The skill inspects README, package.json, components, brand assets, CSS variables, and any style guides to infer visual and interaction patterns. It then asks only the UX-focused questions needed to fill gaps you couldn’t infer from the codebase. Finally, it synthesizes findings into a Design Context section and writes or updates .impeccable.md, with an optional append/update to your AI config file.

When to use it

  • Initial project setup to establish a persistent design language
  • When onboarding new designers or AI assistants to the project
  • Before major UI refactors or redesigns to keep decisions consistent
  • When adding new components to ensure alignment with existing tokens and patterns
  • If visual or accessibility requirements are unclear and need to be formalized

Best practices

  • Run once early in the project lifecycle and re-run only for major brand or product shifts
  • Scan the entire repo first — only ask questions about what can’t be inferred from files
  • Keep answers concise and actionable for direct inclusion in the Design Context
  • Prefer concrete tokens (hex values, font stacks, spacing scales) over vague preferences
  • Commit .impeccable.md to version control so the design language is auditable and shareable

Example use cases

  • Establishing consistent color, typography, and spacing rules for a new app
  • Capturing brand tone and accessibility targets before building UI components
  • Persisting design decisions so AI assistants can generate UI that fits the product’s voice
  • Updating component libraries with a single source of visual truth
  • Onboarding contractors or external vendors to the product’s visual and interaction expectations

FAQ

What file does this write to?

.impeccable.md in the project root contains the Design Context; you can opt to also append/update your AI config file.

Do I need to answer every question?

No. The workflow only asks questions that couldn’t be inferred from the codebase scan; skip items that are already clear.

Can I update the Design Context later?

Yes. Re-run the skill or manually edit .impeccable.md; the skill will update the Design Context in place if it already exists.