Creates architecture design and implementation plan through Socratic dialogue. Use after user approves a research approach - produces design.md and plan.md before any code is written.
/plugin marketplace add astrosteveo/claude-code-plugins/plugin install harness@astrosteveo-pluginsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Collaborative design through Socratic dialogue. Iterate until full agreement on approach.
Start by reading:
requirements.md - What we're building and success criteriacodebase.md - Technical context and patternsresearch.md - Best practices and the approved approachCreate the high-level design through dialogue:
Section by Section
Content to Cover
Create .harness/{nnn}-{slug}/design.md:
# Design: {Task Name}
## Architecture Overview
{High-level description with mermaid diagram}
## Components
{Key components and their responsibilities}
## Data Flow
{How data moves through the system}
## Interfaces
{Key interfaces and boundaries}
## Key Decisions
{Design decisions and their rationale}
Create the granular implementation plan:
Step Sizing
Step Format
{nnn}-1, {nnn}-2, etc.Create .harness/{nnn}-{slug}/plan.md:
# Implementation Plan: {Task Name}
## Overview
{Brief summary of the plan}
## Pre-Implementation Checklist
- [ ] requirements.md reviewed
- [ ] design.md approved
- [ ] User approval of plan
---
## Step {nnn}-1: {Description}
**Files to create/modify:**
- `path/to/file.ext`
**Details:**
{What to implement}
**Commit message:** `{type}: {description}`
---
## Step {nnn}-2: {Description}
...
---
## Summary
| Step | Description | Files |
|------|-------------|-------|
## Deferred Items
{Items moved to backlog.md}
During planning, identify items to defer:
Add deferred items to .harness/backlog.md:
## Deferred from {nnn}-{slug}
- [ ] {Item description} - {Reason for deferral}
Unrelated bugs found:
.harness/backlog.md with detailsRefactoring opportunities:
.harness/backlog.mdBefore proceeding to Execute:
When plan is approved:
"Plan looks good. Ready to move to Execute? We'll follow TDD - writing tests first, then implementation."
You may return to this phase when:
Update design.md and plan.md to reflect changes. Mark where you left off if execution was in progress.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.