claude/ai-resources-plugin/skills/init-design-config/SKILL.md
Initialize DESIGN-AGENTS.md config for the /design workflow, populated from project context.
npx skillsauth add amhuppert/my-ai-resources init-design-configInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Initialize a memory-bank/DESIGN-AGENTS.md configuration file for the /design workflow, populated with values discovered from project context.
Check if memory-bank/DESIGN-AGENTS.md already exists.
If it exists, report to user and ask if they want to overwrite or abort.
Gather information from the project to populate the configuration:
Design System File:
**/design-system*.md, **/design-spec*.md, **/*-design*.mddocs/, agent-docs/, memory-bank/ directories[path/to/design-system.md - remove if none]Requirements File:
memory-bank/*requirements*.md, memory-bank/*REQUIREMENTS*.mddocs/*requirements*.md, **/PRD*.md[auto-detected from memory-bank/*requirements*.md]Existing Project Agents:
.claude/agents/ directory existsProject Type (for suggestions):
tsconfig.json → suggest TypeScript-related agentsapp.json with expo → suggest mobile-related agents.kiro/steering/tech.md for domain hintsCreate the DESIGN-AGENTS.md content:
# Design Agents Configuration
This file configures project-specific agents for the `/design` workflow.
## Configuration
Optional settings for the design workflow:
- design-system-file: [discovered path or placeholder]
- requirements-file: [discovered path or placeholder]
## Research Agents
Domain experts that gather information during Phase 2 (before design synthesis).
These agents run in parallel to research specific aspects of the problem domain.
Add entries as: `- agent-name: Brief description of expertise`
[If domain hints found from steering files, add suggestions as comments:]
<!-- Suggested based on project context:
- [domain]-expert-agent: Researches [domain] best practices and patterns
-->
## Review Agents
Additional reviewers beyond the universal agents that run during Phase 4.
These agents evaluate the design draft for project-specific concerns.
Add entries as: `- agent-name: Brief description of what it reviews`
[If existing project agents found, list them as suggestions:]
<!-- Existing agents in .claude/agents/ that could be added:
- [agent-name]: [description if available]
-->
<!-- Common review agents to consider:
- security-review-agent: Reviews for authentication, authorization, and data protection
- performance-review-agent: Reviews for performance bottlenecks and optimization opportunities
- accessibility-review-agent: Reviews for WCAG compliance and inclusive design
-->
If memory-bank/ directory doesn't exist, create it.
Write the generated content to memory-bank/DESIGN-AGENTS.md.
Report to the user:
## DESIGN-AGENTS.md Initialized
**Location**: memory-bank/DESIGN-AGENTS.md
### Discovered Values
- **Design System**: [path found | not found - placeholder added]
- **Requirements**: [path found | not found - will auto-detect]
### Next Steps
1. Review and update `memory-bank/DESIGN-AGENTS.md`
2. Remove placeholder comments for unused sections
3. Add project-specific research and review agents:
- Use `/add-design-agent` to create new agents
- Or manually add existing agents from `.claude/agents/`
4. Run `/design` to start the design workflow
### Universal Agents (always included)
The following agents run automatically for all projects:
- requirements-validation-agent
- software-engineering-agent
- simplicity-advocate-agent
- testing-strategy-agent
- ux-usability-agent
### Conditional Agents (auto-detected)
These agents are included based on project type:
[List which conditional agents will be included based on detection]
- [If TypeScript]: typescript-type-safety-agent ✓
- [If Expo]: expo-best-practices-agent ✓
- [If design system configured]: design-system-agent ✓
development
Debug a running web app via the web-debugger SDK: app logs, application state, runtime snapshots, React state, query cache.
development
Thoroughly understand a software development objective before implementation: research, identify ambiguities, ask clarifying questions. Use before starting implementation of a non-trivial or ambiguously specified feature, or when requirements leave open design decisions.
development
Locate the on-disk Claude Code transcript file (.jsonl under ~/.claude/projects/) for the current or a specified conversation.
development
Reflect on codebase navigation effectiveness at end of conversation. Surfaces dead ends, inefficiencies, missing context. Does not write files — pair with /kiro:steering-custom to persist.