amhuppert/my-ai-resources/add-design-agent
- community
Checking that the SKILL.md file is still in the repository.
Create a research or review agent for the /design workflow.
Install
npx vskill@latest install amhuppert/my-ai-resources/add-design-agentSKILL.md
Create a new project-specific design agent that integrates with the /design workflow.
Arguments
- Agent type (optional) - "research" or "review"
- research: Domain expert that gathers information during Phase 2 (before design synthesis)
- review: Evaluator that reviews designs during Phase 4 (after synthesis)
- Agent name (optional) - Name for the agent (will be suffixed with
-agent)
Extract both values from the user's invocation input.
Process
Step 1: Determine Agent Type
If the agent type is missing or is not "research" or "review", ask the user with the active client's user-question mechanism:
- Question: "What type of design agent do you want to create?"
- Options:
- "Research Agent" - Gathers domain-specific information before design synthesis
- "Review Agent" - Evaluates designs for specific concerns after synthesis
Step 2: Get Agent Details
Use the active client's user-question mechanism to gather:
Question 1: Agent Name
- "What should this agent be called? (will be suffixed with -agent)"
- If an agent name was provided, skip this question and use it
Question 2: Domain/Expertise
- "What is this agent's area of expertise?"
- Example answers: "security", "accessibility", "performance", "domain X best practices"
Question 3: Key Responsibilities
- "What are the main things this agent should analyze? (Select all that apply or describe)"
- Options will vary based on type:
- Research: "Best practices", "Industry standards", "Implementation patterns", "Tradeoffs"
- Review: "Security issues", "Performance concerns", "Compliance", "Best practices adherence"
Step 3: Create the Agent
Create the agent directly using the active client's custom-agent format. If a dedicated agent-development skill is available, use it.
Provide this context to the skill:
Step 4: Save the Agent
Save the generated agent file to the active client's path above. Create the parent directory if it doesn't exist.
Step 5: Update DESIGN-AGENTS.md
Check if memory-bank/DESIGN-AGENTS.md exists.
If it doesn't exist:
- Create it using
references/design-agents-template.md - Add the new agent to the appropriate section
If it exists:
- Read the current content
- Find the appropriate section:
- For research agents: "## Research Agents"
- For review agents: "## Review Agents"
- Add a new entry:
- [agent-name]-agent: [brief description of expertise]
Step 6: Confirm Creation
Report to the user:
Error Handling
- If the active client's project agent directory cannot be created, report the error and suggest manual creation
- If DESIGN-AGENTS.md update fails, provide the entry to add manually
- If agent name conflicts with existing agent, ask for a different name
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingplugins/ai-resources/skills/add-design-agent/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/amhuppert/my-ai-resources/add-design-agent)