Agent skill
prototype-react-iterate
Generate and iterate on React/Tailwind/ShadCN prototypes with Persona-driven feedback loops. Creates multiple variants, serves them, uses VLM to simulate user feedback based on Persona traits (Federated Taxonomy), and iterates on the code.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/prototype-react-iterate
Metadata
Additional technical details for this skill
- author
- Horus
- version
- 0.1.0
- short description
- Persona-driven React/ShadCN prototyping lab
SKILL.md
Prototype React Iterate
A closed-loop system for evolving UI designs using AI personas as users.
Workflow
- Create: Scaffolds a Next.js + ShadCN app with
Nvariants (A, B, C...). - Serve: Runs the app (dev server).
- Simulate: Uses a Persona (e.g., "Embry") + VLM to "look" at the UI and provide feedback.
- Feedback is grounded in Persona traits (Bio/Bridge Attributes).
- Output:
ANNOTATIONS.jsonl(coordinates + comments).
- Iterate: Applies feedback to the code using an LLM patcher.
- Loop: Repeats until Persona satisfaction threshold is met.
Quick Start
cd .pi/skills/prototype-react-iterate
# 1. Create 3 variants for a prompt
./run.sh create "Cyberpunk dashboard for controlling a drone swarm" --variants 3
# 2. Run the loop (Serve -> Simulate -> Iterate)
./run.sh loop "Cyberpunk dashboard" --persona "Embry" --max-cycles 3
Commands
create
Scaffold new variants.
./run.sh create "PROMPT" [--variants N] [--out DIR]
simulate
Run a VLM session where a Persona critiques the UI.
./run.sh simulate --url http://localhost:3000 --persona "Embry" --out outputs/run-01/variants/A
iterate
Apply feedback from ANNOTATIONS.jsonl to the code.
./run.sh iterate --dir outputs/run-01/variants/A
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?