Design AI Feature — AI skill for Claude Code
Design an AI-powered feature end-to-end — model selection, prompt architecture, eval framework, failure modes, cost modeling, and improvement flywheel.
How to install Design AI Feature
Installs to ~/.claude/skills/productfculty-aipm-pm-copilot-by-product-faculty-design-ai-feature/SKILL.md
mkdir -p ~/.claude/skills/productfculty-aipm-pm-copilot-by-product-faculty-design-ai-feature && curl -fsSL https://raw.githubusercontent.com/Productfculty-aipm/PM-Copilot-by-Product-Faculty/HEAD/commands/design-ai-feature.md -o ~/.claude/skills/productfculty-aipm-pm-copilot-by-product-faculty-design-ai-feature/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Design AI Feature does
description: Design an AI-powered feature end-to-end — model selection, prompt architecture, eval framework, failure modes, cost modeling, and improvement flywheel argument-hint: allowed-tools: [Read, Write, Glob, WebSearch, Agent]
/design-ai-feature
You are a senior PM partner designing an AI-powered feature. This chains AI evals skills into a product design workflow: problem validation → model selection → prompt architecture → eval fram
Alternatives in AI
- Axonhub — ⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs 3.2k ★
- Skill Architecture — System architecture and API design with multi-AI consensus — use for design reviews and new subsystems 2.8k ★
- Model Selection — Model Selection & Task Tool 1.1k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Find Failures
Find how your AI product fails: review real traces in Eval Studio and group your notes into failure modes
AI Agents Workshop
2-hour workshop: build an AI agent in under 150 lines of Node.js. Concepts, architecture, failure modes, and l
Codex Plan Review
Adversarial Codex review of a PLAN or design (not code) via the local Codex CLI. Read-only second-model challe
Shain Design System Skill
Claude skill for token-based design systems in Figma — three-tier architecture, Light/Dark modes, BEM-style co
Claude Failures
Documented failure modes from working with Claude Code. Post-mortems of real incidents where the AI agent assu
Luck
A skill for improving the luck of your AI stack and projects—developed from an applied theoretical framework.
Related Agents
AI Integration Specialist
Use this agent for AI model integration, prompt engineering, and intelligent code generation features. This ag
Brain Eval Engineer
Evaluation engineer — question set tooling, layered metrics (harvest/graph/retrieval/answer), fixed-strategy a
Run Analyst
Run Analyst -- chunk-read agent-run JSONs and surface failure patterns, cost outliers, fix-cycle loops, and im