Prompt Architecture — AI skill for Claude Code
Reference guide for designing production LLM prompt systems in this codebase.
How to install Prompt Architecture
Installs to ~/.claude/skills/33-strategies-33-strategies-claude-code-starter-kit-prompt-architecture/SKILL.md
mkdir -p ~/.claude/skills/33-strategies-33-strategies-claude-code-starter-kit-prompt-architecture && curl -fsSL https://raw.githubusercontent.com/33-Strategies/33-strategies-claude-code-starter-kit/HEAD/.claude/skills/prompt-architecture.md -o ~/.claude/skills/33-strategies-33-strategies-claude-code-starter-kit-prompt-architecture/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Prompt Architecture does
name: prompt-architecture description: Reference guide for designing production LLM prompt systems in this codebase. Covers the Two-Pass Gap Analysis pattern, structured extraction prompts, confidence scoring, dynamic rubric injection, and validation patterns. Use when building AI extraction, synthesis, or coaching features.
Prompt Architecture Skill
This skill documents the prompt engineering patterns used in 33 Strategies production systems. Use when building new LLM-powered featur
Alternatives in AI
- Guizang Ppt Skill — AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts 24.9k ★
- Dive Into Claude Code — A Systematic Analysis and Discussion of Claude Code for Designing Today's and Future AI Agent Systems 2.1k ★
- Learning Goal — A Claude Code skill for designing learning goals during AI-assisted coding 249 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Agentic Job Search
Agentic job-application system built AI-first with Claude Code: hourly watcher over 46 job boards with qualifi
Autoconst Claude Drawing Takeoff
Turn a construction PDF drawing set into a priced Bill of Quantities in Excel. Deterministic vector-text extra
Team Memory MCP
Shared team memory for AI coding agents. Bayesian confidence scoring with temporal decay. Works with Claude Co
ComputerAgent
Run any AI agent — Claude Code, GAP, LangGraph DeepAgents — in a hermetic sandbox. Reference implementation of
AI Engineering Claude C3 Agent Evaluation And Observability Project
Three Claude AI agent pipelines demonstrating evaluation and observability: validated retry with human-in-the-
RedBook Note Workflow
🔥 All-in-one Xiaohongshu (RedBook) content creation workflow powered by Claude Code. AI-driven topic scoring,
Related Agents
Pipeline Developer
Implements data-pipeline work (code: pipeline) against a principal-engineer plan, in an isolated worktree — pi
LLM Specialist
Prompt engineering specialist and LLM expert. Use when crafting prompts, optimizing AI responses, or implement
AI Redteam
Use PROACTIVELY for AI CTF challenges and LLM security challenges. Triggers on prompt injection, jailbreak, LL