Prompt Writer — Data & AI agent for Claude Code
Generate concise, focused prompts using a lightweight model.
How to install Prompt Writer
Installs to ~/.claude/agents/shimo4228-claude-harness-prompt-writer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/shimo4228/claude-harness/HEAD/agents/prompt-writer.md -o ~/.claude/agents/shimo4228-claude-harness-prompt-writer.md Restart Claude Code, or start a new session, for it to be picked up.
What Prompt Writer does
name: prompt-writer description: Generate concise, focused prompts using a lightweight model. Use when creating or rewriting LLM prompt templates. tools: ["Read", "Grep", "Glob"] model: haiku origin: shimo4228
You are a prompt writer. Your job is to generate clear, concise prompts for LLM tasks.
Core Principle
Less is more. A shorter prompt that captures the essence outperforms a longer one cluttered with edge cases.
Writing Guidelines
- Start with the task: First sente
Alternatives in Data & AI
- Visual Explainer — Agent skill + prompt templates that generate rich HTML pages for visual diff reviews, architecture overviews 6.8k ★
- Lemonade Specialist — Lemonade Server and SDK specialist for local LLM on AMD hardware 1.5k ★
- LLM AI Hunter — LLM and Agentic AI vulnerability specialist 812 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
10 Content Strategist
AI prompts, landing page copy, email templates, UX microcopy, brand voice. Invoke for any written content or A
LLM Integrator
LLM integration specialist who connects to OpenAI/Anthropic/Ollama APIs, designs prompt templates, implements
Prompt Reviewer Code
Locates LLM call sites in any codebase (Go, Python, TypeScript, anything), reconstructs the resolved prompt fr
Judge Writer
Writes a binary LLM-as-judge prompt for exactly one failure mode, from a definition and a handful of human-lab
LLM Specialist
Prompt engineering specialist and LLM expert. Use when crafting prompts, optimizing AI responses, or implement
Prompt Reviewer Logs
Reads LLM input/output records from any database (Postgres, MongoDB, MySQL, BigQuery, SQLite, etc.) via standa
Related Skills
Secure LLM Gateway
Security-focused gateway in front of an LLM API — auth, prompt-injection defense, output filtering, audit logg
Brainrouter
LLM routing proxy for coding harnesses. Auto-routes to cloud or local inference via Bonsai LLM classification.
LLM Coding Templates
Battle-tested, customizable prompt templates for safe AI-assisted development.