system-prompt-writer
This skill should be used when writing or improving system prompts for AI agents, providing expert guidance based on Anthropic's context engineering principles.
npx skills add majiayu000/claude-skill-registry --skill system-prompt-writer --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Provides comprehensive guidelines for writing effective system prompts for AI agents, grounded in context engineering principles and Anthropic-style recommendations.
How it works
- Emphasizes Context Engineering: curate the information within the context window to the minimum effective dose.
- Guides on Altitude: prompts should be in a Goldilocks zone—neither too rigid nor too vague.
- Encourages Minimal but Sufficient information: prioritize high-signal tokens; provide necessary decision-making criteria when needed.
- Recommends a structured hybrid format: use Markdown headers for major sections and XML-like tags for content within sections; details template escaping and Python .format usage with specific rules for single vs double braces.
- Includes concrete examples and templates for Role, Background Information, Instructions, Tool Guidance, Success Criteria, and Constraints.
- Stresses clear Tool Guidance with decision frameworks and prerequisites, plus best practices and common pitfalls.
- Promotes few-shot prompting with canonical examples and a defined success criteria set.
When to use it
Use when creating or refining system prompts for AI agents to ensure prompts are clear, actionable, and aligned with context-engineering principles. Triggers appear in contexts requiring structured, parseable prompts with explicit tool guidance and template safety rules.
What it can touch
- Tool Guidance: provides guidance on when to use tools and how to structure decision trees.
- Template Guidance: outlines escaping rules for Python-style templating and how to handle placeholders vs literals.
- Structure Guidelines: demonstrates how to organize prompts with role, background, instructions, tool guidance, success criteria, and constraints.
Caveats
- Based on Anthropic's context-engineering principles; adheres to the template rules that single braces denote variables and double braces escape braces in code samples.
- Recommends explicit, unambiguous tool usage guidance and avoidance of vague terms like "as needed."
# System Prompt Writer Skill This skill provides comprehensive guidelines for writing effective system prompts for AI agents, based on Anthropic's "Effective Context Engineering for AI Agents" principles. ## Core Philosophy: Context Engineering **Context Engineering** is the art and science of curating what goes into the limited context window. The key principle is: > "Find the minimum effective dose of information - the smallest possible set of high-signal tokens that maximize the likelihood of the desired outcome." ## System Prompt Writing Guidelines ### 1. Write at the "Right Altitude" System prompts should be in the **Goldilocks zone** - not too rigid, not too vague. **Too Rigid (Avoid):** ``` When the user asks about weather, first check the database, then validate the ZIP code format using regex pattern ^\d{5}(?:[-\s]\d{4})?$, then call get_weather_data with exactly these parameters... ``` **Too Vague (Avoid):** ``` Help users with their questions. ``` **Just Right (Use):** ``` You are a weather assistant. When users ask about weather: 1. Validate location information 2. Use available tools to fetch current weather data 3. Present information in a clear, conversational format
- Core Philosophy: Context Engineering
- System Prompt Writing Guidelines
- 1. Write at the "Right Altitude"
- 2. Minimum Effective Information
- 3. Structure for Clarity
- Analysis Stage: {{stagename}}
- Execution Time: {{currenttime}}
- 4. Tool Guidance in Prompts
- 5. Few-Shot Prompting: Use Examples Wisely
- 6. Define Success Criteria
- 7. Provide Motivation Context
- Context Management Strategies
- Strategy 1: Just-in-Time Loading
- Strategy 2: Progressive Disclosure
What does the system-prompt-writer skill do?
This skill should be used when writing or improving system prompts for AI agents, providing expert guidance based on Anthropic's context engineering principles.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill system-prompt-writer --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.