atomic-prompts
This skill should be used when the user asks to "write system prompt", "configure SystemPromptGenerator", "prompt engineering", "background steps output_instructions", "improve agent prompt", or needs guidance on structuring system prompts, writing effective instructions, and optimizing agent behavior in Atomic Agents applications.
npx skills add majiayu000/claude-skill-registry --skill atomic-prompts --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.
# Atomic Agents System Prompt Design The `SystemPromptGenerator` creates structured, effective system prompts for agents. It combines static instructions with dynamic context from providers. ## SystemPromptGenerator Structure ```python from atomic_agents.lib.components.system_prompt_generator import SystemPromptGenerator system_prompt = SystemPromptGenerator( background=[ # WHO the agent is "You are an expert data analyst.", "You specialize in financial data interpretation.", ], steps=[ # HOW to process requests "1. Understand the user's question about the data.", "2. Identify relevant data points and trends.", "3. Analyze patterns and correlations.", "4. Formulate clear, actionable insights.", ], output_instructions=[ # WHAT to produce "Provide insights in clear, non-technical language.", "Include specific numbers and percentages.", "Highlight key takeaways at the beginning.", ], ) ``` ## Three-Part Structure ### Background (WHO) Establishes the agent's identity, expertise, and role: ```python background=[ "You are an expert [role] with deep knowledge in [domain].", "Your purpose is to [primary function].", "You have experience with [relevant experience].", "You approach problems
- SystemPromptGenerator Structure
- Three-Part Structure
- Background (WHO)
- Steps (HOW)
- Output Instructions (WHAT)
- Integrating Context Providers
- Prompt Engineering Tips
- Be Specific
- Use Action Verbs
- Constrain Output
- Handle Edge Cases
- Common Prompt Patterns
- Expert Assistant
- Analyst
What does the atomic-prompts skill do?
This skill should be used when the user asks to "write system prompt", "configure SystemPromptGenerator", "prompt engineering", "background steps output_instructions", "improve agent prompt", or needs guidance on structuring system prompts, writing effective instructions, and optimizing agent behavior in Atomic Agents applications.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill atomic-prompts --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.