prompting

• Prompt engineering questions
• Context engineering guidance
• AI agent design
• Prompt structure help
• Best practices for LLM prompts
• Agent configuration

Context engineering = Curating optimal set of tokens during LLM inference

Primary Goal: Find smallest possible set of high-signal tokens that maximize desired outcomes

1. Context is Finite Resource

• LLMs have limited "attention budget"
• Performance degrades as context grows
• Every token depletes capacity
• Treat context as precious

2. Optimize Signal-to-Noise

• Clear, direct language over verbose explanations
• Remove redundant information
• Focus on high-value tokens

3. Progressive Discovery

• Use lightweight identifiers vs full data dumps
• Load detailed info dynamically when needed
• Just-in-time information loading

Use clear semantic sections:

• Background Information: Minimal essential context
• Instructions: Imperative voice, specific, actionable
• Examples: Show don't tell, concise, representative
• Constraints: Boundaries, limitations, success criteria

Clarity Over Completeness

✅ Good: "Validate input before processing"

❌ Bad: "You should always make sure to validate..."

Be Direct

✅ Good: "Use calculate_tax tool with amount and jurisdiction"

❌ Bad: "You might want to consider using..."

Use Structured Lists

✅ Good: Bulleted constraints

❌ Bad: Paragraph of requirements

Just-in-Time Loading

Don't load full data dumps - use references and load when needed

Structured Note-Taking

Persist important info outside context window

Sub-Agent Architecture

Delegate subtasks to specialized agents with minimal context

• [ ] Uses Markdown headers for organization
• [ ] Clear, direct, minimal language
• [ ] No redundant information
• [ ] Actionable instructions
• [ ] Concrete examples
• [ ] Clear constraints
• [ ] Just-in-time loading when appropriate

❌ Verbose explanations

❌ Historical context dumping

❌ Overlapping tool definitions

❌ Premature information loading

❌ Vague instructions ("might", "could", "should")

For full standards: read ${PAI_DIR}/skills/prompting/CLAUDE.md

Anthropic's "Effective Context Engineering for AI Agents"