prompting
Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive discovery, and optimization for signal-to-noise ratio.
Best use case
prompting is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive discovery, and optimization for signal-to-noise ratio.
Teams using prompting should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/prompting/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How prompting Compares
| Feature / Agent | prompting | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive discovery, and optimization for signal-to-noise ratio.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Prompting Skill
## When to Activate This Skill
- Prompt engineering questions
- Context engineering guidance
- AI agent design
- Prompt structure help
- Best practices for LLM prompts
- Agent configuration
## Core Philosophy
**Context engineering** = Curating optimal set of tokens during LLM inference
**Primary Goal:** Find smallest possible set of high-signal tokens that maximize desired outcomes
## Key Principles
### 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
## Markdown Structure Standards
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
## Writing Style
### 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
## Context Management
### 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
## Best Practices Checklist
- [ ] Uses Markdown headers for organization
- [ ] Clear, direct, minimal language
- [ ] No redundant information
- [ ] Actionable instructions
- [ ] Concrete examples
- [ ] Clear constraints
- [ ] Just-in-time loading when appropriate
## Anti-Patterns
❌ Verbose explanations
❌ Historical context dumping
❌ Overlapping tool definitions
❌ Premature information loading
❌ Vague instructions ("might", "could", "should")
## Supplementary Resources
For full standards: `read ${PAI_DIR}/skills/prompting/CLAUDE.md`
## Based On
Anthropic's "Effective Context Engineering for AI Agents"Related Skills
video-prompting-guide
Best practices and techniques for writing effective AI video generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting strategies. Learn: shot types, camera movements, lighting, pacing, style keywords, negative prompts. Use for: improving video quality, getting consistent results, professional video prompts. Triggers: video prompt, how to prompt video, veo prompts, video generation tips, better ai video, video prompt engineering, video prompt guide, video prompt template, ai video tips, video prompt best practices, video prompt examples, cinematography prompts
DSPy — Programming (Not Prompting) LLMs
You are an expert in DSPy, the Stanford framework that replaces prompt engineering with programming. You help developers define LLM tasks as typed signatures, compose them into modules, and automatically optimize prompts/few-shot examples using teleprompters — so instead of manually crafting prompts, you write Python code and DSPy finds the best prompts for your task.
managing-deployment-rollbacks
This skill manages and executes deployment rollbacks with safety checks. It helps ensure smooth recovery from failed deployments by automating the rollback process. Use this skill when a deployment has issues, such as errors, performance degradation, or unexpected behavior. The skill is triggered by requests to "rollback deployment", "revert to previous version", or similar phrases related to deployment recovery. It prioritizes safe rollback procedures and provides options for verification.
orchestrating-deployment-pipelines
This skill orchestrates complex, multi-stage deployment pipelines. It generates production-ready configurations and setup code based on user-specified requirements and infrastructure. Use this skill when the user asks to create a deployment pipeline, generate CI/CD configurations, or needs help with automating software deployments. Trigger terms include "deployment pipeline", "CI/CD", "automate deployment", "pipeline configuration", and "deployment orchestration".
deploying-monitoring-stacks
Monitor use when deploying monitoring stacks including Prometheus, Grafana, and Datadog. Trigger with phrases like "deploy monitoring stack", "setup prometheus", "configure grafana", or "install datadog agent". Generates production-ready configurations with metric collection, visualization dashboards, and alerting rules.
deploying-machine-learning-models
Deploy this skill enables AI assistant to deploy machine learning models to production environments. it automates the deployment workflow, implements best practices for serving models, optimizes performance, and handles potential errors. use this skill when th... Use when deploying or managing infrastructure. Trigger with phrases like 'deploy', 'infrastructure', or 'CI/CD'.
dependency-vulnerability-checker
Dependency Vulnerability Checker - Auto-activating skill for Security Fundamentals. Triggers on: dependency vulnerability checker, dependency vulnerability checker Part of the Security Fundamentals skill category.
analyzing-dependencies
This skill analyzes project dependencies for security vulnerabilities, outdated packages, and license compliance issues. It helps identify potential risks in your project's dependencies using the dependency-checker plugin. Use this skill when you need to check dependencies for vulnerabilities, identify outdated packages that need updates, or ensure license compatibility. Trigger phrases include "check dependencies", "dependency check", "find vulnerabilities", "scan for outdated packages", "/depcheck", and "license compliance". This skill supports npm, pip, composer, gem, and go modules projects.
definition-of-done-generator
Definition Of Done Generator - Auto-activating skill for Enterprise Workflows. Triggers on: definition of done generator, definition of done generator Part of the Enterprise Workflows skill category.
deepgram-webhooks-events
Implement Deepgram callback and webhook handling for async transcription. Use when implementing callback URLs, processing async transcription results, or handling Deepgram event notifications. Trigger: "deepgram callback", "deepgram webhook", "async transcription", "deepgram events", "deepgram notifications", "deepgram async".
deepgram-upgrade-migration
Plan and execute Deepgram SDK upgrades and model migrations. Use when upgrading SDK versions (v3->v4->v5), migrating models (Nova-2 to Nova-3), or planning API version transitions. Trigger: "upgrade deepgram", "deepgram migration", "update deepgram SDK", "deepgram version upgrade", "nova-3 migration".
deepgram-security-basics
Apply Deepgram security best practices for API key management and data protection. Use when securing Deepgram integrations, implementing key rotation, or auditing security configurations. Trigger: "deepgram security", "deepgram API key security", "secure deepgram", "deepgram key rotation", "deepgram data protection", "deepgram PII redaction".