prompt-authoring
Guidance for creating effective prompts, chains, and gates using CAGEERF methodology
When & Why to Use This Skill
The Prompt Authoring skill provides a professional framework for engineering high-performance AI interactions using the CAGEERF methodology. It enables developers to move beyond simple prompting by implementing structured templates, sequential prompt chains, and automated quality gates, ensuring that AI agent outputs are consistent, validated, and optimized for complex tasks.
Use Cases
- Structured Prompt Engineering: Applying the CAGEERF (Context, Analysis, Goals, Execution, Evaluation, Refinement, Finalization) framework to create comprehensive prompts that improve accuracy and reduce hallucinations.
- Complex Workflow Orchestration: Designing multi-step execution chains that connect prompts sequentially (e.g., analyze -> design -> implement) with seamless context passing.
- Automated Quality Assurance: Implementing severity-based 'Quality Gates' to programmatically validate AI-generated content against specific business criteria and technical requirements.
- Standardized Resource Management: Utilizing standardized YAML structures and the resource_manager tool to create, organize, and maintain a scalable library of prompt templates for AI agent systems.
| name | prompt-authoring |
|---|---|
| description | Guidance for creating effective prompts, chains, and gates using CAGEERF methodology |
| version | 1.0.0 |
Prompt Authoring Guide
This skill provides patterns for creating prompts in the claude-prompts system.
CAGEERF Methodology
Prompts follow the C.A.G.E.E.R.F framework:
| Phase | Purpose | Output |
|---|---|---|
| Context | Gather domain knowledge | Situational understanding |
| Analysis | Break down the problem | Structured insights |
| Goals | Define success criteria | Measurable objectives |
| Execution | Implement the solution | Concrete deliverables |
| Evaluation | Validate against goals | Quality assessment |
| Refinement | Iterate based on feedback | Improved output |
| Finalization | Complete and document | Final deliverable |
Prompt Structure
---
id: my-prompt
name: My Prompt
description: What this prompt accomplishes
category: development
execution_hint: single # or 'chain'
arguments:
- name: input
type: string
description: Primary input
---
system_message: |
You are an expert at [domain].
user_message_template: |
Task: {input}
Requirements:
- Requirement 1
- Requirement 2
Chain Definition
Chains connect prompts with -->:
>>analyze --> >>design --> >>implement --> >>test
Chain features:
- Sequential execution with context passing
- Gate validation between steps
- Resume capability with
chain_id
Quality Gates
Gates validate output quality:
id: code-quality
name: Code Quality Gate
severity: high
criteria:
- "Code follows established patterns"
- "Error handling is comprehensive"
pass_criteria:
- "All criteria met with evidence"
Severity levels: critical | high | medium | low
Creating New Prompts
Use the resource_manager tool:
resource_manager({
resource_type: "prompt",
action: "create",
id: "new-prompt",
name: "New Prompt",
description: "Purpose",
category: "development",
system_message: "...",
user_message_template: "..."
})
Best Practices
- Clear objectives: Define what success looks like
- Structured output: Specify expected format
- Validation criteria: Include checkable requirements
- Composability: Design prompts that chain well
- Gate integration: Add quality checks for critical outputs