| Dimension | Shared | Only in A | Only in B | Overlap |
|---|---|---|---|---|
| Sections | 0 | 6 | 8 | 0% |
| Commands | 0 | 0 | 1 | 0% |
| Section tags | 1 | 1 | 2 | 25% |
What each file covers
Sections
0 shared · 6 only in A · 8 only in B- − Cline Rules for Megarepo
- − Rules Structure
- − How Cline Uses These Rules
- − Customization
- − Rules Bank Approach
- − Consistency with Other AI Assistants
- + Prompt Engineering Templates
- + Prompt Engineering Best Practices
- + 1. Prompt Structure Templates
- + 2. Prompt Versioning
- + 3. Dynamic Prompt Generation
- + 4. Context Management
- + 5. Prompt Optimization Techniques
- + 6. Testing and Validation
Commands
0 shared · 0 only in A · 1 only in B- + task: string,
Section tags
1 shared · 1 only in A · 2 only in B- − do-not
- + test
- + code-style
- architecture
Line diff
HerringtonDarkholme/megarepo · .clinerules/README.md
@@ −1 @@
1# Cline Rules for Megarepo
2
3This directory contains Cline Rules that provide system-level guidance for the Cline AI assistant when working on this AI setup repository.
4
5## Rules Structure
6
7The rules are organized into focused files that build upon each other:
8
91. **`01-core-principles.md`** - Fundamental principles including minimal change philosophy and AI-first development
102. **`02-development.md`** - Development guidelines for Node.js/Next.js AI projects
113. **`03-documentation.md`** - Documentation requirements and standards
124. **`04-security.md`** - Security guidelines for AI projects and API key management
13
14## How Cline Uses These Rules
15
16Cline automatically processes all Markdown files in this directory, combining them into a unified set of rules. The numeric prefixes help organize the files in a logical sequence, ensuring core principles are established before specific guidelines.
17
18## Customization
19
20These rules are tailored specifically for the Megarepo AI setup repository and should be updated as the project evolves. The rules emphasize:
21
22- **Minimal Changes**: Surgical, precise modifications that respect the repository's intentional simplicity
23- **AI-First Development**: Patterns and practices optimized for AI service integrations
24- **Security Best Practices**: Safe handling of API keys and sensitive data
25- **Node.js/Next.js Patterns**: Guidelines specific to the target technology stack
26
27## Rules Bank Approach
28
29This repository follows the "active rules" pattern where the `.clinerules/` directory contains only the rules that should be active. For projects with multiple contexts, consider creating a `clinerules-bank/` directory with additional rule sets that can be activated as needed.
30
31## Consistency with Other AI Assistants
32
33These rules are designed to work alongside other AI assistant configurations in this repository:
34- GitHub Copilot (`.github/copilot-instructions.md`)
35- Claude AI (`CLAUDE.md`)
36- Cursor AI (`.cursorrules`)
37- Gemini CLI (`GEMINI.md`)
38- Universal AI guidelines (`AGENT.md`, `AGENTS.md`)
39
40All configurations share common principles while being optimized for each assistant's specific capabilities.
HerringtonDarkholme/megarepo · .cursor/rules/prompt-engineering.mdc
@@ +1 @@
1---
2description: "Prompt engineering templates and best practices for AI model interactions"
3alwaysApply: false
4---
5
6# Prompt Engineering Templates
7
8Guidelines and templates for effective AI prompt engineering. Use `@prompt-engineering` to include this rule.
9
10## Prompt Engineering Best Practices
11
12### 1. Prompt Structure Templates
13```typescript
14// System prompt template
15const SYSTEM_PROMPT = `
16You are an expert assistant specialized in [DOMAIN].
17Your responses should be:
18- Accurate and factual
19- Concise but comprehensive
20- Professional in tone
21- Focused on [SPECIFIC_GOAL]
22
23Context: [CONTEXT_INFORMATION]
24`;
25
26// User prompt template
27const createUserPrompt = (input: string, context?: string) => `
28Task: ${input}
29${context ? `Additional context: ${context}` : ''}
30
31Please provide a response that follows the system guidelines.
32`;
33```
34
35### 2. Prompt Versioning
36- Store prompts in separate configuration files
37- Version prompts for A/B testing
38- Track prompt performance and iterate
39- Document prompt changes and rationale
40
41### 3. Dynamic Prompt Generation
42```typescript
43interface PromptConfig {
44 system: string;
45 temperature: number;
46 maxTokens: number;
47 stopSequences?: string[];
48}
49
50const generatePrompt = (
51 task: string,
52 userInput: string,
53 config: PromptConfig
54) => {
55 // Build context-aware prompts
56 // Include relevant examples
57 // Optimize for token efficiency
58};
59```
60
61### 4. Context Management
62- Implement conversation memory
63- Manage context window limits
64- Prioritize relevant information
65- Handle context overflow gracefully
66
67### 5. Prompt Optimization Techniques
68- Use few-shot learning examples
69- Implement chain-of-thought prompting
70- Apply role-based prompting
71- Include output format specifications
72
73### 6. Testing and Validation
74- Create test suites for prompt effectiveness
75- Measure response quality metrics
76- Compare different prompt versions
77- Monitor prompt performance in production
@@ −1 +1 @@
1−# Cline Rules for Megarepo
1+---
2+description: "Prompt engineering templates and best practices for AI model interactions"
3+alwaysApply: false
4+---
25
3−This directory contains Cline Rules that provide system-level guidance for the Cline AI assistant when working on this AI setup repository.
6+# Prompt Engineering Templates
47
5−## Rules Structure
8+Guidelines and templates for effective AI prompt engineering. Use `@prompt-engineering` to include this rule.
69
7−The rules are organized into focused files that build upon each other:
10+## Prompt Engineering Best Practices
811
9−1. **`01-core-principles.md`** - Fundamental principles including minimal change philosophy and AI-first development
10−2. **`02-development.md`** - Development guidelines for Node.js/Next.js AI projects
11−3. **`03-documentation.md`** - Documentation requirements and standards
12−4. **`04-security.md`** - Security guidelines for AI projects and API key management
12+### 1. Prompt Structure Templates
13+```typescript
14+// System prompt template
15+const SYSTEM_PROMPT = `
16+You are an expert assistant specialized in [DOMAIN].
17+Your responses should be:
18+- Accurate and factual
19+- Concise but comprehensive
20+- Professional in tone
21+- Focused on [SPECIFIC_GOAL]
1322
14−## How Cline Uses These Rules
23+Context: [CONTEXT_INFORMATION]
24+`;
1525
16−Cline automatically processes all Markdown files in this directory, combining them into a unified set of rules. The numeric prefixes help organize the files in a logical sequence, ensuring core principles are established before specific guidelines.
26+// User prompt template
27+const createUserPrompt = (input: string, context?: string) => `
28+Task: ${input}
29+${context ? `Additional context: ${context}` : ''}
1730
18−## Customization
31+Please provide a response that follows the system guidelines.
32+`;
33+```
1934
20−These rules are tailored specifically for the Megarepo AI setup repository and should be updated as the project evolves. The rules emphasize:
35+### 2. Prompt Versioning
36+- Store prompts in separate configuration files
37+- Version prompts for A/B testing
38+- Track prompt performance and iterate
39+- Document prompt changes and rationale
2140
22−- **Minimal Changes**: Surgical, precise modifications that respect the repository's intentional simplicity
23−- **AI-First Development**: Patterns and practices optimized for AI service integrations
24−- **Security Best Practices**: Safe handling of API keys and sensitive data
25−- **Node.js/Next.js Patterns**: Guidelines specific to the target technology stack
41+### 3. Dynamic Prompt Generation
42+```typescript
43+interface PromptConfig {
44+ system: string;
45+ temperature: number;
46+ maxTokens: number;
47+ stopSequences?: string[];
48+}
2649
27−## Rules Bank Approach
50+const generatePrompt = (
51+ task: string,
52+ userInput: string,
53+ config: PromptConfig
54+) => {
55+ // Build context-aware prompts
56+ // Include relevant examples
57+ // Optimize for token efficiency
58+};
59+```
2860
29−This repository follows the "active rules" pattern where the `.clinerules/` directory contains only the rules that should be active. For projects with multiple contexts, consider creating a `clinerules-bank/` directory with additional rule sets that can be activated as needed.
61+### 4. Context Management
62+- Implement conversation memory
63+- Manage context window limits
64+- Prioritize relevant information
65+- Handle context overflow gracefully
3066
31−## Consistency with Other AI Assistants
67+### 5. Prompt Optimization Techniques
68+- Use few-shot learning examples
69+- Implement chain-of-thought prompting
70+- Apply role-based prompting
71+- Include output format specifications
3272
33−These rules are designed to work alongside other AI assistant configurations in this repository:
34−- GitHub Copilot (`.github/copilot-instructions.md`)
35−- Claude AI (`CLAUDE.md`)
36−- Cursor AI (`.cursorrules`)
37−- Gemini CLI (`GEMINI.md`)
38−- Universal AI guidelines (`AGENT.md`, `AGENTS.md`)
39−
40−All configurations share common principles while being optimized for each assistant's specific capabilities.
73+### 6. Testing and Validation
74+- Create test suites for prompt effectiveness
75+- Measure response quality metrics
76+- Compare different prompt versions
77+- Monitor prompt performance in production
