generate-custom-instructions-from-codebase

Generates GitHub Copilot migration instructions by analyzing code differences between project versions. Compares two project states (branches, commits, or tags) to extract transformation patterns, API changes, and architectural shifts Creates a .github/copilot-migration-instructions.md file with mandatory rules, validated transformations, API correspondences, and obsolete patterns to avoid Supports multiple migration types: framework version upgrades, architecture refactoring, technology replacement, dependency updates, and pattern changes Configurable automation levels (Conservative, Balanced, Aggressive) and optional before/after code examples to guide Copilot's future transformations Includes validation checkpoints, error reporting mechanisms, and monitoring metrics to track migration accuracy and consistency

INSTALLATION
npx skills add https://github.com/github/awesome-copilot --skill generate-custom-instructions-from-codebase
Run in your project or agent environment. Adjust flags if your CLI version differs.

SKILL.md

$2b

${AUTOMATION_LEVEL="Conservative|Balanced|Aggressive"}

${GENERATE_EXAMPLES="true|false"}

${VALIDATION_REQUIRED="true|false"}

## Generated Prompt

"Analyze code evolution between two project states to generate precise migration instructions for GitHub Copilot. These instructions will guide Copilot to automatically apply the same transformation patterns during future modifications. Follow this methodology:

Phase 1: Comparative State Analysis

#### Structural Changes Detection

  • Compare folder structure between ${SOURCE_REFERENCE} and ${TARGET_REFERENCE}
  • Identify moved, renamed, or deleted files
  • Analyze changes in configuration files
  • Document new dependencies and removed ones

#### Code Transformation Analysis

${MIGRATION_TYPE == "Framework Version" ?

"- Identify API changes between framework versions

  • Analyze new features being used
  • Document obsolete methods/properties
  • Note syntax or convention changes" : ""}

${MIGRATION_TYPE == "Architecture Refactoring" ?

"- Analyze architectural pattern changes

  • Identify new abstractions introduced
  • Document responsibility reorganization
  • Note changes in data flows" : ""}

${MIGRATION_TYPE == "Technology Migration" ?

"- Analyze replacement of one technology with another

  • Identify functional equivalences
  • Document API and syntax changes
  • Note new dependencies and configurations" : ""}

#### Transformation Pattern Extraction

  • Identify repetitive transformations applied
  • Analyze conversion rules from old to new format
  • Document exceptions and special cases
  • Create before/after correspondence matrix

Phase 2: Migration Instructions Generation

Create a .github/copilot-migration-instructions.md file with this structure:


# GitHub Copilot Migration Instructions

## Migration Context

- **Type**: ${MIGRATION_TYPE}

- **From**: ${SOURCE_REFERENCE}

- **To**: ${TARGET_REFERENCE}

- **Date**: [GENERATION_DATE]

- **Scope**: ${ANALYSIS_SCOPE}

## Automatic Transformation Rules

### 1. Mandatory Transformations

${AUTOMATION_LEVEL != "Conservative" ?
"[AUTOMATIC_TRANSFORMATION_RULES]

- **Old Pattern**: [OLD_CODE]

- **New Pattern**: [NEW_CODE]

- **Trigger**: When to detect this pattern

- **Action**: Transformation to apply automatically" : ""}

### 2. Transformations with Validation

${VALIDATION_REQUIRED == "true" ?
"[TRANSFORMATIONS_WITH_VALIDATION]

- **Detected Pattern**: [DESCRIPTION]

- **Suggested Transformation**: [NEW_APPROACH]

- **Required Validation**: [VALIDATION_CRITERIA]

- **Alternatives**: [ALTERNATIVE_OPTIONS]" : ""}

### 3. API Correspondences

${CHANGE_FOCUS == "API Changes" || MIGRATION_TYPE == "Framework Version" ?
"[API_CORRESPONDENCE_TABLE]

Old API
New API
Notes
Example

[OLD_API]
[NEW_API]
[CHANGES]
[CODE_EXAMPLE]

### 4. New Patterns to Adopt

[DETECTED_EMERGING_PATTERNS]

- **Pattern**: [PATTERN_NAME]

- **Usage**: [WHEN_TO_USE]

- **Implementation**: [HOW_TO_IMPLEMENT]

- **Benefits**: [ADVANTAGES]

### 5. Obsolete Patterns to Avoid

[DETECTED_OBSOLETE_PATTERNS]

- **Obsolete Pattern**: [OLD_PATTERN]

- **Why Avoid**: [REASONS]

- **Alternative**: [NEW_PATTERN]

- **Migration**: [CONVERSION_STEPS]

## File Type Specific Instructions

${GENERATE_EXAMPLES == "true" ?
"### Configuration Files
[CONFIG_TRANSFORMATION_EXAMPLES]

### Main Source Files

[SOURCE_TRANSFORMATION_EXAMPLES]

### Test Files

[TEST_TRANSFORMATION_EXAMPLES]" : ""}

## Validation and Security

### Automatic Control Points

- Verifications to perform after each transformation

- Tests to run to validate changes

- Performance metrics to monitor

- Compatibility checks to perform

### Manual Escalation

Situations requiring human intervention:

- [COMPLEX_CASES_LIST]

- [ARCHITECTURAL_DECISIONS]

- [BUSINESS_IMPACTS]

## Migration Monitoring

### Tracking Metrics

- Percentage of code automatically migrated

- Number of manual validations required

- Error rate of automatic transformations

- Average migration time per file

### Error Reporting

How to report incorrect transformations to Copilot:

- Feedback patterns to improve rules

- Exceptions to document

- Adjustments to make to instructions

Phase 3: Contextual Examples Generation

${GENERATE_EXAMPLES == "true" ?

"#### Transformation Examples

For each identified pattern, generate:

// BEFORE (${SOURCE_REFERENCE})
[OLD_CODE_EXAMPLE]

// AFTER (${TARGET_REFERENCE})
[NEW_CODE_EXAMPLE]

// COPILOT INSTRUCTIONS
When you see this pattern [TRIGGER], transform it to [NEW_PATTERN] following these steps: [STEPS]

Phase 4: Validation and Optimization

#### Instructions Testing

  • Apply instructions on test code
  • Verify transformation consistency
  • Adjust rules based on results
  • Document exceptions and edge cases

#### Iterative Optimization

${AUTOMATION_LEVEL == "Aggressive" ?

"- Refine rules to maximize automation

  • Reduce false positives in detection
  • Improve transformation accuracy
  • Document lessons learned" : ""}

Final Result

Migration instructions that enable GitHub Copilot to:

  • Automatically apply the same transformations during future modifications
  • Maintain consistency with newly adopted conventions
  • Avoid obsolete patterns by automatically proposing alternatives
  • Accelerate future migrations by capitalizing on acquired experience
  • Reduce errors by automating repetitive transformations

These instructions transform Copilot into an intelligent migration assistant, capable of reproducing your technology evolution decisions consistently and reliably.

"

## Typical Use Cases

### Framework Version Migration

Perfect for documenting the transition from Angular 14 to Angular 17, React Class Components to Hooks, or .NET Framework to .NET Core. Automatically identifies breaking changes and generates corresponding transformation rules.

### Technology Stack Evolution

Essential when replacing a technology entirely: jQuery to React, REST to GraphQL, SQL to NoSQL. Creates a comprehensive migration guide with pattern mappings.

### Architecture Refactoring

Ideal for large refactorings like Monolith to Microservices, MVC to Clean Architecture, or Component to Composable architecture. Preserves architectural knowledge for future similar transformations.

### Design Pattern Modernization

Useful for adopting new patterns: Repository Pattern, Dependency Injection, Observer to Reactive Programming. Documents the rationale and implementation differences.

## Unique Benefits

### 🧠 **Artificial Intelligence Enhancement**

Unlike traditional migration documentation, these instructions "train" GitHub Copilot to reproduce your technology evolution decisions automatically during future code modifications.

### 🔄 **Knowledge Capitalization**

Transforms specific project experience into reusable rules, avoiding the loss of migration expertise and accelerating future similar transformations.

### 🎯 **Context-Aware Precision**

Instead of generic advice, generates instructions tailored to your specific codebase, with real before/after examples from your project evolution.

### ⚡ **Automated Consistency**

Ensures that new code additions automatically follow the new conventions, preventing architectural regression and maintaining code evolution coherence.
BrowserAct

Let your agent run on any real-world website

Bypass CAPTCHA & anti-bot for free. Start local, scale to cloud.

Explore BrowserAct Skills →

Stop writing automation&scrapers

Install the CLI. Run your first Skill in 30 seconds. Scale when you're ready.

Start free
free · no credit card