codemod-generator

Generate automated code migration scripts (codemods)

509 stars

Best use case

codemod-generator is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Generate automated code migration scripts (codemods)

Teams using codemod-generator 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

$curl -o ~/.claude/skills/codemod-generator/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/specializations/sdk-platform-development/skills/codemod-generator/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/codemod-generator/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How codemod-generator Compares

Feature / Agentcodemod-generatorStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Generate automated code migration scripts (codemods)

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

# Codemod Generator Skill

## Overview

This skill generates automated code migration scripts (codemods) that transform consumer code to use new API versions, reducing the burden of SDK upgrades on developers.

## Capabilities

- Create AST-based code transformations
- Support multiple languages (JavaScript, TypeScript, Python, Go)
- Provide dry-run mode with change preview
- Implement safe rollback mechanisms
- Generate detailed migration reports
- Handle edge cases and partial migrations
- Support interactive migration modes
- Validate transformations with tests

## Target Processes

- Backward Compatibility Management
- Package Distribution
- SDK Versioning and Release Management

## Integration Points

- jscodeshift for JavaScript/TypeScript
- libcst for Python
- go-codemod for Go
- Rector for PHP
- Custom AST transformers

## Input Requirements

- Source and target API versions
- Transformation rules specification
- Test cases for validation
- Edge case handling requirements
- Rollback strategy

## Output Artifacts

- Codemod scripts per language
- Dry-run reports
- Migration validation tests
- Edge case documentation
- CLI wrapper for execution
- Rollback scripts

## Usage Example

```yaml
skill:
  name: codemod-generator
  context:
    sourceVersion: "1.x"
    targetVersion: "2.0"
    languages:
      - typescript
      - python
    transformations:
      - type: methodRename
        from: oldMethod
        to: newMethod
      - type: parameterChange
        method: createResource
        changes:
          - name: config
            wrap: options
    dryRun: true
    generateTests: true
```

## Best Practices

1. Always provide dry-run mode first
2. Generate comprehensive change reports
3. Handle partial migrations gracefully
4. Include rollback capabilities
5. Test codemods against real codebases
6. Document manual intervention cases

Related Skills

color-palette-generator

509
from a5c-ai/babysitter

Generate accessible color palettes with WCAG compliance

tracing-schema-generator

509
from a5c-ai/babysitter

Generate distributed tracing schemas for OpenTelemetry with Jaeger/Zipkin integration

metrics-schema-generator

509
from a5c-ai/babysitter

Generate metrics schemas for Prometheus, OpenTelemetry, and Grafana dashboards

log-schema-generator

509
from a5c-ai/babysitter

Generate structured logging schemas with correlation ID patterns and ELK/Splunk integration

load-test-generator

509
from a5c-ai/babysitter

Generate load test scripts for k6, Locust, and Gatling from OpenAPI specs

graphql-schema-generator

509
from a5c-ai/babysitter

Generate GraphQL schemas from data models with resolver stubs and federation support

docs-site-generator

509
from a5c-ai/babysitter

Generate documentation sites using Docusaurus, MkDocs, or VuePress

dependency-graph-generator

509
from a5c-ai/babysitter

Generate module dependency graphs with circular dependency detection and coupling metrics

dashboard-generator

509
from a5c-ai/babysitter

Generate monitoring dashboards for Grafana and DataDog with alert integration

c4-diagram-generator

509
from a5c-ai/babysitter

Specialized skill for generating C4 model architecture diagrams. Supports Structurizr DSL, PlantUML, and Mermaid formats with multi-level abstraction (Context, Container, Component, Code).

adr-generator

509
from a5c-ai/babysitter

Specialized skill for generating and managing Architecture Decision Records (ADRs). Supports Nygard, MADR, and custom templates with auto-numbering, linking, and status management.

typespec-sdk-generator

509
from a5c-ai/babysitter

Microsoft TypeSpec-based API and SDK generation