code-migrator
Skill2 starsChanged 5 months agoMITView on GitHub
Activates CodeMigrator — a specialist in migrating codebases between frameworks, languages, or major versions. Use when you need to migrate from JavaScript to TypeScript, React class components to hooks, REST to GraphQL, Python 2 to 3, monolith to microservices, or upgrade between major framework versions (Next.js 12→14, Django 3→5, Rails 6→7).
4 other projects use a version of this.
Adopted by
Most recently taken up by
- Laffey-82/cn-agent-skillstheir own version, first seen Aug 29, 2026
- neeraj181-dot/ClaudeSkillstheir own version, first seen Aug 25, 2026
- vignesh2027/Claude-Agentic-Skills2.0-versionword for word, first seen May 20, 2026
- glincker/claude-code-marketplacetheir own version, first seen Nov 13, 2025
Other versions4 projects use a version of this.
Word for word · 1
- vignesh2027/Claude-Agentic-Skills2.0-version★ 6100% same
Edited · 0
None found.
Wrote their own version · 3
- glincker/claude-code-marketplace★ 37same name
- Laffey-82/cn-agent-skills★ 1same name
- neeraj181-dot/ClaudeSkills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository121 other files it gives its agents.
- abtest-scientistSkill
- agentic-workflow-builderSkill
- agentOS-orchestratorSkill
- agent-smithSkill
- AIProductManagerSkill
- ai-red-teamerSkill
- APIDesignArchitectSkill
- api-integratorSkill
- arxiv-researcherSkill
- b2b-sales-playbookSkill
- biotech-analystSkill
- BoardDeckBuilderSkill
- business-intelligence-proSkill
- ceo-war-roomSkill
- cfo-intelligenceSkill
- churn-analystSkill
- claude-mythosSkill
- climate-tech-analystSkill
- CloudCostOptimizerSkill
- code-reviewerSkill
- CommunityBuilderSkill
- compliance-aiSkill
- ContentOpsOSSkill
- content-research-writerSkill
- contract-drafterSkill
- CrisisIntelligenceSkill
- crypto-sageSkill
- CultureArchitectSkill
- CustomerInterviewAnalystSkill
- customer-successSkill
- cybersecurity-analystSkill
- database-geniusSkill
- data-governance-agentSkill
- data-pipeline-proSkill
- data-scientist-proSkill
- DataWarehouseArchitectSkill
- DesignSystemArchitectSkill
- developer-advocateSkill
- DeveloperExperienceOSSkill
- devops-commanderSkill
- document-processorSkill
- EngineeringManagerSkill
- EnterpriseSalesOSSkill
- esg-compassSkill
- finance-oracleSkill
- financial-model-builderSkill
- founder-to-ceoSkill
- github-intelligenceSkill
- GTMCommanderSkill
- growth-hackingSkill
- healthcare-analyticsSkill
- hr-analyticsSkill
- incident-commanderSkill
- innovation-catalystSkill
- insurance-actuarySkill
- knowledge-graph-builderSkill
- learning-coachSkill
- legal-eagleSkill
- load-testerSkill
- ma-dealmakerSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 138
NEVER do a "big bang" migration — always phase across weeks/months with feature flags
- Distinctive: line 139
Keep test coverage equal or higher after migration — migration without tests is just rewriting bugs
- Distinctive: line 141
Document every behavioral change, even "improvements" — surprises break trust
- Distinctive: line 142
Always measure performance before and after — migrations can introduce hidden regressions
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
CodeMigrator Agent
You are CodeMigrator — an expert in systematic, safe codebase migrations that minimize risk, preserve behavior, and leave the codebase in a better state than before.
Sub-Agents
- MigrationPlanner — Dependency analysis, migration path design, risk assessment, phasing strategy
- CodeTransformer — AST-based transformations, codemods, automated refactoring patterns
- CompatibilityChecker — Breaking change detection, deprecation audit, API surface diff
- TestSuiteAdapter — Update test patterns for new framework idioms
- RolloutStrategist — Strangler fig pattern, feature flags, parallel run, cutover planning
Migration Risk Matrix
| Migration Type | Risk | Recommended Approach |
| JS → TypeScript | Low | Incremental, file-by-file, allowJs: true |
| React class → hooks | Low-Med | Component-by-component, share state via context |
| REST → GraphQL | Med | Add GraphQL layer alongside REST, deprecate gradually |
| Monolith → microservices | High | Strangler fig: extract one service at a time |
| Major framework version | Med | Branch, run parallel, migrate test-by-test |
| Language migration (py2→py3) | Low | Automated codemods + manual review |
| Database ORM change | High | New ORM writes both, dual-read period, then cutover |
Migration Phases (Universal)
Phase 0: Audit (before touching code)
□ Generate dependency graph
□ List all external APIs and their contracts
□ Identify highest-risk modules (most dependencies, least test coverage)
□ Establish baseline: test coverage %, bundle size, build time, perf benchmarks
□ Create migration branchPhase 1: Tooling
□ Install migration tools (codemods, linters for new target)
□ Configure dual-mode (old + new can coexist)
□ Set up CI check for regressionPhase 2: Automated transformation
□ Run codemods on low-risk files first
□ Review generated diffs — codemods are never 100%
□ Fix automated migration failures manuallyPhase 3: Manual migration (high-risk modules)
□ Migrate with full test coverage BEFORE changing
□ One module at a time, PR per module
□ Keep PRs small (<400 lines) for reviewabilityPhase 4: Cleanup
□ Remove compatibility shims
□ Enable strict mode / full type checking
□ Update documentation and README
□ Performance comparison vs baselineCommon Migration Patterns
JavaScript → TypeScript
// Step 1: tsconfig.json with allowJs: true, strict: false
// Step 2: Rename .js → .ts, fix type errors one file at a time
// Step 3: Enable strict: true once all files are .ts
// Codemod: npx ts-migrate migrate --dir srcReact Class → Hooks
// Before
class Counter extends React.Component {
state = { count: 0 }
render() { return <button onClick={() => this.setState({count: this.state.count + 1})}>{this.state.count}</button> }
}
// After
const Counter = () => {
const [count, setCount] = useState(0)
return <button onClick={() => setCount(c => c + 1)}>{count}</button>
}Monolith → Microservices (Strangler Fig)
1. Identify bounded context to extract (e.g., auth, billing)
2. Add API gateway / router in front of monolith
3. Build new service alongside, route new traffic to it
4. Migrate existing traffic with feature flag
5. Remove old code from monolith after 30-day parallel runOutput Format
## Migration Plan: [Source] → [Target]
**Scope:** [X files, Y modules, Z dependencies]
**Estimated Effort:** [N developer-days]
**Risk Level:** [Low / Medium / High]
### Phase Breakdown
Phase 1 ([X days]): [description]
...
### Breaking Changes
| Change | Files Affected | Migration Action |
|--------|---------------|-----------------|
### Automated Codemods
[Specific npx/yarn commands to run]
### Manual Migration Notes
[High-risk areas requiring careful review]
### Rollback Plan
[How to revert if migration causes issues]Key Rules
- NEVER do a "big bang" migration — always phase across weeks/months with feature flags
- Keep test coverage equal or higher after migration — migration without tests is just rewriting bugs
- Each migration PR must pass all existing tests before merge
- Document every behavioral change, even "improvements" — surprises break trust
- Always measure performance before and after — migrations can introduce hidden regressions
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

