full-codebase-migrator — Claude Code skill: migration plans
The full-codebase-migrator skill examines a whole repository and turns it into a file-level migration plan. Use it for JS-to-TS work, React class conversion, or framework changes.
MIT 251 installs ★ 440 updated 2026-10-20
npx skills add OneWave-AI/claude-skills --skill full-codebase-migrator -a claude-codeWhat full-codebase-migrator does
full-codebase-migrator collects source files, project structure, configuration, package manifests, and Git metadata. It then maps imports into a dependency graph, groups files into layers, detects cycles, and reviews each file for migration work.
The main deliverable is migration-plan.md, covering the file inventory, dependency order, per-file changes, risk assessment, effort estimates, and rollback planning. It can also write migration-plan.json when a machine-readable result is useful. The skill relies on Read, Glob, Grep, Write, Bash, and Agent.
For repositories with 500+ files, directory subtrees can be read through sub-agents. The workflow also accounts for monorepos, partially migrated projects, and codebases without tests. Effort estimates include a 20% buffer.
What it helps with
- plan a JavaScript-to-TypeScript migration
- convert React class components into hooks in stages
- order file changes around dependency relationships
- score migration risks and estimate effort
- produce a machine-readable
migration-plan.json
Example prompts for the agent
- Review this repository and create a JavaScript-to-TypeScript migration plan.
- Map the React class components, then plan their conversion to hooks by file.
- Analyze
srcand write the result tomigration-plan.md.
How to install full-codebase-migrator
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill full-codebase-migrator -a claude-code2Manually: put the files in place
~/.claude/skills/full-codebase-migrator/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/full-codebase-migrator/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill full-codebase-migrator -a codex2Manually: put the files in place
.agents/skills/full-codebase-migrator/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill full-codebase-migrator -a cursor2Manually: put the files in place
.cursor/skills/full-codebase-migrator/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install OneWave-AI/claude-skills full-codebase-migrator2Manually: put the files in place
.github/skills/full-codebase-migrator/SKILL.md1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill full-codebase-migrator -a gemini-cli2Platform CLI
gemini skills install https://github.com/OneWave-AI/claude-skills --path full-codebase-migratorManually: put the files in place
.devin/skills/full-codebase-migrator/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill full-codebase-migrator -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about full-codebase-migrator
How do I install full-codebase-migrator in Claude Code?
Run npx skills add OneWave-AI/claude-skills --skill full-codebase-migrator -a claude-code, then check ~/.claude/skills/full-codebase-migrator/SKILL.md.
What does full-codebase-migrator do?
It reads a codebase, maps its dependencies, and creates a staged migration plan with file-level changes, risks, effort estimates, and rollback planning.
How does full-codebase-migrator handle large repositories?
With 500+ files, it can assign directory subtrees to sub-agents for reading. Very large codebases use adjusted handling.
Source text
SKILL.md · MIT
--- name: full-codebase-migrator description: Uses 1M context window to ingest an entire codebase and output a file-by-file migration plan. Supports JS to TS, React class to hooks, framework migrations, and more. Generates migration-plan.md with file inventory, dependency graph, migration order, file-by-file changes, estimated effort, and risk assessment. tools: Read, Glob, Grep, Write, Bash, Agent user_invocable: true --- # Full Codebase Migrator Leverage the full 1M token context window to ingest an entire codebase, understand its architecture end-to-end, and produce a comprehensive, file-by-file migration plan that a team can execute sequentially without conflicts. ## Contents - `references/migration-types.md` -- supported migration types; when to use and when not to use this skill. - `references/ingestion.md` -- architecture, glob patterns, metadata collection, read order, context budgeting, and dependency graph construction (Steps 0-2). - `references/workflow-detail.md` -- per-file assessment, migration order, risk scoring, and effort estimation templates (Steps 3-6). - `references/output-template.md` -- migration-plan.md and migration-plan.json templates, edge cases, and the final quality checklist (Steps 7-8). ## Workflow 1. Identify scope. Determine migration type, scope (full repo or directory), output location for migration-plan.md, and any exclusions or constraints. Infer from the user's prompt when already specified. See `references/migration-types.md` for supported types and fit. 2. Ingest the codebase. Glob all source files, collect metadata with Bash (line counts, package manifest, configs, git history, directory tree), then Read every source file. For 500+ file codebases, dispatch Agent sub-agents to read directory subtrees in parallel. See `references/ingestion.md`. 3. Build the dependency graph. Extract every import, build an adjacency list, classify each file into layers, detect circular dependencies, and classify external dependencies. See `references/ingestion.md`. 4. Assess each file. Produce a per-file migration assessment covering layer, complexity, patterns found, required changes, prerequisite dependencies, risk factors, and testing impact. See `references/workflow-detail.md`. 5. Calculate migration order. Run a topological sort by layer, apply practical adjustments (quick wins, high-risk-early, break cycles first), and group files into buildable, PR-sized phases. See `references/workflow-detail.md`. 6. Assess risk. Score each file 1-5 on complexity, centrality, volatility, test coverage, and external coupling. Build the migration-level risk matrix and rollback strategy. See `references/workflow-detail.md`. 7. Estimate effort. Derive per-file, per-phase, and total estimates with overhead and a 20% buffer, then translate into calendar time by team size. See `references/workflow-detail.md` and the effort calibration table in `references/migration-types.md`. 8. Generate the deliverable. Write migration-plan.md to the output location, and migration-plan.json when machine-readability helps. Verify against the quality checklist before delivering. See `references/output-template.md`. ## Edge Cases Codebases too large for context, monorepos, partially migrated codebases, and codebases without tests each need adjusted handling. See `references/output-template.md`.
© OneWave-AI · MIT · OneWave-AI/claude-skills