Skip to content
cccskills
FreePublished on GitHub

full-codebase-migrator

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.

The English summary is being prepared. Showing the original description.

OneWave-AI/claude-skills
See how to install

Files included (5)

  • SKILL.md3.3 KB
  • references/ingestion.md4.3 KB
  • references/migration-types.md1.6 KB
  • references/output-template.md6.3 KB
  • references/workflow-detail.md6.5 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

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.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

accessibility-auditor

Free

Audit websites for accessibility issues and WCAG compliance. Use when checking accessibility, fixing a11y issues, or ensuring WCAG compliance.

The English summary is being prepared. Showing the original description.

OneWave-AI/claude-skills354Updated Oct 19, 2026

agent-army

Free

Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus) orchestrates the swarms; the user picks a power level (Max Power / Heavy / Balanced / Economy) that sets the Opus/Sonnet/Haiku model mix per layer. Layer 1 is 3-50+ specialist agents, each with its own full context window; Layer 2 is 2+ sub-agents per member. Includes git safety, tiered sizing, a pre-deploy gate, phantom-completion checks, and multi-wave follow-up.

The English summary is being prepared. Showing the original description.

OneWave-AI/claude-skills354Updated Oct 19, 2026

agent-eval-harness

Free

Use to test whether an AI agent, prompt, or skill actually works before or after it ships — build a small eval set, score runs, and catch regressions when the prompt or model changes. Trigger when the user asks whether a prompt is good, wants to compare models or versions, sees inconsistent agent output, or is about to put an agent in front of customers.

The English summary is being prepared. Showing the original description.

OneWave-AI/claude-skills354Updated Oct 19, 2026

agent-swarm-deployer

Free

Deploys swarms of sub-agents for massive parallel data processing tasks. Unlike agent-army (which is for code changes), this is for DATA tasks -- processing 1000 documents, analyzing datasets, bulk content generation. Configurable swarm size, task distribution, result aggregation, progress tracking, and error recovery.

The English summary is being prepared. Showing the original description.

OneWave-AI/claude-skills354Updated Oct 19, 2026

agent-team-builder

Free

Designs and deploys custom agent teams for specific business workflows. Interactive discovery of business processes, then generates complete team configurations with specialized agent roles, tool access, communication protocols, and handoff rules.

The English summary is being prepared. Showing the original description.

OneWave-AI/claude-skills354Updated Oct 19, 2026

agent-to-agent

Free

Agent-to-Agent (A2A) communication protocol. Connect two or more Claude agents that pass messages, share context, delegate tasks, and collaborate. Implements structured handoffs, shared memory, and multi-agent conversations.

The English summary is being prepared. Showing the original description.

OneWave-AI/claude-skills354Updated Oct 19, 2026

See all skills by OneWave-AI

Report a problem with this skill