claude-migrate

claude-migrate is a Claude Code configuration skill for AI agents, published by yan-yanko in the rainman repository on GitHub. Skillspace rates claude-migrate D (62/100) and it passed the safety scan; the rating is based on static analysis only.

Audit whether an older repository is "built right for today's Claude," and migrate it — subtractively and safely. Use when a project predates today's conventions (a lean CLAUDE.md, skills, hooks, a web SessionStart setup, MCP) and you want to know what's ready, what's bloated, and what's missing. It first produces a non-mutating READINESS REPORT across every pillar — rules (CLAUDE.md), the verify loop (tests + lint), web/session setup, workflow automation, and recallable history/memory — then a migration plan for one approval. Diagnosis is comprehensive; prescription stays subtractive: it shrinks always-on context (relocating rules/history/automation out of CLAUDE.md into skills/hooks/memory) and recommends ADDING only what the project demonstrably needs — never a bloat checklist. Nothing mutates without approval. Optional rainman lane backfills lost context from git history.

Grade
D
Quality
62 / 100
Safety
Passed
GitHub stars
22

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubyan-yanko/rainman

Our review

Architecture
84 / 100
Maturity
Structured: ships references or scripts
Security scan
Low-risk patterns
License
MIT
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • mentions secrets in text

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Claude Code configuration

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.