Agent skill · Databases

migrate-nanoclaw

Extracts user customizations from a fork, generates a replayable migration guide, and upgrades to upstream by reapplying customizations on a clean base. Replaces merge-based upgrades with intent-based migration.

NanoCo30,389★ · +78/wk · 1 repos on radarProfile →
claude-codeMIT
Install
npx skills add nanocoai/nanoclaw --skill migrate-nanoclaw --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 23 KB
Bundled scripts: none
Path: .claude/skills/migrate-nanoclaw/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 30,426 · +37 this week
Language: TypeScript
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Extracts user customizations from a fork, generates a replayable migration guide, and upgrades to upstream by reapplying customizations on a clean base. Replaces merge-based upgrades with intent-based migration.

How it works

  • The skill describes a two-phase process: Extract and Upgrade. In Extract, it builds a migration guide that captures both the intent and implementation details of user customizations, including code snippets and configurations for non-standard changes. In Upgrade, it checks out a clean upstream worktree and reapplies customizations using the migration guide, avoiding merge conflicts.
  • It uses a worktree workflow, creates a rollback point (backup branch and tag) before touching anything, and treats the migration guide as the source of truth rather than diffs.
  • It avoids touching data directories and focuses only on code changes. It employs sub-agents to explore the codebase, identify customizations, and summarize changes per skill or file.
  • It defines two phases: Extract and Upgrade, with multiple sub-steps for preflight, scope assessment, guide writing, and potential plan formation for complex migrations.

When to use it

  • Use when upgrading Nanoclaw forks where upstream updates are substantial and a merge-based upgrade would cause conflicts due to overlapping changes in core files.
  • Use when user customizations are spread across config values, source files, and integrations, and there is a desire to reapply them deterministically on upstream.
  • Use when a migration guide already exists to decide between updating it or re-extracting; the workflow supports both paths.

What it can touch

  • Code directories only; data directories (groups/, store/, data/, .env) are never touched. The process emphasizes upgrading by reapplying customizations on a clean upstream base via a migration guide.
  • It prescribes absolute-path usage for worktrees and relies on git commands and sub-agents to inspect and summarize changes.

Caveats

  • The workflow requires maintaining a migration guide as the single source of truth and relies on a clean upstream worktree to reapply changes.
  • It may involve creating and managing worktrees, backup branches, and tags before applying migrations.
  • The license for the skill is MIT, and it uses claude-code as a declared tool.
From the SKILL.md

# Context NanoClaw users fork the repo and customize it — changing config values, editing source files, modifying personas, adding skills. When upstream ships updates or refactors, `git merge` produces painful conflicts because the same core files were changed on both sides. This skill extracts the user's customizations into a migration guide — capturing both the intent (what they want) and the implementation details (how they did it, with code snippets, API calls, and specific configurations). On upgrade, it checks out clean upstream in a worktree, then reapplies customizations using the guide. No merge conflicts because there's nothing to merge. The migration guide is markdown, not structured data. It needs to capture the full range of what a user might customize, with enough implementation detail that a fresh Claude session can reapply it without having seen the original code. Standard changes (config values, simple logic) can be described briefly. Non-standard changes (specific APIs, custom integrations, unusual patterns) need code snippets and precise instructions. Two phases: **Extract** (build the migration guide) and **Upgrade** (use it). If a guide already exists, offer to

What's inside
Steps it walks through
  1. 1.0 Preflight
  2. 1.1 Assess scope and determine path
  3. Tier 1: Lightweight — suggest /update-nanoclaw instead
  4. Tier 2: Standard
  5. Tier 3: Complex
  6. 1.2 Update existing guide (if applicable)
  7. 1.3 Explore the codebase
  8. 1.4 Analyze customizations
  9. 1.5 Confirm with user
  10. 1.6 Migration plan (Tier 3 only)
  11. 1.7 Write the migration guide
  12. 2.0 Preflight
  13. 2.1 Safety net
  14. 2.2 Preview upstream changes
Ships with 1 file
  • diagnostics.md
Commands it runs
Divergence stats
git rev-list --count $BASE..upstream/$UPSTREAM_BRANCH  # upstream commits
git rev-list --count $BASE..HEAD                       # user commits
git diff --name-only $BASE..HEAD | wc -l               # user changed files
git diff --stat $BASE..HEAD | tail -1                   # insertions/deletions
git diff --name-only $BASE..upstream/$UPSTREAM_BRANCH | wc -l  # upstream changed files
git add .nanoclaw-migrations/
git commit -m "chore: save migration guide"
git branch backup/pre-migrate-$HASH-$TIMESTAMP
git tag pre-migrate-$HASH-$TIMESTAMP
More from nanoclaw
All skills →
About this skill
What does the migrate-nanoclaw skill do?

Extracts user customizations from a fork, generates a replayable migration guide, and upgrades to upstream by reapplying customizations on a clean base. Replaces merge-based upgrades with intent-based migration.

How do I install it?

Run `npx skills add nanocoai/nanoclaw --skill migrate-nanoclaw --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From nanocoai/nanoclaw, a repository with 30,426 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going