NanoClaw Migration (migrate-nanoclaw)
Extracts your NanoClaw fork's customizations into a replayable migration guide, then upgrades by reapplying them on a clean upstream checkout — no merge conflicts.
Dev & CodingAdvanced★ 30,471⑂ 12,865AI score 8/10Last updated: Aug 9, 2026
What it does
- Scans your NanoClaw fork for everything you changed (config values, source edits, personas, added skills) and writes a replayable migration guide at
.nanoclaw-migrations/guide.md. - Auto-assesses divergence and picks one of three tiers (lightweight / standard / complex), delegating codebase exploration to parallel haiku sub-agents.
- On upgrade it skips
git mergeentirely: it checks out clean upstream in a git worktree, re-runs eachadd-*skill's own apply, then reapplies your customizations from the guide. - Creates a backup branch and tag first, validates with install/build/test plus an optional live message test, then swaps the upgraded tree into main.
- Never touches data paths:
groups/,store/,data/,.env.
Who it's for
- NanoClaw fork maintainers who dread merge conflicts every time upstream refactors core files.
- Anyone who wants their customizations documented so upgrades are repeatable.
- Users who need a safe upgrade workflow with worktree validation, backup tags, and a clear rollback path.
Examples
- "Upgrade my NanoClaw fork to latest upstream" → the skill measures divergence, picks a tier, writes the guide, reapplies in a worktree, and validates the build before swapping.
- A fork with both the Telegram and Slack skills applied: the skill detects a duplicated constant declaration, records it under "Skill Interactions", and tells you how to dedupe after reapplying.
- Simple tweaks like changing the trigger name from
@Andyto@Bobinsrc/config.tsget a one-line instruction, while non-standard work such as a DeepL translation hook is captured with verbatim code snippets and import paths.
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/nanocoai/nanoclaw/HEAD/.claude/skills/migrate-nanoclaw/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the .claude/skills/migrate-nanoclaw folder from the GitHub repo nanocoai/nanoclaw into my ~/.claude/skills/migrate-nanoclaw/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/nanocoai/nanoclaw.git /tmp/nanoclaw && mkdir -p ~/.claude/skills && cp -r /tmp/nanoclaw/.claude/skills/migrate-nanoclaw ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal and clone the NanoClaw repo to a temp folder:
git clone https://github.com/nanocoai/nanoclaw.git /tmp/nanoclaw - Create the skills folder:
mkdir -p ~/.claude/skills - Copy the skill over:
cp -r /tmp/nanoclaw/.claude/skills/migrate-nanoclaw ~/.claude/skills/ - If you already run a NanoClaw fork, prefer the copy inside your repo at
.claude/skills/migrate-nanoclaw/— the skill self-refreshes from upstream when it runs. - In your fork, run
git remote -v; if noupstreamremote exists, add it:git remote add upstream https://github.com/nanocoai/nanoclaw.git - Make sure your working tree is clean (commit or stash), start Claude Code, and ask: "Use migrate-nanoclaw to upgrade my fork to upstream."
- Note the backup tag the skill creates — if anything goes wrong, roll back with
git reset --hard <backup-tag>.
View source on GitHub ↗License: MIT