agentleFS
Sign inStart free
tonydzitonydzi/second-brain-starter-kit/skills/migrate/SKILL.md

migrate

Skill6 starsChanged 2 months agoMITView on GitHub

Move or sync the hub role of an agent-plus-vault setup between computers, where an always-on desktop is the hub and laptops are satellites. Checklist with counters verified before and after, and it never migrates silently. Triggers: "/migrate", "/migrate check", "/migrate pack", "/migrate bootstrap".

  • Reads credentials

63 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use incident, sdd and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • JkudjoSkill

    incident

    Production incident response — structured triage, hypothesis tree, safe remediation, incident record

    Also in 4 projects that use this

  • liatrio-labsSkill

    sdd

    Execute the Liatrio Spec-Driven Development (SDD) workflow when explicitly invoked by the user. NOTE: this skill is NOT intended to be dynamically loaded or automatically triggered; it should only ever be explicitly called by the user.

    Also in 4 projects that use this

  • BerryKuipersSkill

    scaffold

    Detect project stack, apply architecture patterns, wire quality gates, and scaffold features. Use when bootstrapping a project, adding a vertical slice, wiring CI/CD, adding Docker compose, or setting up quality gates.

    Also in 4 projects that use this

  • MicrosoftSkill

    init

    Also in 8 projects that use this

  • agenticnotetakingSkill

    upgrade

    Apply plugin knowledge base updates to an existing generated system. Consults the Ars Contexta research graph for methodology improvements, proposes skill upgrades with research justification. Never auto-implements. Triggers on "/upgrade", "upgrade skills", "check for improvements", "update methodology".

    Also in 3 projects that use this

  • genomewalkerSkill

    checkpoint

    Save a checkpoint of task status, decisions, active files, and next steps

    Also in 5 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 50 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All migration .ps1 are ASCII-only (PowerShell 5.1 mangles Cyrillic — [[deterministic-script-gotchas]]).

    line 33

“Common” is measured: kept by at least 6 in 10 of the 50 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/migrate — seamless Claude across Anton's machines

🧒 When reporting to Anton end with a child-simple "In plain words" recap. (memory eli5-always)

This is the single command over the migration project that several sessions already built. It does NOT redesign anything — it reads MIGRATION-PLAN.md + the migration-prep\* scripts and runs the right one. Full state + decisions = memory [[machine-migration]] (READ it first each run — the project is live and moves fast).

The shape (decided, do not re-litigate): always-on Windows DESKTOP = HUB (vault + automation + RAG); this laptop + Mac Studio + MacBook = satellites. Transport: small CONFIG → git/private GitHub; huge live VAULT → Syncthing star (Introducer OFF, .git hub-only). "Seamless" = same vault + same ~/.claude config + same memory on every machine, NOT teleporting the live chat.

Working dir: $USERPROFILE/!CLAUDE-HP17 May26\ · scripts under migration-prep\ · config repo $USERPROFILE/.claude/_config-backup/.

Modes

  • check (default, read-only) — status + drift. Report: is _config-backup fresh (working tree clean vs HEAD; run config_sync.ps1 if skills/memory changed since)? how many Windows scheduled tasks now vs the 16 captured in migration-prep\tasks\*.xml (drift = re-export before a move)? is the F:\ chemodan stale? is gh logged in (offsite optional)? Surface what's BLOCKED.
  • pack — refresh the carry-kit right before an actual move (snapshots go stale): powershell migration-prep\config_sync.ps1 (config+memory → repo) then powershell migration-prep\build_chemodan.ps1 (→ <MIGRATION_DRIVE>\, robocopy COPY-only). Re-export tasks if drifted. ⚠️ confirm with Anton before writing F:\ (it's the seed drive).
  • bootstrap — on a NEW machine: read & execute _config-backup\BOOTSTRAP-NEW-MACHINE.md (ordered A→G) or migration-prep\NEW-SESSION-RUNME.md. New machine user = Anton (%WORKDIR%) → every %USERPROFILE%\ path needs _→Anton; memory encoded-path + task XML absolute paths need the rename too. MANDATORY config-safety step: run powershell "$env:USERPROFILE\.claude\scripts\claude_git_backup_setup.ps1" (idempotent — git-inits the ~/.claude config repos + sets a global git identity) THEN ensure the 15-min "Claude Config Git Snapshot" task exists. Without the init, the snapshot task commits NOTHING (the 2026-06-24 hub near-loss). Canon: [[claude-skills-git-backup]] + [[config-safety-backup-and-migration-check]].
  • connectors — reconnect external MCPs after a move via migration-prep\CONNECTORS-INVENTORY.md. The 3 blind spots the vault+config backup MISSES: <TELEGRAM_MCP_DIR>\ (.env + patched source), $USERPROFILE/.claude/secrets/ (n8n.env + SSH key), $USERPROFILE/.local/share/whatsapp-mcp/. Enumerate from .claude.json mcpServers, not the backup. After reconnecting, verify each server is actually alive & authed with the /mcp skill (its in-session health check — and it carries the Telegram AUTH_KEY_DUPLICATED landmine that bites right after a move: re-auth per machine, never copy .claude.json).
  • sync — Syncthing setup/repair via migration-prep\SETUP-SYNC.md. First-sync order is CRITICAL: laptop is most-current → laptop = Send&Receive, desktop = Receive-Only on first pass to ABSORB, THEN flip. Laptop Device ID is in [[machine-migration]]. Same Syncthing pipe also carries the cross-machine RELAY — Claude-to-Claude messages between machines (folder $OBSIDIAN_VAULT/_machine-bus/); that is the /inbox skill's job, NOT /migrate (rule lives in [[reglament-multi-machine-claude-i-peredacha-mezhdu-mashinami]]).

Hard "never" (safety invariants)

  • NEVER copy $USERPROFILE/.claude.json to another machine (Telegram MCP session) → AUTH_KEY_DUPLICATED logs the account out. Re-auth per machine.
  • NEVER start a 2nd MCP client on the same StringSession (see [[mcp-health-check]]).
  • _originals (3.75 GB) is SACRED — send-only from hub, never delete.
  • All migration .ps1 are ASCII-only (PowerShell 5.1 mangles Cyrillic — [[deterministic-script-gotchas]]).
  • Writes to F:\ / pushing the repo / registering tasks on a new box = pause + confirm (Tier-2, [[operating-agreement]]).

Output

One-liner status + what's fresh/stale/blocked + the exact next command. Then 🧒 recap. Don't duplicate logic that lives in the scripts — point at them.

<!--kit-footer-->

Like this skill? It is one of 100 in second-brain-starter-kit: the second brain we built for ourselves and run every day at Palo Alto AI Research Lab. Install the whole set with npx skills add tonydzi/second-brain-starter-kit. Everything is open source and free, so take what you need.

Flagships worth a look on their own: secondop-panel (a second opinion from a panel of external models), claude-memory-tidy (stop your agent's memory from rotting), telegram-mcp-kit (your own Telegram over MCP in about 15 minutes).

Author: Anton Dziatkovskii, Palo Alto AI Research Lab. Telegram @tonydzi - WhatsApp +1 341 222 9178 - X @Tony_Stef_

Engineers: want to test-drive this setup? Message me. I hand out free starter seeds to engineers who test and report back, and custom skill requests are welcome.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free