Sync Workspace logo

Sync Workspace

Community
paulinevos
sync-workspace

Recover a stale, divergent, or conflicted Jujutsu workspace, or rebase a slice onto a moved base or parent. Use for stale-working-copy errors, divergent change IDs, or conflicted bookmarks.

Overview

Publisherpaulinevos
Repositoryclaude-stuff
Skill namesync-workspace
Stars
64
Forks
0
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by paulinevos on GitHub. Read the source before you install it.

Installation

Install the Sync Workspace AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/paulinevos/claude-stuff/tree/main/plugins/jj-workflow/skills/sync-workspace
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/paulinevos/claude-stuff.git /tmp/claude-stuff
mkdir -p .claude/skills
cp -r /tmp/claude-stuff/plugins/jj-workflow/skills/sync-workspace .claude/skills/sync-workspace
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sync Workspace in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Sync Workspace on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Sync Workspace is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

sync-workspace

Identify the symptom before acting.

SymptomRecovery
Stale working copyjj workspace update-stale, then jj status. If @ is divergent and edits disappeared, handle it below.
Base or parent movedjj git fetch && jj rebase -b <slice> -o <base>; check jj log -r 'conflicts() & (<base>..@)'. Rebase only your slice.
Divergent change/0, change/1Inspect versions; combine with jj squash --from <other-commit-id> --into @, abandon the unwanted version, or preserve both with jj metaedit --update-change-id <commit-id>. Verify jj log -r @ and jj status.
Bookmark name??Inspect jj bookmark list <name>, rebase wanted work together if necessary, then jj bookmark move <name> --to <change-id>; fetch for a remote conflict.
Divergence you cannot rewriteThe versions are immutable. See below.

update-stale snapshots first. Unsnapshotted edits during an ancestor rewrite become a divergent change and leave the working copy. jj merges racing operations rather than locking; one owner per workspace, bookmark, and change prevents these states.

Divergence in immutable history

jj squash and jj abandon need mutable revisions, so neither applies once the divergent versions are published. Never reach for --ignore-immutable; diagnose instead, because the cause decides the fix:

sh
jj log -r 'divergent()' --no-graph -T 'commit_id.short() ++ " imm=" ++ if(immutable,"Y","n") ++ " [" ++ bookmarks ++ "]\n"'
jj diff --from <one-commit-id> --to <other-commit-id> --stat   # empty = duplicates
jj log -r '<bookmark> ~ ::main'                                # empty = nothing unique

Both empty means a stale bookmark — typically a merged pull request whose branch the forge kept, holding pre-rebase copies of revisions now in main. Nothing is lost; the bookmark is only keeping the old copies visible. Deleting it changes a shared remote, so confirm with the user first. A remote bookmark with no local counterpart must be tracked before the deletion can propagate:

sh
jj bookmark track <bookmark>@origin
jj bookmark delete <bookmark>      # `forget` drops jj's record only; the next fetch undoes it
jj git push --deleted
jj git fetch

If instead both versions are reachable from main (divergent() & ::main), two published commits share a change ID. Leave them and refer to them by commit ID.

Frequently asked questions

What does the Sync Workspace AI skill do?

Recover a stale, divergent, or conflicted Jujutsu workspace, or rebase a slice onto a moved base or parent. Use for stale-working-copy errors, divergent change IDs, or conflicted bookmarks.

Why use Sync Workspace on TypingMind?

Because you install it once and use it with any model. Sync Workspace is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Sync Workspace in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/paulinevos/claude-stuff/tree/main/plugins/jj-workflow/skills/sync-workspace. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Sync Workspace?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Sync Workspace?

As many as you like. As long as a model supports skills, you can use Sync Workspace with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Sync Workspace AI skill free?

Yes. It is published on GitHub by paulinevos under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇