Skip to content
Get packs

Workflow threads manager

Oversee parallel Claude sessions on one repo: check merges, changelog pictures, live site, and archive finished threads.

Source Download skill
Repository
MengTo/Skills
Stars
7,187
Licence
MIT
Files
6 files

What it does

It lets an AI agent act as a supervisor for several other AI chat sessions working on the same code project. When asked, it checks which of those sessions have merged their work into the main branch, whether each change has its changelog entry and screenshots, and whether the live site still loads. It can then archive sessions that are truly finished, or flag ones that were cut off mid-task, after saving their screenshots first.

Great for

  • Developers who run many Claude sessions in parallel on one repository and lose track of what each one shipped
  • Small teams with a game or web project that keeps an in-app changelog with screenshots

Skip it if

  • Single-session projects, since there are no other threads to oversee
  • Anyone wanting unattended deploys: the skill says it never publishes, deploys or rolls back live, but it does run shell and Python scripts and archiving deletes worktrees, so review its actions before approving them

Try asking

  • “check threads”
  • “are the threads merged and pushed?”
  • “archive the done threads”
  • “check new changes and send me a contact sheet of what shipped”
Step-by-step guide: how to use Workflow threads managerInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 6 original files, the MIT licence and an attribution note.

    workflow-threads-manager.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip workflow-threads-manager.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip workflow-threads-manager.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Put project specifics such as changelog format, live URL and capture folders in a local references file so the skill stays generic
  • Say explicitly when you want finished threads archived; the skill only archives after that permission

What's inside

  • scripts/audit-changelog.py
  • scripts/contact-sheet.py
  • scripts/live-check.sh
  • scripts/repo-status.sh
  • scripts/save-captures.sh
  • SKILL.md

Redistributed unmodified from MengTo/Skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.