workers
- Repo stars 330
- License MIT
- Author updated Live
- Author repo claude-skill-registry
- Domain
- Data
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 94 / 100 · audit passed
- Author / version / license
- @majiayu000 · MIT
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: workers
description: List all active Claude workers and their git worktrees. Shows branch status, commits, and sugges…
category: data
runtime: no special runtime
---
# workers output preview
## PART A: Task fit
- Use case: List all active Claude workers and their git worktrees. Shows branch status, commits, and suggests next actions. Use to see what workers are running. List and manage active Claude workers. runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Usage / Instructions / 1. List Git Worktrees” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “List all active Claude workers and their git worktrees. Shows branch status, commits, and suggests next actions. Use to see what workers are running. List and manage active Claude workers. runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Usage / Instructions / 1. List Git Worktrees” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. The source mentions slash commands such as `/workers`, `/worker-cleanup`, `/worker-pr`, `/worker-continue`; use them first when your agent supports command triggers.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Start with a small task and check whether the result follows “Usage / Instructions / 1. List Git Worktrees”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: workers
description: List all active Claude workers and their git worktrees. Shows branch status, commits, and sugges…
category: data
source: majiayu000/claude-skill-registry
---
# workers
## When to use
- List all active Claude workers and their git worktrees. Shows branch status, commits, and suggests next actions. Use t…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Usage / Instructions / 1. List Git Worktrees” and keep inference separate from source facts.
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "workers" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Usage / Instructions / 1. List Git Worktrees
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
} Workers Skill
List and manage active Claude workers.
Usage
/workers
Instructions
When the user invokes /workers, show the status of all worktrees and workers:
1. List Git Worktrees
git worktree list
2. Show Worker Details
For each worktree (excluding main):
- Branch name and last commit
- Files changed vs main
- Whether it's ahead/behind main
# For each worktree branch
git log <branch> --oneline -1
git diff main...<branch> --stat | tail -1
git rev-list --left-right --count main...<branch>
3. Format Output
Display as a table:
| Worktree | Branch | Last Commit | Changes | Status |
|----------|--------|-------------|---------|--------|
| ../artemis-issue-42 | feat/issue-42-retry | abc123 Add retry | 3 files | +2 ahead |
| ../artemis-feat-logging | feat/add-logging | def456 Add logs | 5 files | +1 ahead |
4. Suggest Actions
Based on status, suggest:
- Workers with commits → "Ready for PR?"
- Stale worktrees (no recent commits) → "Clean up?"
- Workers behind main → "Rebase needed"
5. Quick Actions
Offer shortcuts:
/worker-cleanup <worktree>- Remove a specific worktree/worker-pr <branch>- Create PR from worker branch/worker-continue <worktree> "additional task"- Send more work
Notes
- Only shows worktrees in the parent directory (
../artemis-*) - Main repo worktree is always excluded from the list
- Worktrees can be filtered by status if needed
Decide Fit First
Design Intent
How To Use It
Boundaries And Review