teamwork-clean
Reset and clean up teamwork project state. Use when project is stuck, failed, or needs a fresh start. Uses native TeamDelete API for cleanup.
What this skill does
# Teamwork Clean
## Overview
Teamwork-clean resets a project to start fresh by cleaning up team and task state.
### Core Principles
1. **Native API cleanup** - Uses `TeamDelete()` to remove team and all associated tasks
2. **Idempotent operation** - Safe to run multiple times
3. **Clean shutdown** - Sends shutdown messages to active workers before cleanup
### Use Case
When task state becomes inconsistent, workflow fails, or you need to restart execution with the same project configuration.
---
## When to Use
**USE teamwork-clean for:**
- Starting a new run in the same project (multiple attempts at same goal)
- Recovering from failed orchestration or stuck workers
- Cleaning up after testing or experimentation
- Resolving state corruption (stuck tasks, orphaned workers)
**DON'T use teamwork-clean for:**
- Normal project completion (state is valuable)
- Fixing a single task (release the task instead)
- Active projects with workers running (shut down workers first)
---
## Cleanup Process
### Step 1: Shutdown Active Workers
Before cleaning, send shutdown messages to all active teammates:
```python
# Notify all workers to stop
SendMessage(
type="shutdown_request",
recipient="worker-backend",
content="Project cleanup in progress. Please stop."
)
SendMessage(
type="shutdown_request",
recipient="worker-frontend",
content="Project cleanup in progress. Please stop."
)
```
### Step 2: Delete Team
Use the native `TeamDelete` API to remove the team and all associated tasks:
```python
# Delete team (removes all tasks and team state)
TeamDelete()
```
This removes:
- All task definitions and their status
- Task ownership and dependency information
- Team metadata
### Step 3: Recreate (Optional)
If restarting with the same goal, create a new team:
```python
# Create fresh team
TeamCreate(team_name="<team-name>", description="<project goal>")
# Recreate tasks from scratch
TaskCreate(subject="...", description="...")
```
---
## What Gets Cleaned
| Item | Method | Impact |
|------|--------|--------|
| All tasks | `TeamDelete()` | Task definitions, status, evidence, ownership |
| Team state | `TeamDelete()` | Team metadata and configuration |
| Worker associations | `TeamDelete()` | Worker-to-team bindings |
**After cleanup**: The team no longer exists. You start with a blank slate.
---
## What's Preserved
| Item | Why |
|------|-----|
| Project files on disk | Code changes remain in the git repository |
| Git history | All commits from previous run are preserved |
| Project metadata files | Plugin-level `project.json` if used by `project-create.js` |
---
## Usage
### Command Invocation
```bash
/teamwork-clean
```
### Workflow: Clean and Restart
```bash
# 1. Check current status
/teamwork-status
# 2. Clean the project
/teamwork-clean
# 3. Start fresh
/teamwork "same goal or updated goal"
```
### Workflow: After Failed Project
```bash
# Project failed, want to retry with different approach
/teamwork-clean
# Orchestrator will plan from scratch
/teamwork "updated goal with more context"
```
---
## Agent Guidance
### Decision-Making Checklist
Before recommending `/teamwork-clean`, verify:
1. **Is the project stuck?**
- Check task status for stalled tasks (in_progress for too long)
- Check if workers are idle with no available tasks
2. **Are workers stopped?**
- Cleaning while workers are active causes undefined behavior
- Send shutdown messages first, then clean
3. **Is cleanup the right solution?**
- Single stuck task -> Release the task (TaskUpdate with status="open", owner="")
- Want to abandon project entirely -> TeamDelete is sufficient
- Just checking status -> Use `/teamwork-status` only
### When to Recommend Clean
| Situation | Recommend Clean? | Alternative |
|-----------|------------------|-------------|
| First project attempt failed | Yes | Clean and retry |
| Multiple tasks stuck | Yes | Shutdown workers, clean, restart |
| Single task needs retry | No | Release the task |
| Want to change goal | Yes | Clean and start with new goal |
| Checking progress | No | Use `/teamwork-status` |
---
## Related Commands
| Command | Purpose | When to Use |
|---------|---------|-------------|
| `/teamwork` | Start or resume project | After cleaning, to begin fresh execution |
| `/teamwork-status` | Check project progress | Before cleaning, to diagnose issues |
Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.