win4r

Team Tasks — Data skill for Claude Code

Data community

Multi-agent pipeline coordination: Linear, DAG, and Debate modes for AI agent orchestration.

How to install Team Tasks

This entry records only its repository, not the path inside it, so there is no exact command to give. Open win4r/team-tasks and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Team Tasks does

Multi-agent pipeline coordination: Linear, DAG, and Debate modes for AI agent orchestration.

Alternatives in Data

LLM Redteam — LLM red-team corpus runner — fires categorized prompt-injection / jailbreak / system-prompt-leak / data-exfil 4.5k ★
Book Translation Skill — You are a book translation assistant 489 ★
Graph Engineering — Graph engineering for AI agents: the 9-stage knowledge-graph pipeline (translated from SEU's graduate course) 452 ★

README

Team Tasks — Multi-Agent Pipeline Coordination

A Python CLI tool for coordinating multi-agent development workflows through shared JSON task files. Designed for use with [OpenClaw](https://github.com/openclaw/openclaw) and AI agent orchestration systems.

Features

Three coordination modes for different workflows:

Mode	Description	Use Case
Linear	Sequential pipeline with auto-advance	Bug fixes, simple features, step-by-step workflows
DAG	Dependency graph with parallel dispatch	Large features, spec-driven dev, complex dependencies
Debate	Multi-agent position + cross-review	Code reviews, architecture decisions, competing hypotheses

Requirements

Python 3.12+ (stdlib only, no external dependencies)
Data stored as JSON in /home/ubuntu/clawd/data/team-tasks/ (override with TEAM_TASKS_DIR env var)

Installation

# Clone the repo
git clone https://github.com/win4r/team-tasks.git

# No pip install needed — it's a standalone script
python3 team-tasks/scripts/task_manager.py --help

For OpenClaw skill integration, copy to your skills directory:

cp -r team-tasks/ /path/to/clawd/skills/team-tasks/

Quick Start

Mode A: Linear Pipeline

A sequential pipeline where agents execute one after another in order.

TM="python3 scripts/task_manager.py"

# 1. Create project with pipeline order
$TM init my-api -g "Build REST API with tests and docs" \
  -p "code-agent,test-agent,docs-agent,monitor-bot"

# 2. Assign tasks to each stage
$TM assign my-api code-agent "Implement Flask REST API: GET/POST/DELETE /items"
$TM assign my-api test-agent "Write pytest tests, target 90%+ coverage"
$TM assign my-api docs-agent "Write README with API docs and examples"
$TM assign my-api monitor-bot "Security audit and deployment readiness check"

# 3. Check what's next
$TM next my-api
# ▶️  Next stage: code-agent

# 4. Dispatch → work → save result → mark done
$TM upda