Team Tasks
Coordinate multi-agent development pipelines using shared JSON task files. Supports Linear, DAG, and Debate modes for AI agent orchestration across code, test, docs, and monitor agents.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add team-tasks npx -- -y @trustedskills/team-tasks
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"team-tasks": {
"command": "npx",
"args": [
"-y",
"@trustedskills/team-tasks"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The team-tasks skill enables the coordination of multiple AI agents working on a software development pipeline. It uses shared JSON task files to define workflows involving agents responsible for coding, testing, documentation, and monitoring. This allows for orchestration in Linear, Directed Acyclic Graph (DAG), or Debate modes, ensuring tasks are completed in a structured and collaborative manner.
When to use it
- Automated Feature Development: Streamline the creation of new features by having agents handle code generation, unit testing, documentation updates, and performance monitoring sequentially.
- Complex Bug Fixes: Coordinate agents to diagnose issues, implement fixes across multiple files, verify solutions with automated tests, and update relevant documentation.
- Release Preparation: Orchestrate a series of tasks including final code review, security scans, deployment scripts generation, and post-deployment validation using different specialized AI agents.
- Documentation Refresh: Automatically trigger agents to update documentation based on changes made by other agents in the development pipeline.
Key capabilities
- JSON task file definition for workflow configuration
- Linear execution mode
- Directed Acyclic Graph (DAG) execution mode
- Debate execution mode
- Support for code, test, docs, and monitor AI agent types
- Multi-agent orchestration
Example prompts
- "Run the 'release_v1.2' task file in DAG mode."
- "Execute the 'new_feature_x' workflow using linear execution."
- "Start the 'documentation_update' task, prioritizing agents for code changes."
Tips & gotchas
The JSON task files require careful structuring to define dependencies and agent interactions. Ensure all participating AI agents are compatible with the team-tasks skill and understand their assigned roles within the defined workflows.
Requirements
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Installing this skill downloads the exact code at commit c9ef7384, not the current state of the repository. This prevents supply-chain attacks from unauthorized updates.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.
Install command fetches the verified snapshot, not the live repository.