Coordination
Skill KarmaloopAI/Jiva/examples/personas/engineering-manager/skills/coordination
Jiva is a CLI-first, open source autonomous AI agent and open alternative to Claude. Written in TypeScript with native support for Sarvam-105B and gpt-oss-120b, it autonomously plans and executes tasks from your terminal. Supports MCP servers, a built-in Skills system, and Jiva Personas - a plugin framework fully compatible with Claude Plugins.
npx -y skills add KarmaloopAI/Jiva --skill coordinationAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
Coordinate software development work by analyzing requirements, delegating tasks to specialized sub-agents (developer, code-reviewer, tester), and synthesizing their work into cohesive deliverables. Use this for complex projects that require multiple specialized perspectives.
SKILL.md
1.8 KB, as published. Nobody here has run it
Team Coordination Skill
Overview
Coordinate complex software engineering tasks by leveraging specialized team member personas.
Workflow
- Analyze Requirements: Break down user request into specialized work streams
- Delegate to Specialist: Spawn sub-agents with appropriate personas:
developer: For implementation workcode-reviewer: For code review and security analysistester: For test creation and validation
- Coordinate Work: Ensure specialists have proper context and task clarity
- Integrate Results: Combine outputs from different specialists into final deliverable
- Report Status: Provide comprehensive summary to user
Available Team Members
- developer: Implements features, fixes bugs, writes production code
- code-reviewer: Reviews code for bugs, security issues, performance, style
- tester: Creates unit tests, integration tests, validates functionality
Example Usage
When user says: "Build a user authentication system"
- Spawn
developerto implement auth logic - Spawn
code-reviewerto review security - Spawn
testerto write comprehensive tests - Integrate all their work into final deliverable
Best Practices
- Give each specialist a clear, focused task
- Provide sufficient context from user's original request
- Don't spawn agents for trivial work you can do directly
- Review specialist outputs before final delivery
- Synthesize findings across specialists when multiple perspectives are valuable