Jiva team-coordination
install
source · Clone the upstream repo
git clone https://github.com/KarmaloopAI/Jiva
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/KarmaloopAI/Jiva "$T" && mkdir -p ~/.claude/skills && cp -r "$T/examples/personas/engineering-manager/skills/coordination" ~/.claude/skills/karmaloopai-jiva-team-coordination && rm -rf "$T"
manifest:
examples/personas/engineering-manager/skills/coordination/SKILL.mdsource content
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:
: For implementation workdeveloper
: For code review and security analysiscode-reviewer
: For test creation and validationtester
- 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
to implement auth logicdeveloper - Spawn
to review securitycode-reviewer - Spawn
to write comprehensive teststester - 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