Best use case
openup-deploy-team is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Deploy an OpenUP agent team to work on the current iteration
Teams using openup-deploy-team should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/openup-deploy-team/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How openup-deploy-team Compares
| Feature / Agent | openup-deploy-team | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Deploy an OpenUP agent team to work on the current iteration
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Deploy Team This skill deploys an OpenUP agent team to work on the current iteration. It reads the iteration context and creates the appropriate team with proper role assignments. ## When to Use Use this skill **after** `/openup-start-iteration` has completed: - Iteration is initialized - Branch is created - Project status is updated - Roadmap has the task Then use this skill to deploy the team. ## When NOT to Use Do NOT use this skill: - Before `/openup-start-iteration` has been called - Without knowing the iteration goal - For non-OpenUP work ## Process ### 1. Read Current Iteration Context Read `docs/project-status.md` to get: - Current phase - Current iteration number - Current iteration goal - Current task (if set) ### 2. Determine Team Composition Based on the iteration goal and team_type: - **feature**: analyst, architect, developer, tester - **investigation**: architect, developer, tester - **construction**: developer, tester (+ architect, analyst as needed) - **elaboration**: architect, developer, tester (+ analyst as needed) - **inception**: analyst, project-manager (+ architect as needed) - **transition**: tester, project-manager, developer (+ analyst as needed) - **planning**: project-manager, analyst (+ architect, developer as needed) - **full**: all roles Or use custom roles from `$ARGUMENTS[roles]` ### 3. Create the Team Spawn teammates using the Task tool with appropriate subagent types. ### 4. Brief the Team Send initial message to all teammates with: - Iteration goal - Current phase - Task context - Expected workflow - Coordination instructions ### 5. Set Up Coordination Ensure the team lead knows to: - Monitor progress - Assign tasks to appropriate roles - Use `/openup-complete-task` when work is done ## Output Returns: - Team composition - Team member assignments - Current iteration context - Expected workflow ## Example Usage ``` /openup-deploy-team team_type: feature ``` Or with specific roles: ``` /openup-deploy-team roles: analyst,developer,tester ``` ## Common Errors | Error | Cause | Solution | |-------|-------|----------| | No iteration found | docs/project-status.md doesn't exist or no active iteration | Run /openup-start-iteration first | | Unknown team type | team_type parameter not recognized | Use one of: feature, investigation, construction, elaboration, inception, transition, planning, full | | Cannot spawn team | Agent teams not enabled | Set CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 | ## See Also - [openup-start-iteration](../openup-start-iteration/SKILL.md) - Initialize iteration first - [openup-complete-task](../openup-complete-task/SKILL.md) - Complete work when done - [Team configurations](../../teams/) - Team definition files
Related Skills
openup-transition
Initialize and manage Transition phase activities - deploy to users
openup-tdd-workflow
Guide Test-Driven Development cycle adapted for AI agents with a pragmatic approach
openup-sync-spec
Back-propagate pure refactors to stale artifacts; classify the diff, refuse behaviour-changes, propose targeted edits for approval (read-only by default)
openup-start-iteration
Begin a new OpenUP iteration with proper phase context and task selection
openup-shared-vision
Create shared technical vision for team alignment
openup-retrospective
Generate iteration retrospective with feedback and action items
openup-request-input
Create an input request document for asynchronous stakeholder communication
openup-readiness
Compute the change-folder dependency DAG and print READY/BLOCKED/collision report for PM intake
openup-quick-task
Fast iteration mode for small changes - simplified workflow with minimal overhead
openup-plan-feature
Generate iteration plan and roadmap entry for a feature idea
openup-phase-review
Check phase completion criteria and prepare for phase review
openup-orchestrate
Run a full orchestrated iteration — PM decomposes the goal, delegates to specialist roles, collects outputs, and synthesizes results