Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.
git clone https://github.com/rohitg00/pro-workflow.git--- name: orchestrate description: Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases. user-invocable: true --- # Orchestrate - Multi-Phase Feature Development Build features through structured phases with validation gates. ## The Pattern ```text /develop <feature> │ ├── Phase 1: Research (orchestrator agent) │ └── Score confidence → GO/HOLD │ ├── Phase 2: Plan (orchestrator agent) │ └── Present plan → wait for approval │ ├── Phase 3: Implement (orchestrator agent) │ └── Execute plan → quality gates │ └── Phase 4: Review (reviewer agent) └── Code review → commit ``` ## Usage When asked to build a feature: 1. **Start with research**: Delegate to the orchestrator agent or scout agent to explore the codebase 2. **Wait for GO/HOLD**: Don't proceed if confidence is below 70 3. **Present a plan**: List all files to change, the approach, and risks 4. **Get approval**: Never implement without explicit "proceed" 5. **Implement step by step**: Quality gates every 5 edits 6. **Review before commit**: Run the reviewer agent on changes ## When to Use This - Feature touches >5 files - Architecture decisions needed - Requirements are unclear or complex - Cross-cutting concerns (auth, logging, error handling) - New patterns not yet established in the codebase ## When NOT to Use This - Quick bug fixes (just fix it) - Single-file changes - Well-understood patterns (follow existing code) - Documentation-only changes ## Agent Selection | Phase | Agent | Why | |-------|-------|-----| | Research | scout (background, worktree) | Non-blocking exploration | | Plan | orchestrator (opus, memory) | Deep reasoning, pattern recall | | Implement | orchestrator (opus, memory) | Full tool access | | Review | reviewer (read + bash) | Security and quality focus | | Debug | debugger (opus, memory) | Systematic investigation | ## Integration with Pro-Workflow - Corrections during implementation trigger self-correction loop - Quality gates fire at checkpoints via hooks - Learnings are captured at the end of each phase - Session handoff works across phases
[{"step":"Define the feature and its scope","action":"Clearly describe [FEATURE_NAME] and its objectives. Break down the workflow into logical phases (e.g., research, planning, implementation).","tip":"Use the SMART criteria (Specific, Measurable, Achievable, Relevant, Time-bound) to define success for each phase."},{"step":"Identify agents and tools","action":"List the agents or tools required for each task. Specify their roles, dependencies, and success criteria.","tip":"Prioritize agents/tools based on their ability to directly impact the feature's success. For example, a UX designer is critical for UI-related features."},{"step":"Set up dependencies and fallback plans","action":"Document dependencies between tasks and agents. Define fallback options for high-risk tasks to ensure continuity.","tip":"Use a Gantt chart or project management tool (e.g., Trello, Asana) to visualize dependencies and timelines."},{"step":"Execute and monitor","action":"Run the workflow phase-by-phase, monitoring progress against success criteria. Adjust timelines or tasks as needed based on real-time feedback.","tip":"Use a shared dashboard (e.g., Notion, Airtable) to track progress and flag issues early."},{"step":"Review and iterate","action":"After implementation, review the results against the success criteria. Identify lessons learned and iterate on the workflow for future features.","tip":"Conduct a retrospective meeting with all agents to discuss what worked and what didn’t."}]
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/rohitg00/pro-workflow/tree/main/skills/orchestrateCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Act as an orchestrator to design and execute a multi-phase workflow for [FEATURE_NAME]. Break this into three phases: 1) Research and planning: [RESEARCH_TASKS], 2) Agent coordination: [AGENT_TASKS], and 3) Implementation: [IMPLEMENTATION_TASKS]. Provide a step-by-step execution plan, including dependencies, success criteria, and fallback options for each phase. Use tools like [TOOL_1], [TOOL_2], or [TOOL_3] where applicable.
Feature Name: Automated Customer Onboarding Portal **Phase 1: Research and Planning** - Task: Analyze customer onboarding pain points in [COMPANY_X]'s current process. - Deliverable: A report identifying 5 key friction points (e.g., 37% of users drop off during step 3 due to unclear instructions). - Tools: Use Notion for documentation and Google Analytics for user behavior data. - Success Criteria: Documented pain points with supporting data and proposed solutions. **Phase 2: Agent Coordination** - Task: Assign agents to address each pain point: - Agent A (UX Designer): Redesign step 3 of the onboarding flow. - Agent B (Content Strategist): Create interactive tutorials for unclear instructions. - Agent C (Developer): Integrate a progress tracker with CRM. - Dependencies: Agent A's redesign must be approved before Agent B's content is finalized. - Fallback: If Agent A misses deadline, Agent B will create a simplified static guide as a temporary fix. **Phase 3: Implementation** - Task: Deploy the redesigned onboarding portal in stages: - Week 1: Launch progress tracker and CRM integration. - Week 2: Roll out new step 3 design to 50% of users (A/B test). - Week 3: Deploy interactive tutorials to the remaining 50% of users. - Success Criteria: 20% reduction in onboarding drop-off rate and 15% increase in customer satisfaction (measured via post-onboarding surveys). **Risk Mitigation** - If the A/B test shows no improvement, revert to the original design and investigate further with user interviews. - If Agent B's content is delayed, use pre-recorded video walkthroughs as a stopgap.
skills-collection
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan