agentic-orchestrating
Provides the "how-to" for workflow / task execution orchestration. Defines methods for planning multi-phase task/workflows, implementing them through agent delegation, and managing artifacts.
When & Why to Use This Skill
This Claude skill provides a professional framework for orchestrating complex, multi-phase agentic workflows. It standardizes the entire lifecycle of task execution—from initial planning and agent delegation to artifact management and workflow resumption—ensuring high-quality, scalable results through structured folder systems and progressive context disclosure.
Use Cases
- Complex Task Planning: Breaking down ambiguous, high-level objectives into structured, multi-phase execution plans with clearly defined outputs (PLAN.md).
- Efficient Agent Delegation: Implementing a 'pass file paths, not content' strategy to maintain high signal-to-noise ratios and focused context during agent handoffs.
- Standardizing Business Processes: Converting plain-English SOPs into executable blueprints (EXECUTE.md) for repeatable marketing, research, or technical workflows.
- Workflow Resumption: Restarting interrupted or failed long-running tasks from specific phases without losing previous progress, allowing for selective regeneration of artifacts.
- Structured Knowledge Management: Organizing multi-agent outputs into a standardized folder hierarchy (data, artifacts, plans) for better auditability and data flow.
| name | agentic-orchestrating |
|---|---|
| description | Provides the "how-to" for workflow / task execution orchestration. Defines methods for planning multi-phase task/workflows, implementing them through agent delegation, and managing artifacts. |
Workflow Orchestration
Knowledge base for orchestrating multi-phase workflow executions with standardized folder structures and agent delegation.
Core Concepts
This skill embodies seven key orchestration principles:
- Planning - HOW to create execution plans with phase breakdown and artifact definition
- Implementation - HOW to execute plans through agent delegation and artifact management
- Executing - HOW to run pre-defined workflows using EXECUTE.md blueprints
- Workflow to Execute - HOW to convert plain-English WORKFLOW.md into structured EXECUTE.md
- Resuming - HOW to restart workflows from specific phases with selective regeneration
- Delegation - HOW to maintain focused context through strategic agent handoffs
- Artifacts - HOW to standardize outputs that flow between phases
Progressive Disclosure
A core architectural principle that emerges from delegation: pass file paths, not content. This enables agents to load context when needed, maintaining high signal-to-noise ratio. Instead of inlining everything upfront, each agent reads only the files it needs for its specific task.
Standard Execution Folder
All task/workflow executions follow this structure:
/{base-dir}/{task/workflow-name}/{YYYY-MM-DD_HH:MM}/
├── data/ # Input files (optional)
├── artifacts/ # Phase outputs
│ ├── 01-*.md
│ ├── 02a-*.md
│ ├── 02b-*.md
│ └── 03-*.md
├── PLAN.md # Initial plan
└── RESEARCH.md/STRATEGY.md/CONTENT.md # Final output
Where base-dir is either research, strategy or content.
See Artifacts for naming conventions and folder structure details.
Orchestration Workflows
Custom Task Execution (Planning → Implementation)
For one-off, custom tasks that require bespoke execution plans:
Planning Phase
Purpose: Create a structured execution plan
Inputs:
- Task description or workflow definition
- User requirements and context
Process: See Planning
Outputs:
- Execution folder structure
- PLAN.md with phase breakdown
- Expected artifact definitions
Implementation Phase
Purpose: Execute the plan through agent delegation
Inputs:
- PLAN.md from execution folder
- data/ (optional, created in planning phase)
Process: See Implementation
Outputs:
- Phase artifacts in execution folder
- Final RESEARCH.md/STRATEGY.md/CONTENT.md
Standardized Workflow Execution
For repeatable, standardized workflows defined by Marketing Architects:
Workflow Conversion (One-time Setup)
Purpose: Convert plain-English WORKFLOW.md into structured EXECUTE.md
Inputs:
- WORKFLOW.md from skill folder
- Understanding of agent types and capabilities
Process: See Workflow to Execute
Outputs:
- EXECUTE.md in same folder as WORKFLOW.md
- Ready for repeated execution via
/executecommand
Execution Phase
Purpose: Run pre-defined workflow using EXECUTE.md blueprint
Inputs:
- EXECUTE.md from skill workflow folder
- User inputs (slug, topic, context)
- data/ (optional, if EXECUTE.md specifies)
Process: See Executing
Outputs:
- Execution folder in appropriate location
- Phase artifacts
- Final RESEARCH.md/STRATEGY.md/CONTENT.md
Resumption Phase
Purpose: Restart execution from specific phase with selective regeneration
Inputs:
- Existing execution folder with PLAN.md (or EXECUTE.md)
- User specification of resume point
- Existing artifacts/ (some preserved, some regenerated)
Process: See Resuming
Outputs:
- Regenerated artifacts from resume point forward
- Preserved artifacts from before resume point
- Updated final output
Tools and Resources
Scripts
scripts/create_execution_folder.py- Creates timestamped execution folders
Templates
assets/PLAN_EXECUTE_template.md- Plan/Execute blueprint template