A structural skeleton for managing deterministic, queue-driven AI orchestration and multi-phase state transitions.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install workflow-engine
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install workflow-engine using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Workflow Orchestrator?
The Workflow Orchestrator is a technical framework designed to provide structural parity for queue-driven orchestration within a workflow context. It serves as a foundational component for developers building sophisticated AI agents that require rigorous phase ordering and state management. By utilizing this skill within the Openclaw Skills ecosystem, users can ensure that their agent workflows follow a standardized lifecycle including detection, understanding, derivation, proposal, generation, and validation.
This skill is particularly focused on execution parity and deterministic behavior. It manages runtime context through specific persisted artifacts like derivation manifests and configuration files, allowing for reliable session resumption and handoff. While it operates as a skeleton without external plugin hooks, it emulates critical lifecycle routines to maintain high standards of write-time validation and session capture.
Workflow Orchestrator Use Cases
- Managing large-scale batch processing tasks through structured YAML or JSON queues.
- Orchestrating multi-step AI development workflows that require explicit state transitions.
- Standardizing the handoff process between different AI agents or human-in-the-loop sessions.
- Implementing resumable long-running tasks that persist state across session captures.
- Enforcing validation checklists during the file writing phase to prevent data corruption.
How Workflow Orchestrator Works
- The skill parses incoming arguments to identify the target, batch ID, and specific phase type (e.g., extract, create, or verify).
- It loads the runtime environment by checking for configuration files and derivation manifests within the ops directory.
- The orchestrator searches for a queue file with a specific fallback precedence, starting with ops/queue/queue.yaml.
- It enters the execution phase, strictly following the setup derivation ordering: detection, understanding, derivation, proposal, generation, and validation.
- During execution, it emulates lifecycle routines such as session orientation and write-time validation checklists.
- Upon completion or interruption, it produces deterministic handoff text and persists the current state for future resumability.
Workflow Orchestrator Setup
To integrate the Workflow Orchestrator into your Openclaw Skills setup, follow these steps:
# Navigate to the workflow-engine directory
cd workflow-engine
# Execute the installation script to configure hooks
./install-hooks.sh
You can also manually enable the required lifecycle hooks using the CLI:
openclaw hooks enable session-orient
openclaw hooks enable write-validate
openclaw hooks enable session-capture
Workflow Orchestrator Data Schema & Taxonomy
The skill organizes its operations using a structured directory schema to ensure data integrity and traceability.
| Artifact | Path | Description |
|---|---|---|
| Derivation State | ops/derivation.md | Main file for tracking derivation logic and current phase. |
| Manifest | ops/derivation-manifest.md | Metadata regarding setup artifacts and derivation history. |
| Configuration | ops/config.yaml | Global settings and workflow parameters. |
| Task Queue | ops/queue/queue.yaml | The primary task list (supports .yml and .json extensions). |
| Session Logs | ops/session-capture | Persisted state for resuming interrupted workflows. |
Workflow Orchestrator Advanced Features
- Deterministic phase-gate execution ensuring no step in the lifecycle is bypassed.
- Automated handoff generation for seamless transitions between different Openclaw Skills instances.
- Support for batch-based isolation, allowing multiple orchestration tracks to run concurrently.
- High-fidelity state persistence that enables agents to stop and resume without losing context.
- Strict safety constraints that prevent arbitrary shell execution and unauthorized queue mutations.
SKILL.md
Loading
Related Openclaw Skills
Web Markdown Navigator
A deterministic tool for converting complex webpages into clean, LLM-ready markdown with intelligent fallback mechanisms.
Report Generator
An automated reporting engine designed to transform structured data files into professional, decision-ready executive summaries and visualizations.
Recursive Swarm
A bounded recursive orchestration skill that decomposes massive tasks into manageable, trackable sub-task trees with explicit state management.
OpenRouter Analytics
A comprehensive monitoring tool for tracking OpenRouter API consumption, costs, and request-level diagnostics.
TBOT Controller
A specialized automation interface for the TradingBoat stack that prioritizes DB-first queries and secure lifecycle management.
Venice.ai Supreme Router
A smart model router for Venice.ai that optimizes API costs and privacy by automatically selecting the ideal model tier for any given prompt.
Featured*
