A deterministic coordination engine that manages autonomous planning, multi-agent delegation, and result verification for complex development tasks.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install joko-orchestrator
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 joko-orchestrator 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 Autonomous Skill Orchestrator?
The Autonomous Skill Orchestrator is a advanced framework designed to solve the challenges of context overload and cognitive drift in AI development. By implementing a three-layer architecture inspired by established orchestration patterns, it transforms standard AI interactions into a systematic process of planning, conducting, and executing. This skill allows users to leverage the full power of Openclaw Skills by delegating tasks to specialized sub-agents while maintaining a central conductor that ensures quality and adherence to project guardrails.
At its core, the orchestrator functions as a project manager, dividing large objectives into granular tasks with specific acceptance criteria. It maintains a continuous wisdom log, ensuring that insights gained during one phase of the project are immediately available to sub-agents in subsequent phases. This approach effectively removes the human bottleneck, allowing for parallel processing and relentless execution until the project goals are fully met.
Autonomous Skill Orchestrator Use Cases
- Large-scale codebase refactoring requiring systematic verification across multiple modules.
- Building complex new features from scratch while adhering to existing architectural patterns.
- Automated debugging and fixing of deep-seated issues that require reproduction and testing.
- High-breadth research and documentation tasks spanning various files and external references.
- Parallelizing independent development tasks to drastically reduce project completion time.
How Autonomous Skill Orchestrator Works
- Discovery Interview: The skill initiates a brief interview to clarify objectives, boundaries, and completion criteria.
- Structured Planning: A detailed work plan is generated, categorizing tasks by complexity and defining explicit guardrails.
- Plan Validation: A self-review phase (Momus Mode) ensures all tasks are concrete and dependencies are explicitly mapped.
- Task Delegation: The Atlas conductor spawns sub-agents for specific tasks, using appropriate model hints based on task type (e.g., deep, quick, creative).
- Wisdom Accumulation: Learnings, discovered patterns, and successful commands are logged in real-time to guide future sub-agents.
- Independent Verification: The orchestrator personally verifies all sub-agent output against acceptance criteria, refusing to trust claims blindly.
- Final Reporting: A comprehensive summary is produced, documenting changes, learnings, and recommended next steps.
Autonomous Skill Orchestrator Setup
To activate this skill within the Openclaw Skills environment, you can use explicit triggers or the magic keyword mode. No complex installation is required if the skill file is present in your library.
# Activation via magic keyword
ultrawork "refactor the payment gateway to use Stripe"
# Short-hand activation
ulw "generate a comprehensive API documentation site"
# Explicit orchestration request
use autonomous-skill-orchestrator
Autonomous Skill Orchestrator Data Schema & Taxonomy
The orchestrator utilizes a structured data hierarchy to maintain state and context throughout the project lifecycle.
| Data Component | Format | Storage Location | Purpose |
|---|---|---|---|
| Work Plan | Markdown | Session Context | Defines objectives, tasks, and acceptance criteria. |
| Wisdom Log | Markdown | memory/orchestrator-wisdom.md |
Persists discovered patterns and successful approaches. |
| Summary Report | Markdown | Session Output | Provides a final audit of changes and next steps. |
| Memory Persistence | Markdown | MEMORY.md |
Archives significant project learnings for long-term use. |
Autonomous Skill Orchestrator Advanced Features
- Parallel Execution: Automatically identifies and spawns independent tasks simultaneously to maximize throughput.
- Dynamic Model Hinting: Adjusts the underlying LLM specialized for the task (thinking models for logic, fast models for trivial changes).
- Automated Retry Logic: Includes a built-in mechanism for re-delegating failed tasks with updated context and error logs.
- Strict Safety Guardrails: Prevents recursive spawning and unauthorized external API calls to maintain a secure environment.
- Isolated Task Contexts: Each sub-agent operates in a clean session, preventing context pollution and reducing token usage.
SKILL.md
Loading
Related Openclaw Skills
Joko Moltbook
A specialized integration for AI agents to autonomously engage, post, and monitor activity on the Moltbook social network.
JobHunter Master
An aggressive career-hunting agent that replaces passive applications with a high-conversion, automated sales funnel approach.
Google Flow AI Video Generation Skill
Automate the Google Flow interface to generate professional AI videos from text prompts using the Veo model.
Data Analyst
A professional-grade data analysis toolkit for AI agents to query databases, automate spreadsheets, and generate visual insights.
Joko Proactive Agent
A sophisticated, self-improving agent architecture that shifts AI from reactive task-following to proactive partnership and persistent memory management.
Content Factory
An all-in-one automated YouTube content production suite for generating regular videos and viral Shorts from text or long-form content.
Featured*
