An intelligent pattern-recognition engine that observes user behavior to automatically discover and generate executable automation workflows.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install meta-workflow-discoverer
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 meta-workflow-discoverer 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 Meta Workflow Discoverer?
Meta Workflow Discoverer is a sophisticated AI-powered tool designed to eliminate the manual overhead of creating automations. By leveraging machine learning models like scikit-learn, this Openclaw Skills component mines task history for similarities, sequence patterns, and contextual triggers to identify recurring manual work that is ripe for automation.
Once a pattern is identified, the skill doesn't just notify the user; it synthesizes full workflow templates complete with error handling, parallelization, and optimization. It serves as a bridge between manual execution and autonomous operation, constantly learning from success rates and user feedback to refine its generated logic.
Meta Workflow Discoverer Use Cases
- Automated Report Generation: Identify recurring data fetching and charting tasks to create scheduled stakeholder reports.
- Data Pipeline Orchestration: Automatically sequence repetitive analysis steps into a robust processing pipeline.
- Routine Communication: Detect patterns in messaging or notifications to automate Slack or email updates.
- Systematic Research: Streamline the process of web searching, filtering, and summarizing new topics.
- Trading & Finance: Transform manual stock analysis routines into systematic, triggered execution flows.
How Meta Workflow Discoverer Works
- Pattern Mining: The system records task execution data, including steps, context, and results, to identify recurring sequences.
- Workflow Synthesis: Using a confidence threshold, the discoverer generates a structured workflow model from the detected patterns.
- Optimization: The engine analyzes the sequence to identify parallelizable steps and adds robust error-handling logic.
- Trigger Assignment: It detects time-based or event-based regularity to suggest optimal execution triggers.
- Continuous Learning: The skill monitors the success of created automations and incorporates user corrections to improve future discovery accuracy.
Meta Workflow Discoverer Setup
To begin using this tool within your Openclaw Skills environment, install the necessary machine learning dependencies:
pip install numpy pandas scikit-learn
Initialize the discoverer in your project:
from workflow_discoverer import WorkflowDiscoverer
discoverer = WorkflowDiscoverer(user_id="dev_user", min_occurrences=3)
Meta Workflow Discoverer Data Schema & Taxonomy
The skill maintains a structured taxonomy of task history and discovered patterns to ensure high-fidelity automation:
| Entity | Attributes | Description |
|---|---|---|
| Task Record | name, steps, context, result | Raw execution data from manual user actions. |
| Pattern | frequency, consistency, similarity | Statistical metrics used to validate a workflow. |
| Workflow | id, name, steps, trigger | The executable JSON-based definition of an automation. |
| Metrics | time_saved, error_rate | Value-based tracking for each discovered workflow. |
Meta Workflow Discoverer Advanced Features
- Cross-User Learning: Share anonymized pattern insights across different users to suggest industry-standard workflows.
- OpenClaw Hook Integration: Automatically record tasks directly from conversation intents and tool usage history.
- Self-Healing Workflows: Automatically refine and improve workflow steps based on execution results and success tracking.
- Natural Language Creation: Support for generating executable logic from simple descriptive patterns identified in user history.
SKILL.md
Loading
Related Openclaw Skills
Substrate Reference Tool
A comprehensive CLI-based reference suite for developers and auditors working within the Substrate blockchain ecosystem.
Einstein Research — Portfolio Risk Analyzer
A comprehensive financial risk management skill that quantifies systemic and correlated risks across investment portfolios using industry-standard metrics.
Investment Browser SEC Scraper
A professional-grade SEC EDGAR parser that extracts 47 financial metrics and calculates margins directly from 10-Q and 10-K filings without requiring expensive APIs.
Einstein Research Edge
Einstein Research Edge formalizes the transition from qualitative market observations to structured, pipeline-ready quantitative research tickets.
EvalLayer Evaluator
An AI-powered evaluation gate that extracts factual claims and scores deliverable quality for autonomous agent workflows.
Qimen Dunjia Chart Analyzer
A deterministic Qimen Dunjia calculation and interpretation engine for strategic timing and spatial forecasting.
Featured*
