A high-level strategic orchestrator that decomposes complex tasks and delegates them to specialized AI agents for efficient, economical execution.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install deep-strategy
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 deep-strategy 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 Deep Strategy?
Deep Strategy is an advanced AI agent designed for knowledge workers who need to manage complex, multi-step projects. Acting as a CEO with a focus on absolute loyalty to user input, this skill excels at breaking down vague goals into actionable plans. It leverages a Knowledge Amnesia protocol, ensuring it always verifies current market data rather than relying on stale internal memory. By integrating this into your Openclaw Skills library, you gain a powerful manager capable of coordinating specialized subordinates for research, data analysis, and content creation.
The skill operates on a foundation of cost-effectiveness and progress, proactively identifying and terminating invalid, high-cost looping behaviors. It is designed to be the ultimate strategic layer for AI-driven workflows, ensuring that every step taken is a meaningful move toward the final deliverable.
Deep Strategy Use Cases
- Developing comprehensive market research reports and competitor analyses.
- Creating strategic business plans or strategy manuals from scratch.
- Decomposing complex data analysis tasks into manageable sub-steps.
- Coordinating multi-agent workflows involving research, analysis, and writing.
- Fact-checking and verifying current industry standards or product versions.
How Deep Strategy Works
- CEO Cognitive Synchronization: The agent performs a rapid shallow search to verify user-provided entities and overcome knowledge cutoff limitations.
- Reverse Planning: It reverse-engineers the production steps required to reach the final deliverable requested by the user.
- Task Decomposition: The project is broken down into specific sub-goals assigned to specialized leads such as Research, Content, Data, or Knowledge agents.
- Execution & Supervision: The agent monitors subordinates, validates their output against expectations, and handles deadlocks or failures proactively.
- Final Integration: It synthesizes all subordinate outputs into a high-fidelity final product, ensuring no raw materials are delivered as final articles unless requested.
Deep Strategy Setup
To use the Deep Strategy agent, ensure your environment supports Openclaw Skills. Install the skill using the CLI and configure your subordinate tool API keys.
# Install the Deep Strategy skill
openclaw install deep-strategy
# Configure required subordinate tools
openclaw configure data-analyst
openclaw configure conduct_deep_research
Ensure that the environment variables for date and session management are correctly mapped to allow the agent to maintain temporal awareness during planning.
Deep Strategy Data Schema & Taxonomy
The skill organizes its operations through a structured hierarchy of tasks and metadata:
| Component | Description |
|---|---|
| todo_list | A step-by-step sequence of internal actions and delegated tasks. |
| attached_files | Metadata and documents passed between the CEO and subordinate agents. |
| task_description | Mandatory structured templates for delegating research or writing tasks. |
| final_deliverable | The synthesized final output, such as a strategy manual or data report. |
Deep Strategy Advanced Features
- Golden Rule Protocols: Inviolable logic ensuring security, absolute loyalty to user input, and internal configuration confidentiality.
- Deadlock Handling Mechanism: Automatic termination of failing sub-goals after two consecutive attempts to prevent cost loops and task stagnation.
- Multi-Agent Orchestration: Native support for triggering wiki_retriever, data_analyst, and compose_written_content tools in a specific logical order.
- High-Fidelity Intent Transfer: A core principle ensuring that original user requirements are preserved with maximum accuracy through multiple layers of delegation.
- Expert Group Management: Specialized handling for Research Group Leads and Content Group Leads with mandatory structured instruction templates.
SKILL.md
Loading
Related Openclaw Skills
Deep Research Strategy
A strategic lead agent that orchestrates specialized subordinates to conduct multi-dimensional, deep-dive research with mandatory verification and parallel task decomposition.
Deep Research Agent
A sophisticated AI research leader that orchestrates specialized agents to decompose, execute, and synthesize complex information-gathering tasks.
Data Analyst
An automated agent skill designed to execute complex data analysis tasks and process uploaded files directly within a local working directory.
Coding Skill for Dynamic Dashboards
Automate the end-to-end process of database schema design, data insertion, and the generation of real-time dynamic HTML dashboards.
TikTok Live Commerce
Connect AI agents to professional TikTok livestreamers to automate real-time shopping sessions, interactive product demos, and high-conversion sales events.
TikTok Product Promotion
A powerful AI agent skill for sourcing and managing TikTok influencers to create high-impact product reviews, unboxing videos, and conversion-driven campaigns.
Featured*
