A high-discipline engineering workflow skill that enforces structured planning, TDD, and risk assessment for complex coding tasks.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install superpowers-mode
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 superpowers-mode 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 Superpowers Mode?
Superpowers Mode is a specialized framework for AI agents designed to transform standard chat interactions into a rigorous engineering process. Inspired by high-stakes development methodologies, it compels the agent to prioritize architectural clarity and safety over speed when handling non-trivial code changes. This Openclaw Skills addition ensures that every technical task undergoes a mandatory sequence of goal clarification, specification writing, and incremental execution, reducing the likelihood of regression or architectural debt.
By activating this mode, users can ensure their AI assistants act more like senior staff engineers rather than simple autocomplete tools. The skill focuses on preventing common pitfalls in AI-generated code by introducing friction where it matters most: during the planning and verification phases.
Superpowers Mode Use Cases
- Implementing complex features where architectural integrity is paramount.
- Debugging critical systems where unintended side effects must be avoided.
- Refactoring legacy codebases using Test-Driven Development (TDD) principles.
- Managing high-risk deployments involving authentication, cron jobs, or system configurations.
- Training AI agents to avoid hasty, unverified code injections in production environments.
How Superpowers Mode Works
- The user activates the mode via explicit commands such as enable superpowers or status checks.
- The skill updates and tracks a persistent state file in memory/superpowers-mode.md to maintain context across sessions.
- When a coding or debugging task is identified, the agent automatically triggers the strict workflow.
- The agent clarifies objectives and constraints before any code is written.
- A chunked specification and incremental implementation plan are generated for user approval.
- An optional mini risk review is conducted to identify potential production failures and rollback signals.
- Execution proceeds task-by-task, favoring TDD and explicit verification against acceptance criteria.
Superpowers Mode Setup
To deploy this skill within your environment, ensure your agent has access to the memory directory. Create the state file using the following commands:
mkdir -p memory references
touch memory/superpowers-mode.md
Ensure your agent's system prompt is configured to monitor the memory/superpowers-mode.md file to determine whether to apply the strict engineering guardrails provided by Openclaw Skills.
Superpowers Mode Data Schema & Taxonomy
The skill utilizes a structured Markdown file to track its operational state:
| Property | Type | Description |
|---|---|---|
| enabled | Boolean | Indicates if the strict engineering workflow is active. |
| updatedAt | ISO Timestamp | The last time the mode state was toggled. |
| notes | String | Optional context or metadata about the current session. |
Additionally, the skill can pull from the references/ directory to apply standardized templates during the specification and planning phases.
Superpowers Mode Advanced Features
- Multi-language command recognition supporting English and Russian trigger phrases.
- Red-flag self-checking system that detects when an agent is attempting to bypass the plan or skip testing.
- Context-aware guardrails that automatically disable the workflow for non-coding chat to maintain speed.
- Integration with TDD workflows to ensure high-risk edits are backed by automated verification.
- Support for rapid-skip mode when users explicitly request speed over process via keywords like quick or just do it.
SKILL.md
Loading
Related Openclaw Skills
Playwright MCP Browser Automation
A high-performance browser automation skill that enables AI agents to control web browsers via the Model Context Protocol.
Playwright Browser Automation
A high-performance browser automation skill for Openclaw Skills that leverages the direct Playwright API for reliable web interaction and data extraction.
NotebookLM Ops
A specialized automation suite for managing the Google NotebookLM MCP authentication lifecycle and virtual browser stack on Linux.
Interactive LeetCode MCP
A powerful Model Context Protocol (MCP) server designed to transform AI agents into interactive LeetCode tutors and submission engines.
Claude Code Usage Reporter
A professional reporting tool that tracks Claude Code token consumption, cache hits, and real-time API expenditure.
Idea Spark
Idea Spark is an automated research agent that scans developer communities for real-world pain points to generate and validate actionable project ideas.
Featured*
