superpowers-subagent-dev
Use when executing implementation plans with independent tasks - coordinates task execution by dispatching subagents per task with verification checkpoints, adapted for OpenClaw's isolated session model
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/axelhu/superpowers-subagent-devWhat This Skill Does
The superpowers-subagent-dev skill is a sophisticated orchestrator designed for OpenClaw agents to execute complex technical implementation plans. Rather than attempting to handle every aspect of a project within a single, potentially bloated session, this skill adopts a granular, isolated approach. It functions by spawning individual, purpose-built subagents for specific tasks.
Each task undergoes a rigorous two-stage verification process: first, an assessment of specification compliance to ensure the work matches the project requirements; second, a detailed code quality review, focusing on principles like DRY, naming conventions, and robust test design. By leveraging OpenClaw's session management, it ensures that each subagent remains focused on its designated scope without inheriting irrelevant historical baggage from the main session.
Installation
To integrate this skill into your environment, run the following command in your OpenClaw terminal:
clawhub install openclaw/skills/skills/axelhu/superpowers-subagent-dev
Ensure that you have the prerequisite skills, specifically superpowers-writing-plans, superpowers-finishing-branch, and superpowers-tdd, to maximize the effectiveness of the subagent workflow.
Use Cases
- Complex Refactoring: Use this when a project requires breaking down a large codebase update into individual, isolated module refactors.
- New Feature Implementation: Perfect for multi-stage feature rollouts where each sub-component (e.g., API layer, DB schema, UI component) requires testing and validation before moving to the next.
- Technical Debt Cleanup: Useful for executing a series of systematic fixes across a repository where each fix requires specific environmental context and testing.
- Automated Bug Resolution: Ideal for systematic, reproducible bug fixes where a clear plan is defined and needs precise execution per task.
Example Prompts
- "I've just created a project plan using superpowers-writing-plans. Please use superpowers-subagent-dev to execute the implementation tasks in order."
- "The subagent for the authentication task is reporting DONE_WITH_CONCERNS. Read the concerns and decide if we need to refine the implementation before moving to the next task."
- "Execute the next task in the implementation plan using a high-capability model because this module requires complex architectural decisions."
Tips & Limitations
- Model Selection: Always choose the most cost-effective model that can handle the specific task. Reserve high-end models for architectural tasks and smaller, faster models for mechanical coding tasks.
- Strict Sequencing: Never initiate a code quality review before the specification compliance review is finalized.
- Context Handling: Never let subagents read the entire plan file directly; extract the specific task context to prevent unnecessary overhead and confusion. If a subagent reports BLOCKED, analyze the root cause—it is often a sign of insufficient context provided in the initial dispatch.
- Avoid Over-Automation: Ensure you, the human, always approve moving to the final branch merging process to maintain control over the project state.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-axelhu-superpowers-subagent-dev": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, code-execution
Related Skills
Openclaw Sleep
Skill by axelhu
superpowers-overview
Use when starting any development work or when unsure which superpowers development skill to use - provides entry point and navigation to the full superpowers skill suite for OpenClaw agents
contacts
通讯录查询与维护技能。用于查找联系人信息（open_id、chat_id、account_id 等）、记录新联系人、或查询历史沟通偏好。触发时机：(1) 需要 @某人或向某渠道发消息时 (2) 认识新联系人后需要录入通讯录时 (3) 查询某人的联系方式或交流偏好时 (4) 询问"谁知道xxx的飞书ID"或"怎么联系xxx"时。
superpowers-executing-plans
Use when executing a written implementation plan in the current session with sequential task execution and review checkpoints - for when subagent-driven mode is not available
superpowers-requesting-code-review
Use when completing tasks, implementing major features, or before merging - dispatches code review subagent to catch issues before they cascade, adapted for OpenClaw sessions_spawn model