superpowers-isolated-workspace
Use when starting feature work that needs isolation from current workspace - creates isolated git branches with clean setup and safety verification, adapted for OpenClaw environments
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/axelhu/superpowers-isolated-workspaceWhat This Skill Does
The superpowers-isolated-workspace skill is an essential developer tool designed for OpenClaw agents to manage feature development with surgical precision. It automates the creation of isolated git environments by enforcing a rigorous workflow: checking for existing workspace structures, verifying directory exclusion via .gitignore, and automatically configuring project dependencies. Instead of relying on complex git worktree configurations which can be volatile in WSL-based OpenClaw environments, this skill uses a stable git branch and directory management strategy. It ensures that every new feature starts from a clean, validated baseline, drastically reducing the risk of environment contamination and 'it works on my machine' bugs.
Installation
To integrate this into your agent, run the following command in your terminal:
clawhub install openclaw/skills/skills/axelhu/superpowers-isolated-workspace
Use Cases
- Starting a new feature development session after a brainstormed design is approved.
- Refactoring existing codebases where you need a 'sandbox' that is isolated from the main branch.
- Onboarding to a new project where dependency installation and environment validation are repetitive manual tasks.
- Rapidly pivoting between multiple feature branches without polluting the root workspace or causing dependency conflicts.
Example Prompts
- "I've finished the design for the new authentication module. Can you use isolated-workspace to set up the environment and start on the implementation?"
- "We need to fix a critical bug in the legacy parser. Please create an isolated workspace for this work and ensure the test suite is passing before I start coding."
- "Let's begin the refactor of the API layer. Please initialize a new feature branch and set up the local project dependencies."
Tips & Limitations
- Safety First: Always allow the agent to verify your
.gitignore. If the agent requests that a directory be added to your ignore file, approve it to prevent local build artifacts from being committed to the repository. - Dependency Detection: The skill detects
package.json,requirements.txt,Cargo.toml, andgo.mod. If you use custom build tools or nix-shells, you may need to supplement the initial setup manually. - Baseline Testing: Always pay attention to the test output. If the baseline fails, the skill will halt. It is better to debug the base branch than to pile new features on top of a broken build.
- Environment Compatibility: This skill is optimized specifically for OpenClaw (WSL). If you find yourself in a non-standard shell environment, ensure your git configuration supports the branch-based isolation pattern.
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-isolated-workspace": {
"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
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
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