superpowers
Agentic software development methodology — 13 integrated skills for disciplined AI-assisted development covering brainstorming, planning, TDD, debugging, code review, git worktrees, and branch management.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/cutd/claw-superpowersSuperpowers
Disciplined, systematic approach to AI-assisted software development. 13 integrated skills covering the full development lifecycle.
The 7-Step Workflow
- Brainstorm — Design before implementation (Section 2)
- Plan — Write detailed implementation plan (Section 3)
- Execute — Implement with subagents or batches (Sections 4-6)
- Test — TDD throughout: RED-GREEN-REFACTOR (Section 7)
- Debug — Systematic root cause analysis when needed (Section 8)
- Review — Code review after each task (Section 10)
- Finish — Branch completion and integration (Section 12)
How to Use
Apply the relevant section based on your current task:
| Task | Section |
|---|---|
| Starting new work | Section 2 (Brainstorming) → Section 3 (Writing Plans) |
| Implementing a plan (this session) | Section 5 (Subagent-Driven Development) |
| Implementing a plan (separate session) | Section 4 (Executing Plans) |
| Multiple independent problems | Section 6 (Dispatching Parallel Agents) |
| Writing or fixing code | Section 7 (Test-Driven Development) |
| Bug, test failure, unexpected behavior | Section 8 (Systematic Debugging) |
| About to claim work is done | Section 9 (Verification Before Completion) |
| After completing work | Section 10 (Code Review) |
| Need isolated workspace | Section 11 (Using Git Worktrees) |
| Ready to merge/integrate | Section 12 (Finishing a Development Branch) |
| Creating new skills | Section 13 (Writing Skills) |
Skill priority: Process skills first (brainstorming, debugging), then implementation skills.
Skill types:
- Rigid (TDD, debugging, verification): Follow exactly. Don't adapt away discipline.
- Flexible (patterns, worktrees): Adapt principles to context.
1. Using Superpowers
<EXTREMELY-IMPORTANT> If you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill.IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.
This is not negotiable. This is not optional. You cannot rationalize your way out of this. </EXTREMELY-IMPORTANT>
Rule: Invoke relevant skills BEFORE any response or action. Even a 1% chance a section might apply means you should check.
Process:
- User message received
- Check: might any section apply?
- Yes → Follow that section
- No → Respond directly
- If about to plan: check Section 2 (Brainstorming) first
- If section has checklist: create todo per checklist item
- Announce: "Using [skill] to [purpose]"
Priority order:
- Process sections first (brainstorming, debugging)
- Implementation sections second
User instructions say WHAT, not HOW. "Add X" or "Fix Y" doesn't mean skip workflows.
Red Flags — You're Rationalizing
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-cutd-claw-superpowers": {
"enabled": true,
"auto_update": true
}
}
}