
using-superpowers
by a-ariff
🔌 Production-ready Claude Code plugin marketplace with 41 components: 21 autonomous agents, 15 power skills, 2 smart hooks, 2 custom commands. Transform Claude Code into an autonomous development powerhouse. One-line install, cross-device sync, comprehensive documentation.
SKILL.md
name: using-superpowers description: Core skill activation protocol - establishes mandatory workflows for finding and applying skills before any task version: 1.0.0 author: Ariff
Superpowers Activation Protocol
Core Philosophy
"If a skill exists for your task, you MUST use it. No exceptions. No rationalizations."
Skills encode proven solutions. Ignoring them means repeating solved problems.
Mandatory First Response Protocol
Before ANY action, complete this mental checklist:
□ What skills might apply here?
□ Have I checked the skill registry?
□ Did I read the CURRENT version (not memory)?
□ Am I following it exactly?
The Golden Rules
1. Skills Are Not Optional
If a relevant skill exists → USE IT.
- "This is just a simple question" → Still check for skills
- "I can do this quickly" → Skills exist because "quick" becomes complex
- "The skill is overkill" → Use it anyway
2. Always Announce Skill Usage
"I'm using [Skill Name] to [what you're doing]."
3. Checklists Require TodoWrite
If a skill has a checklist → Create todos for EACH item. Don't work through checklists mentally. Track them.
4. Instructions ≠ Permission to Skip Workflows
User says "Fix X" → That's the WHAT, not the HOW. Still follow brainstorming, TDD, verification workflows.
Skill Categories
| Category | When to Use |
|---|---|
| Checkers | Before assumptions, before actions |
| Collaboration | Planning, brainstorming, executing plans |
| Debugging | When something's broken |
| Problem-Solving | When stuck |
| Testing | TDD, test design |
| Meta | Writing/improving skills |
Quick Dispatch
Starting a feature → brainstorming → writing-plans → executing-plans
Something broken → systematic-debugging or root-cause-tracing
About to assume → assumption-checker
About to modify → pre-action-verifier
Claiming done → verification-before-completion
Anti-Patterns (Stop If You Think These)
| Thought | Reality |
|---|---|
| "I remember this skill" | Skills evolve. Read current version. |
| "This doesn't need a skill" | If skill exists, use it. |
| "Let me just do this first" | Check skills BEFORE anything. |
| "This is simple" | Simple tasks become complex. Use skills. |
Integration with Checker Agents
Before taking action, the checker agents validate:
assumption-checker→ Are you guessing?context-validator→ Do you have enough context?intent-clarifier→ Is the request clear?pre-action-verifier→ Are prerequisites met?fact-checker→ Are your claims about code accurate?
These checkers are strict mode - they halt and ask rather than proceeding.
Summary
- Check for relevant skills FIRST
- Announce you're using them
- Follow them EXACTLY
- Use TodoWrite for checklists
- Verify before claiming completion
スコア
総合スコア
リポジトリの品質指標に基づく評価
SKILL.mdファイルが含まれている
ライセンスが設定されている
100文字以上の説明がある
GitHub Stars 100以上
3ヶ月以内に更新
10回以上フォークされている
オープンIssueが50未満
プログラミング言語が設定されている
1つ以上のタグが設定されている
レビュー
レビュー機能は近日公開予定です

