using-superpowers
Original：🇨🇳 Chinese
Translated
Use at the start of any conversation - Determine how to find and use skills, requiring the skill tool to be invoked before any response (including clarification questions)
2installs
Added on
NPX Install
npx skill4agent add zhucl1006/ailesuperpowers using-superpowersTags
Translated version includes tags in frontmatterSKILL.md Content (Chinese)
View Translation Comparison →<EXTREMELY-IMPORTANT>
If you think there's even a 1% chance a skill applies to the current task, you **must** invoke that skill first.
If a skill applies, you have no choice but to use it.
This is not a suggestion, it's a hard rule. Don't act first and then make up for using the skill later.
</EXTREMELY-IMPORTANT>
How to Obtain Skills
In Claude Code: Use the tool. When you invoke a skill, its content will be loaded and presented to you - follow it directly. Never use the read tool on skill files.
SkillIn other environments: Check your platform documentation for how to load skills.
Usage Tips
Rules
Invoke relevant or requested skills before any response or action.
Even if a skill only has a 1% chance of being applicable, invoke it to check first.
If after invocation you confirm it's not applicable, you can choose not to use it; but you cannot skip the invocation step.
Even if a skill only has a 1% chance of being applicable, invoke it to check first.
If after invocation you confirm it's not applicable, you can choose not to use it; but you cannot skip the invocation step.
dot
digraph skill_flow {
"User message received" [shape=doublecircle];
"Might any skill apply?" [shape=diamond];
"Invoke Skill tool" [shape=box];
"Announce: 'Using [skill] to [purpose]'" [shape=box];
"Has checklist?" [shape=diamond];
"Create TodoWrite todo per item" [shape=box];
"Follow skill exactly" [shape=box];
"Respond (including clarifications)" [shape=doublecircle];
"User message received" -> "Might any skill apply?";
"Might any skill apply?" -> "Invoke Skill tool" [label="yes, even 1%"];
"Might any skill apply?" -> "Respond (including clarifications)" [label="definitely not"];
"Invoke Skill tool" -> "Announce: 'Using [skill] to [purpose]'";
"Announce: 'Using [skill] to [purpose]'" -> "Has checklist?";
"Has checklist?" -> "Create TodoWrite todo per item" [label="yes"];
"Has checklist?" -> "Follow skill exactly" [label="no"];
"Create TodoWrite todo per item" -> "Follow skill exactly";
}Red Flags
These thoughts mean stop - you're rationalizing:
| Thought | Reality |
|---|---|
| "This is just a simple question" | A question is a task. Check skills. |
| "I need more background information first" | Skill check comes before clarification. |
| "Let me explore the codebase first" | Skills tell you how to explore. Check first. |
| "I can quickly check git/files" | Files lack context. Check skills. |
| "I'll gather information first" | Skills tell you how to gather information. |
| "This doesn't need a formal skill" | If a skill exists, use it. |
| "I remember this skill" | Skills evolve. Read the current version. |
| "This isn't a task" | Action = task. Check skills. |
| "The skill is overkill" | Simple things can get complicated. Use it. |
| "I'll just do one thing first" | Check before doing anything. |
| "This feels productive" | Undisciplined action wastes time. Skills prevent this. |
| "I know what this means" | Understanding the concept ≠ using the skill. Invoke it. |
Skill Priority
When multiple skills can be applied, use the following order:
- Process skills first (brainstorming, debugging) - these determine how to approach the task
- Implementation skills second (frontend design, mcp-builder) - these guide execution
"Let's build X" → brainstorm first, then implementation skills.
"Fix this error" → debug first, then domain-specific skills.
User Instructions
Instructions tell you "what to do", not "how to do it". "Add X" or "Fix Y" does not mean skipping the workflow.