1---
2name: using-superpowers
3description: Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
4---
5 
6<SUBAGENT-STOP>
7If you were dispatched as a subagent to execute a specific task, skip this skill.
8</SUBAGENT-STOP>
9 
10<EXTREMELY-IMPORTANT>
11If you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill.
12 
13IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.
14 
15This is not negotiable. This is not optional. You cannot rationalize your way out of this.
16</EXTREMELY-IMPORTANT>
17 
18## Instruction Priority
19 
20Superpowers skills override default system prompt behavior, but **user instructions always take precedence**:
21 
221. **User's explicit instructions** (CLAUDE.md, GEMINI.md, AGENTS.md, direct requests) — highest priority
232. **Superpowers skills** — override default system behavior where they conflict
243. **Default system prompt** — lowest priority
25 
26If CLAUDE.md, GEMINI.md, or AGENTS.md says "don't use TDD" and a skill says "always use TDD," follow the user's instructions. The user is in control.
27 
28## How to Access Skills
29 
30**In Claude Code:** Use the `Skill` tool. When you invoke a skill, its content is loaded and presented to you—follow it directly. Never use the Read tool on skill files.
31 
32**In Gemini CLI:** Skills activate via the `activate_skill` tool. Gemini loads skill metadata at session start and activates the full content on demand.
33 
34**In other environments:** Check your platform's documentation for how skills are loaded.
35 
36## Platform Adaptation
37 
38Skills use Claude Code tool names. Non-CC platforms: see `references/codex-tools.md` (Codex) for tool equivalents. Gemini CLI users get the tool mapping loaded automatically via GEMINI.md.
39 
40# Using Skills
41 
42## The Rule
43 
44**Invoke relevant or requested skills BEFORE any response or action.** Even a 1% chance a skill might apply means that you should invoke the skill to check. If an invoked skill turns out to be wrong for the situation, you don't need to use it.
45 
46```dot
47digraph skill_flow {
48    "User message received" [shape=doublecircle];
49    "About to EnterPlanMode?" [shape=doublecircle];
50    "Already brainstormed?" [shape=diamond];
51    "Invoke brainstorming skill" [shape=box];
52    "Might any skill apply?" [shape=diamond];
53    "Invoke Skill tool" [shape=box];
54    "Announce: 'Using [skill] to [purpose]'" [shape=box];
55    "Has checklist?" [shape=diamond];
56    "Create TodoWrite todo per item" [shape=box];
57    "Follow skill exactly" [shape=box];
58    "Respond (including clarifications)" [shape=doublecircle];
59 
60    "About to EnterPlanMode?" -> "Already brainstormed?";
61    "Already brainstormed?" -> "Invoke brainstorming skill" [label="no"];
62    "Already brainstormed?" -> "Might any skill apply?" [label="yes"];
63    "Invoke brainstorming skill" -> "Might any skill apply?";
64 
65    "User message received" -> "Might any skill apply?";
66    "Might any skill apply?" -> "Invoke Skill tool" [label="yes, even 1%"];
67    "Might any skill apply?" -> "Respond (including clarifications)" [label="definitely not"];
68    "Invoke Skill tool" -> "Announce: 'Using [skill] to [purpose]'";
69    "Announce: 'Using [skill] to [purpose]'" -> "Has checklist?";
70    "Has checklist?" -> "Create TodoWrite todo per item" [label="yes"];
71    "Has checklist?" -> "Follow skill exactly" [label="no"];
72    "Create TodoWrite todo per item" -> "Follow skill exactly";
73}
74```
75 
76## Red Flags
77 
78These thoughts mean STOP—you're rationalizing:
79 
80| Thought | Reality |
81|---------|---------|
82| "This is just a simple question" | Questions are tasks. Check for skills. |
83| "I need more context first" | Skill check comes BEFORE clarifying questions. |
84| "Let me explore the codebase first" | Skills tell you HOW to explore. Check first. |
85| "I can check git/files quickly" | Files lack conversation context. Check for skills. |
86| "Let me gather information first" | Skills tell you HOW to gather information. |
87| "This doesn't need a formal skill" | If a skill exists, use it. |
88| "I remember this skill" | Skills evolve. Read current version. |
89| "This doesn't count as a task" | Action = task. Check for skills. |
90| "The skill is overkill" | Simple things become complex. Use it. |
91| "I'll just do this one thing first" | Check BEFORE doing anything. |
92| "This feels productive" | Undisciplined action wastes time. Skills prevent this. |
93| "I know what that means" | Knowing the concept ≠ using the skill. Invoke it. |
94 
95## Skill Priority
96 
97When multiple skills could apply, use this order:
98 
991. **Process skills first** (brainstorming, debugging) - these determine HOW to approach the task
1002. **Implementation skills second** (frontend-design, mcp-builder) - these guide execution
101 
102"Let's build X" → brainstorming first, then implementation skills.
103"Fix this bug" → debugging first, then domain-specific skills.
104 
105## Skill Types
106 
107**Rigid** (TDD, debugging): Follow exactly. Don't adapt away discipline.
108 
109**Flexible** (patterns): Adapt principles to context.
110 
111The skill itself tells you which.
112 
113## User Instructions
114 
115Instructions say WHAT, not HOW. "Add X" or "Fix Y" doesn't mean skip workflows.
116