using-superpowers

<SUBAGENT-STOP> If you were dispatched as a subagent to execute a specific task, skip this skill. </SUBAGENT-STOP>

<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>

Instruction Priority

Superpowers skills override default system prompt behavior, but user instructions always take precedence:

1. User's explicit instructions (CLAUDE.md, GEMINI.md, AGENTS.md, direct requests) — highest priority
2. Superpowers skills — override default system behavior where they conflict
3. Default system prompt — lowest priority

If 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.

How to Access Skills

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.

In Gemini CLI: Skills activate via the activate_skill tool. Gemini loads skill metadata at session start and activates the full content on demand.

In other environments: Check your platform's documentation for how skills are loaded.

Platform Adaptation

Skills 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.

Using Skills

The Rule

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.

digraph skill_flow {
    "User message received" [shape=doublecircle];
    "About to EnterPlanMode?" [shape=doublecircle];
    "Already brainstormed?" [shape=diamond];
    "Invoke brainstorming skill" [shape=box];
    "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];

    "About to EnterPlanMode?" -> "Already brainstormed?";
    "Already brainstormed?" -> "Invoke brainstorming skill" [label="no"];
    "Already brainstormed?" -> "Might any skill apply?" [label="yes"];
    "Invoke brainstorming skill" -> "Might any skill apply?";

    "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"	Questions are tasks. Check for skills.
"I need more context first"	Skill check comes BEFORE clarifying questions.
"Let me explore the codebase first"	Skills tell you HOW to explore. Check first.
"I can check git/files quickly"	Files lack conversation context. Check for skills.
"Let me 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 current version.
"This doesn't count as a task"	Action = task. Check for skills.
"The skill is overkill"	Simple things become complex. Use it.
"I'll just do this one thing first"	Check BEFORE doing anything.
"This feels productive"	Undisciplined action wastes time. Skills prevent this.
"I know what that means"	Knowing the concept ≠ using the skill. Invoke it.

Skill Priority

When multiple skills could apply, use this order:

1. Process skills first (brainstorming, debugging) - these determine HOW to approach the task
2. Implementation skills second (frontend-design, mcp-builder) - these guide execution

"Let's build X" → brainstorming first, then implementation skills. "Fix this bug" → debugging first, then domain-specific skills.

Skill Types

Rigid (TDD, debugging): Follow exactly. Don't adapt away discipline.

Flexible (patterns): Adapt principles to context.

The skill itself tells you which.

User Instructions

Instructions say WHAT, not HOW. "Add X" or "Fix Y" doesn't mean skip workflows.

Asking Questions (MUST Use the Question Tool)

<EXTREMELY-IMPORTANT> ANY question that expects a user response MUST use the question tool. No exceptions.

Ending a message with a question mark and waiting for the user to respond is FORBIDDEN unless you use the question tool. </EXTREMELY-IMPORTANT>

Why this matters:

• Users often run multiple agents in parallel
• Without the question tool, users have no way to know an agent needs attention
• The question tool triggers a notification so the user sees your question promptly
• Text/markdown questions do NOT notify - the user won't see them until they check

What Counts as "Expecting a Response"

If you write something and then WAIT for the user to reply before continuing, you are expecting a response. You MUST use the question tool.

WRONG - markdown question without tool:

Here's my proposed design...

Does this look right so far?

❌ User gets no notification. Must manually check. May not see for hours.

RIGHT - question tool:

Here's my proposed design...

[Uses question tool: "Does this look right so far?" with Yes/No options]

✅ User gets notification. Can respond immediately or from anywhere.

When You MUST Use the Question Tool

• ANY question you want the user to answer - "Does this look right?" "Should I continue?" "Which option?"
• Clarification needed before proceeding
• User must make a decision or choose between options
• Presenting structured choices (commit preference, execution options, etc.)
• Validating a design, approach, or output
• When you've completed work or reached a stopping point (see below)

When NOT to Use the Question Tool

• Rhetorical questions you're about to answer yourself in the same message
• Don't ask gratuitously - unnecessary questions add delay to task completion

If you're not sure: Use the question tool. False positives (unnecessary notification) are better than false negatives (user doesn't see your question).

Task Completion - MANDATORY

When you've completed the requested work or reached any stopping point where you have nothing left to do, you MUST use the question tool to notify the user. Ask whether they are satisfied or have feedback/follow-up requests. Without this, the user won't know you're idle and time is wasted.

Formatting Questions

• You can output detailed context in markdown, then use the question tool for the actual prompt
• Prefer multiple choice when options are clear and limited
• Include brief descriptions for each option
• Users can select from options OR type a custom answer
• Use multiple: true when the user can select more than one option

Red Flags - You're About to Violate This Rule

If you catch yourself about to:

• End a message with "?" and wait
• Write "Let me know if..." and stop
• Ask "Does this look right?" in markdown
• Write "Should I continue?" without the tool
• Present options in text and wait for selection

STOP. Use the question tool.