using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
When & Why to Use This Skill
This Claude skill establishes a mandatory foundational protocol for agentic workflows, ensuring that specialized skills are identified and invoked before any response is generated. It eliminates guesswork and 'rationalization' by enforcing a disciplined check-first approach, integrating task tracking, and prioritizing process-oriented skills to guarantee high-quality, standardized outcomes across all interactions.
Use Cases
- 1. Agent Initialization & Governance: Sets the primary operational rules for how an AI agent must interact with its toolset at the start of every session to ensure consistency.
- 2. Workflow Discipline Enforcement: Prevents the agent from skipping established SOPs for tasks that seem 'simple' but require specific technical rigor or domain-specific logic.
- 3. Multi-Skill Hierarchy Management: Orchestrates the sequence of operations by ensuring process-heavy skills (like brainstorming or debugging) are applied before execution-focused skills.
- 4. Persistent Task Tracking: Automatically converts skill-based checklists into trackable, persistent issues using command-line integrations to maintain progress across long-running projects.
| name | using-superpowers |
|---|---|
| description | Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions |
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.
Using Skills
The Rule
Check for skills BEFORE ANY RESPONSE. This includes clarifying questions. Even 1% chance means invoke the Skill tool first.
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 bd issues for checklist items" [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 bd issues for checklist items" [label="yes"];
"Has checklist?" -> "Follow skill exactly" [label="no"];
"Create bd issues for checklist items" -> "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. |
Skill Priority
When multiple skills could apply, use this 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" → 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.
BD Integration for Checklists
When a skill contains a checklist, create bd issues to track completion:
# Example: Writing a skill with checklist
bd create "RED Phase: Create pressure scenarios" --type task --priority 1
bd create "RED Phase: Run baseline tests" --type task --priority 1 --deps blocks:<previous-id>
bd create "GREEN Phase: Write minimal skill" --type task --priority 1 --deps blocks:<previous-id>
bd create "REFACTOR Phase: Close loopholes" --type task --priority 1 --deps blocks:<previous-id>
bd create "Quality: Add CSO keywords" --type task --priority 2
bd create "Deploy: Commit and push" --type task --priority 2 --deps blocks:<all-previous>
# Track progress
bd list --status open
bd update <id> --status in_progress
bd close <id>
Benefits of bd for checklists:
- Persistence: Checklist survives session interruptions
- Dependencies: Enforce proper ordering
- Visibility: See what's been done and what remains
- Notes: Add context with
bd comment
User Instructions
Instructions say WHAT, not HOW. "Add X" or "Fix Y" doesn't mean skip workflows.