using-superpowers

Enforces skill discovery and invocation before any AI response or action.

Updated Dec 19, 2024
One-click install
npx skills add https://github.com/DNepovim/yadm --skill using-superpowers-dnepovim
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/DNepovim/yadm/tree/main/.claude/plugins/cache/claude-plugins-official/superpowers/5.0.6/skills/using-superpowers
Command: npx skills add https://github.com/DNepovim/yadm --skill using-superpowers-dnepovim

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? AI agents often skip available skills and respond directly, missing established workflows. This Skill establishes a mandatory protocol requiring the agent to check for and invoke relevant skills before any response, including clarifying questions. ## Core Features & Use Cases - Mandatory Skill Check: Requires invoking any potentially applicable skill (even at 1% relevance) before responding or acting. - Priority Rules: Defines instruction precedence (user instructions over skills over system defaults) and skill ordering (process skills before implementation skills). - Cross-Platform Tool Mapping: Provides reference tables mapping Claude Code tools to Codex and Gemini CLI equivalents. - Use Case: When a user asks to fix a bug, the agent first invokes the debugging skill rather than jumping straight into code edits, ensuring disciplined workflows like TDD are followed. ## Quick Start Start a new conversation and ask the agent to follow the superpowers skill protocol before responding to any task.

Frequently Asked Questions about using-superpowers

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I make an AI agent always check for skills before responding?▼

Invoke the using-superpowers skill at conversation start. It mandates that any skill with even a 1% chance of applying must be invoked before any response, including clarifying questions, and provides a decision flowchart for the check.

What is the skill priority order when multiple skills apply?▼

Process skills like brainstorming and debugging come first because they determine how to approach the task. Implementation skills like frontend-design or mcp-builder come second to guide execution.

Do user instructions override skill instructions?▼

Yes. User instructions in CLAUDE.md, GEMINI.md, AGENTS.md, or direct requests take highest priority. Skills override default system behavior but never override explicit user instructions.

Can I use superpowers skills in Gemini CLI or Codex?▼

Yes. The skill includes reference files mapping Claude Code tools to Gemini CLI equivalents like activate_skill and write_todos, and to Codex equivalents like spawn_agent and update_plan.

Does Gemini CLI support subagent dispatch for skills?▼

No. Gemini CLI has no equivalent to the Task tool, so skills relying on subagent dispatch fall back to single-session execution. Codex supports it via spawn_agent with multi_agent enabled in config.