using-superpowers

Enforces skill discovery and invocation before any AI response across coding platforms.

Updated May 22, 2026
One-click install
npx skills add https://github.com/viniciuscs84/sdd-toolkit --skill using-superpowers-viniciuscs84
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/viniciuscs84/sdd-toolkit/tree/main/skills/using-superpowers
Command: npx skills add https://github.com/viniciuscs84/sdd-toolkit --skill using-superpowers-viniciuscs84

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? AI coding assistants often skip available skills and jump straight into tasks, producing undisciplined or inconsistent work. This Skill establishes a mandatory workflow where the agent checks for and invokes relevant skills before any response, including clarifying questions. ## Core Features & Use Cases - Mandatory Skill Invocation: Requires invoking any potentially relevant skill (even at 1% relevance) before responding or acting. - Cross-Platform Tool Mapping: Ships reference guides mapping Claude Code tools to Copilot CLI, Codex, and Gemini CLI equivalents. - Priority and Red-Flag Rules: Defines instruction priority (user instructions over skills over system defaults), skill ordering (process skills before implementation skills), and a table of rationalization red flags. - Use Case: When a user asks an agent to fix a bug, the agent first invokes the debugging skill, announces its use, creates todos from the skill checklist, and only then proceeds with the fix. ## Quick Start Ask your AI assistant to check for and invoke any applicable skills before answering your next coding request.

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 use skills before responding?

Install this skill so it loads at conversation start. It instructs the agent to invoke any potentially relevant skill via the Skill tool before responding, including before clarifying questions, and to announce which skill it is using.

What is the correct order when multiple skills apply to a task?

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

Does this skill work with Copilot CLI, Codex, or Gemini CLI?

Yes. The references directory includes tool-mapping guides for Copilot CLI, Codex, and Gemini CLI that translate Claude Code tool names like Task, TodoWrite, and Skill into each platform's equivalents.

Do user instructions override skill instructions?

Yes. Explicit user instructions in CLAUDE.md, GEMINI.md, AGENTS.md, or direct requests take highest priority. Skills override default system behavior but never override the user's stated preferences.

Why does the agent skip skills even when they exist?

Agents rationalize skipping with thoughts like 'this is just a simple question' or 'I remember this skill.' This skill lists those red flags explicitly and requires invoking the skill to check, even at 1% perceived relevance.