using-superpowers

Establishes mandatory skill discovery and invocation rules before any AI response.

Updated Jan 28, 2026
One-click install
npx skills add https://github.com/ttphats/project-detedxs26 --skill using-superpowers-ttphats
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/ttphats/project-detedxs26/tree/main/.augment/skills/superpowers/using-superpowers
Command: npx skills add https://github.com/ttphats/project-detedxs26 --skill using-superpowers-ttphats

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? AI agents often skip relevant skills and respond directly, leading to inconsistent workflows and missed process discipline. This Skill enforces a mandatory check-and-invoke rule so that applicable skills are always loaded before any response or action. ## Core Features & Use Cases - Mandatory Skill Invocation: Requires invoking any potentially relevant skill before responding, even for clarifying questions, with a decision flowchart and red-flag rationalization list. - Cross-Platform Tool Mapping: Provides reference tables mapping Augment Agent tool names to Copilot CLI, Codex, and Gemini CLI equivalents. - CodeGraph Integration Guidance: Directs agents to use semantic code intelligence tools when a .codegraph directory exists, falling back to standard file tools otherwise. - Use Case: An agent receives a request to fix a bug; before answering, it invokes the debugging skill first, then follows that skill's workflow exactly. ## Quick Start Invoke the using-superpowers skill at the start of every conversation to load the skill discovery and invocation rules.

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 small chance of applying must be invoked before responding, including before clarifying questions, and provides a decision flowchart for the check.

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

Process skills like brainstorming and 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, and Gemini CLI?▼

Yes. The references directory includes tool mapping tables for Copilot CLI, Codex, and Gemini CLI, translating Augment Agent tool names like Read, Task, and TodoWrite into each platform's native equivalents.

Do user instructions override skill workflows?▼

Yes. User instructions in files like AGENTS.md or GEMINI.md take highest priority. If a user says not to use TDD and a skill mandates it, the user's instruction wins.

When should CodeGraph tools be used instead of file reads?▼

Use CodeGraph tools when a .codegraph directory exists in the project root. Semantic queries like codegraph_explore or codegraph_callers answer structural questions in one call instead of many read and grep cycles.