using-superpowers

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

Updated May 18, 2026
One-click install
npx skills add https://github.com/fts-pro/FTS-MMIS-AFRIKA --skill using-superpowers-fts-pro
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/fts-pro/FTS-MMIS-AFRIKA/tree/main/.agent/skills/using-superpowers
Command: npx skills add https://github.com/fts-pro/FTS-MMIS-AFRIKA --skill using-superpowers-fts-pro

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 and best practices. This Skill establishes a mandatory protocol requiring skill checks before any response, including clarifying questions. ## Core Features & Use Cases - Mandatory Skill Invocation: Requires invoking any potentially relevant skill (even at 1% likelihood) before responding or acting. - Cross-Platform Tool Mapping: Provides reference tables 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 defaults), skill ordering (process skills before implementation skills), and a list of rationalization red flags to stop. - Use Case: When starting any conversation in an AI coding environment, this Skill ensures the agent checks for applicable skills like brainstorming or debugging before writing code or answering questions. ## Quick Start Ask the agent to check for and invoke any applicable skills before responding to your 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 use skills before responding?▼

Invoke this skill at conversation start to enforce a rule requiring skill checks before any response, including clarifying questions. The agent must invoke any skill with even a 1% chance of applying, then announce which skill it is using and follow it exactly.

How do Claude Code tools map to Copilot CLI and Gemini CLI?▼

The references directory contains mapping tables: Claude Code's Read maps to Copilot's view and Gemini's read_file, Bash maps to bash and run_shell_command, and the Skill tool maps to skill and activate_skill respectively. Codex mappings cover spawn_agent and update_plan equivalents.

Do user instructions override skill instructions?▼

Yes, user instructions always take precedence. The priority order is explicit user instructions first, then skill content, then default system prompt behavior. If a user configuration says to skip a workflow like TDD, that instruction wins.

Which skills should run first when multiple skills apply?▼

Process skills like brainstorming and debugging run first because they determine how to approach the task. Implementation skills like frontend-design run second to guide execution. For example, a build request triggers brainstorming before implementation skills.

When should a subagent skip this skill?▼

Subagents dispatched to execute a specific task should skip this skill entirely, as indicated by the SUBAGENT-STOP block. The skill is designed for primary conversation agents deciding how to approach incoming user messages.