skills.rest
gtbauke
gtbaukeCOMMUNITY
Explore all skills by this author →
GitHub

using-superpowers

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

Updated Feb 20, 2026
Search Tags:#claude code#ai workflow#skill discovery#gemini cli#agent protocol#instruction priority#tool mapping
One-click install
npx skills add https://github.com/gtbauke/bj-utils --skill using-superpowers-gtbauke
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/gtbauke/bj-utils/tree/main/.agent/skills/using-superpowers
Command: npx skills add https://github.com/gtbauke/bj-utils --skill using-superpowers-gtbauke

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? AI assistants often skip available skills and respond directly, missing established workflows. This Skill establishes a mandatory protocol that requires checking and invoking relevant skills before any response, including clarifying questions. ## Core Features & Use Cases - Mandatory Skill Check: Requires invoking any potentially relevant skill (even at 1% likelihood) before responding or acting. - Instruction Priority Framework: Defines a clear hierarchy where user instructions override skills, and skills override default system behavior. - 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 assistant first invokes the debugging skill before exploring code, ensuring disciplined workflows instead of ad-hoc fixes. ## Quick Start Start a new conversation and ask the assistant 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 assistant always check skills before responding?▼

Install this skill so it loads at conversation start. It instructs the assistant to invoke any potentially relevant skill before responding, including before clarifying questions, and provides a decision flowchart for the check.

What happens when user instructions conflict with a skill?▼

User instructions always take precedence. The priority order is: explicit user instructions (CLAUDE.md, GEMINI.md, AGENTS.md) first, then skills, then default system prompt behavior.

Does this skill work with Gemini CLI and Codex?▼

Yes. The skill includes reference files mapping Claude Code tool names to Gemini CLI equivalents (activate_skill, read_file, run_shell_command) and Codex equivalents (spawn_agent, update_plan).

Can subagent-based skills run in Gemini CLI?▼

No. Gemini CLI has no equivalent to the Task tool for subagent dispatch. Skills relying on subagents fall back to single-session execution, while Codex requires enabling multi_agent in its config.

When should this skill be skipped?▼

Subagents dispatched to execute a specific task should skip this skill, as indicated by the SUBAGENT-STOP block at the top of the instructions.

Related Skills

Explore More Software Engineering Skills→
fyodorivfyodoriv

agentbrew-add-skill

Register GitHub, local folder, and catalog skill sources for agentbrew deployment.

Community
Intermediate
rishikanthcrishikanthc

using-superpowers

Enforce Skill tool invocation and checklist-driven workflows before responding.

Community
Advanced
CowboyLogicCowboyLogic

copilot-instruction-creator

Configure Copilot behavior with structured instruction files across scopes.

Official
Intermediate
verrio1verrio1

Prompting

Render Handlebars templates with YAML/JSON data to generate prompts.

Community
Advanced