skills.rest
Pgooone
PgoooneCOMMUNITY
Explore all skills by this author →
GitHub

using-superpowers

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

1|Updated Apr 3, 2026
Search Tags:#claude code#codex#workflow enforcement#skill discovery#gemini cli#agent protocol#tool mapping
One-click install
npx skills add https://github.com/Pgooone/oh-pgone-claudecode --skill using-superpowers-pgooone
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/Pgooone/oh-pgone-claudecode/tree/main/.claude/plugins/cache/superpowers-marketplace/superpowers/5.0.6/skills/using-superpowers
Command: npx skills add https://github.com/Pgooone/oh-pgone-claudecode --skill using-superpowers-pgooone

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 and producing inconsistent results. This Skill establishes a mandatory protocol that requires checking for and invoking 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 Framework: Defines instruction precedence 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 rather than jumping straight into code edits, ensuring the correct process is followed. ## 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 for skills before responding?▼

Invoke this skill at conversation start to enforce a rule requiring skill checks before any response, including clarifying questions. Even a 1% chance a skill applies triggers mandatory invocation of the Skill tool.

What happens when user instructions conflict with a skill?▼

User instructions always take precedence over skills. If CLAUDE.md says to skip TDD but a skill mandates it, follow the user's instruction since skills only override default system prompt behavior, not explicit user direction.

Can I use Claude Code skills in Gemini CLI or Codex?▼

Yes, skills activate via activate_skill in Gemini CLI and load natively in Codex. Reference files map Claude Code tool names like Read, Bash, and TodoWrite to each platform's equivalents such as read_file and run_shell_command.

Does Gemini CLI support subagent dispatch from skills?▼

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 config.toml to use spawn_agent.

Which skill should run first when multiple skills apply?▼

Process skills like brainstorming and debugging run first since they determine how to approach the task. Implementation skills like frontend-design run second to guide execution of the chosen approach.

Related Skills

Explore More Software Engineering Skills→
danilonovaisvdanilonovaisv
1

using-superpowers

Load relevant skills before responding across Claude, Copilot, and Gemini.

Community
Advanced
yimwooyimwoo
25

using-hotl

Coordinates HOTL skill-driven workflows for implementation tasks from brainstorm to execute stages.

Community
Advanced
mikeyobrienmikeyobrien

using-superpowers

Enforce mandatory skill usage and checklist workflows before task execution.

Community
Basic
i0switchi0switch

philosophy-first-agent-config

Audit and redesign AGENTS.md, CLAUDE.md, and system prompts into a lean Goal, Philosophy, and Minimal Safeguards template.

Community
Advanced