skills.rest
mst-software-vn
mst-software-vnOFFICIAL
Explore all skills by this author →
WebsiteGitHub

using-superpowers

Establishes rules for discovering and invoking skills before any response.

1|Updated Mar 2, 2026
Search Tags:#claude code#workflow enforcement#skill invocation#gemini cli#instruction priority#tool mapping
One-click install
npx skills add https://github.com/mst-software-vn/mst-checkscam --skill using-superpowers-mst-software-vn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/mst-software-vn/mst-checkscam/tree/main/.claude/skills/using-superpowers
Command: npx skills add https://github.com/mst-software-vn/mst-checkscam --skill using-superpowers-mst-software-vn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? AI assistants often skip available skills and answer directly, missing workflows that would improve results. This Skill enforces a mandatory skill-check discipline so relevant skills are invoked before any response or action. ## Core Features & Use Cases - Mandatory Skill Invocation: Requires checking for applicable skills before responding, even for simple questions or clarifications. - Priority Framework: Defines instruction priority (user instructions > skills > system defaults) and skill ordering (process skills before implementation skills). - 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. ## Quick Start Start a new conversation and let this skill ensure the assistant checks for and invokes any relevant skills before responding.

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?▼

Install a skill-enforcement skill that mandates invoking the Skill tool before any response, including clarifying questions. It defines red-flag rationalizations to avoid and a decision flow for skill invocation.

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 follow to guide execution.

Do user instructions override skill instructions?▼

Yes. User instructions in CLAUDE.md, GEMINI.md, AGENTS.md, or direct requests take highest priority. Skills override default system behavior but never override explicit user instructions.

Can Claude Code skills work in Gemini CLI or Codex?▼

Yes, via tool-mapping references that translate Claude Code tool names to platform equivalents, such as activate_skill in Gemini CLI or spawn_agent in Codex. Gemini CLI lacks subagent support, so subagent-based skills fall back to single-session execution.

When should a skill not be invoked?▼

Subagents dispatched to execute a specific task should skip the skill-check skill. Also, if an invoked skill turns out to be irrelevant to the situation, it does not need to be used.

Related Skills

Explore More Software Engineering Skills→
NVIDIANVIDIA
22.1k

nemoclaw-user-skills-coding

Expose NemoClaw documentation as discoverable skills for AI coding assistants.

Official
Basic
makerjackiemakerjackie
1

using-superpowers

Check and invoke relevant skills before responding to user queries.

Community
Intermediate
zMynxxzMynxx

using-superpowers

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

Community
Intermediate
blucsigma05blucsigma05

tbm-prompt-auditor-pass

Route legacy TBM-prefixed prompt auditor invocations to the global skill.

Community
Basic