skill-using-superpowers

Selects and invokes applicable repository skills before acting on tasks.

Updated Apr 9, 2026
One-click install
npx skills add https://github.com/longdang193/project-OS-starter --skill skill-using-superpowers-longdang193
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-using-superpowers
Source: https://github.com/longdang193/project-OS-starter/tree/main/generated_agents/claude/skills/skill-using-superpowers
Command: npx skills add https://github.com/longdang193/project-OS-starter --skill skill-using-superpowers-longdang193

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? AI coding agents often skip documented repository procedures and act ad hoc, producing inconsistent results. This Skill enforces a discipline of checking for and invoking applicable skills before any action, so established workflows are followed instead of rationalized away. ## Core Features & Use Cases - Skill Selection Gate: A decision flow that checks whether a rule or request selects a skill before responding, with a red-flags table that catches common rationalizations for skipping skills. - Priority and Type Rules: Defines ordering when multiple skills apply (process skills before implementation skills) and distinguishes rigid skills (follow exactly) from flexible ones (adapt principles). - Cross-Platform Tool Mappings: Reference files map generic skill actions (read a file, dispatch a subagent, create a todo) to concrete tools in Claude Code, Codex, Copilot CLI, Gemini CLI, Pi, and Antigravity. - Use Case: A user asks an agent to fix a bug; the agent checks installed skills first, invokes the systematic-debugging skill, announces its use, and follows it exactly rather than improvising. ## Quick Start Before starting any task, check which repository skills apply and invoke the matching one, announcing which skill you are using and why.

Frequently Asked Questions about skill-using-superpowers

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I make an AI agent use repository skills before acting?▼

Install a skill-selection skill that runs a trigger check on every user message before any action. When a documented trigger matches, the agent invokes the skill, announces its use, and follows it exactly instead of improvising.

What is the difference between rigid and flexible skills?▼

Rigid skills like TDD or systematic-debugging must be followed exactly without adapting away their discipline. Flexible skills describe patterns whose principles can be adapted to context. The skill itself states which type it is.

How do skills map to tools in Claude Code versus Codex?▼

Skills express generic actions like read a file or dispatch a subagent. Reference files map these to platform tools: Read, Write, and Agent in Claude Code; exec_command, apply_patch, and spawn_agent in Codex, with similar tables for other runtimes.

Does Gemini CLI support subagent dispatch from skills?▼

No. Gemini CLI has no equivalent to Claude Code's Task tool, so parallel-agent dispatch lanes must run serially. The agent should report that execution was not parallel when subagent dispatch is unavailable.

When should a skill not be invoked?▼

Do not invoke a skill when no documented trigger matches the task, even if it seems applicable. Skills also never override higher-priority system, developer, user, or repository instructions when conflicts arise.