What problem does it solve? AI agents often skip available skills and improvise responses, leading to inconsistent workflows and missed process discipline. This Skill establishes a mandatory protocol requiring the agent to check for and invoke applicable skills before any response, including clarifying questions. ## Core Features & Use Cases - Mandatory Skill Invocation: Requires calling the Skill tool whenever there is even a 1% chance a skill applies, with a decision flowchart and a red-line table of rationalizations to reject. - Instruction Priority Hierarchy: Defines precedence between user instructions (CLAUDE.md, GEMINI.md, AGENTS.md), superpowers skills, and default system prompts. - Cross-Platform Tool Mapping: Ships reference files mapping Claude Code tool names to Copilot CLI, Gemini CLI, Hermes Agent, Codex, and Qoder equivalents. - Use Case: When a user asks to fix a bug in a Chinese-language project, the agent first invokes the debugging skill, then routes to Chinese-specific skills like chinese-commit-conventions for the commit message. ## Quick Start Ask the agent to start any task and it will first check for applicable skills, announce which skill it is using, and follow that skill's checklist before responding.
