What problem does it solve? AI agents often skip relevant skills and respond directly, missing established workflows and producing inconsistent results. This Skill establishes a mandatory protocol that requires checking for and invoking applicable skills before any response, including clarifying questions. ## Core Features & Use Cases - Mandatory Skill-First Rule: Requires invoking any potentially relevant skill (even at 1% likelihood) before responding or acting, with a decision flowchart and a red-flags table that counters rationalizations for skipping skills. - Instruction Priority Hierarchy: Defines a clear precedence order where user instructions (CLAUDE.md, AGENTS.md, GEMINI.md) override skills, and skills override default system prompt behavior. - Cross-Platform Tool Mappings: Ships reference guides mapping generic skill actions (dispatch subagent, create todo, read file) to concrete tools in Claude Code, Codex, Copilot CLI, Gemini CLI, Pi, and Antigravity. - Use Case: An agent receives a request to fix a bug. Instead of diving into the code, it first invokes the systematic-debugging skill, announces its use, creates todos from the skill checklist, and follows the workflow exactly. ## Quick Start Start any conversation by checking which skills might apply to the user's request and invoke the matching skill before responding.
