using-skills

Overview

This skill enforces the discipline of skill invocation, preventing the agent from shortcutting workflows or rationalizing its way out of using available frameworks. It is the core defensive mechanism against AI overconfidence and drift.

Iron Law

IF THERE IS EVEN A 1% CHANCE A SKILL APPLIES, INVOKE IT AI models are biased toward immediate generation over reference-checking. This rule forces a "pause and check" behavior that prevents low-quality, ungrounded output.

State Machine

digraph using_skills_flow {
    "Task Received" [shape=doublecircle];
    "Step 1: Check Skill Database" [shape=box];
    "Decision: Is it ≥ 1%?" [shape=diamond];
    "Step 2: Propose Skill to User" [shape=box];
    "Step 3: Apply Skill Logic" [shape=box];
    "Done" [shape=doublecircle];

    "Task Received" -> "Step 1: Check Skill Database";