What problem does it solve? Writing skills for AI agents often produces bloated, duplicated, or unreliable instructions that cause inconsistent agent behavior. This Skill supplies a shared vocabulary and decision framework for structuring, invoking, and pruning skills so agents follow the same process on every run. ## Core Features & Use Cases - Invocation Design: Decide between model-invoked and user-invoked skills by weighing context load against cognitive load, with concrete mechanics like disable-model-invocation. - Information Hierarchy: Organize content into steps, in-skill reference, and disclosed reference behind context pointers, using progressive disclosure and branching as the test. - Failure Mode Diagnosis: Identify and fix premature completion, duplication, sediment, sprawl, no-ops, and negation in existing skills. - Use Case: When a skill you wrote fires unreliably or the agent rushes through steps, consult this reference to sharpen completion criteria, split sequences, or rewrite the description with leading words. ## Quick Start Review my skill file and diagnose which failure modes are hurting its predictability, then suggest concrete edits.
