What problem does it solve? Agent skills often behave unpredictably across runs because their instructions, descriptions, and structure are poorly designed. This Skill provides a shared vocabulary and concrete principles for writing and editing skills so agents follow the same process every time. ## Core Features & Use Cases - Invocation Design: Decide between model-invoked and user-invoked skills by weighing context load against cognitive load, and configure disable-model-invocation accordingly. - Information Hierarchy: Organize content into steps, in-file references, and disclosed references behind context pointers, using progressive disclosure to keep SKILL.md lean. - Failure-Mode Diagnosis: Identify and fix premature completion, duplication, sediment, sprawl, no-op instructions, and negation using the paired glossary in GLOSSARY.md. - Use Case: When a skill you wrote triggers unreliably or the agent rushes through steps, consult this guide to sharpen completion criteria, rewrite the description with leading words, and split sequences that cause premature completion. ## Quick Start Ask the agent to review your SKILL.md against the writing-great-skills principles and suggest concrete edits to improve predictability.
