What problem does it solve? Writing skills for AI agents often produces bloated, unreliable instructions that trigger inconsistently and drift over time. This Skill supplies a shared vocabulary and decision framework for structuring, invoking, and pruning skills so agents behave predictably on every run. ## Core Features & Use Cases - Invocation Design: Decide between model-invoked and user-invoked skills by weighing context load against cognitive load, and write trigger-rich descriptions. - Information Hierarchy: Organize content into steps, in-file reference, and disclosed reference behind context pointers, using progressive disclosure and co-location. - Failure Diagnosis: Identify and fix failure modes such as premature completion, duplication, sediment, sprawl, no-ops, and negation. - Use Case: When a skill you wrote fires unreliably or has grown to hundreds of lines, consult this reference to restructure its hierarchy, sharpen completion criteria, and prune dead content. ## Quick Start Ask the agent to review your SKILL.md using the writing-great-skills principles and suggest improvements to its structure and description.
