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 behave predictably on every run. ## Core Features & Use Cases - Invocation Design: Guidance on choosing between model-invoked and user-invoked skills, including the trade-offs between context load and cognitive load, and when to use router skills. - Information Hierarchy: A ladder model for arranging steps, in-file reference, and disclosed reference files (like GLOSSARY.md) behind context pointers via progressive disclosure. - Failure Mode Diagnosis: Named failure modes — premature completion, duplication, sediment, sprawl, no-op, and negation — each paired with its cure. - Use Case: When editing an existing skill that has grown too long, use this reference to identify sprawl and sediment, then push reference material behind context pointers and prune no-op lines. ## Quick Start Ask the agent to review your SKILL.md using the writing-great-skills principles and suggest improvements to its description, structure, and pruning.
