What problem does it solve? Writing effective AI skills is hard: descriptions fail to trigger, instructions bloat, and agents behave inconsistently across runs. This Skill provides a shared vocabulary and set of principles for designing, structuring, and pruning skills so the agent follows the same process every run. ## Core Features & Use Cases - Invocation Design: Guidance on choosing between model-invoked and user-invoked skills, and how to write trigger-rich descriptions. - Information Hierarchy: A ladder model for arranging steps and reference material, including progressive disclosure into linked files like GLOSSARY.md. - Failure Mode Diagnosis: Named failure modes (premature completion, duplication, sediment, sprawl, no-op, negation) with concrete cures for each. - Use Case: When reviewing a skill that fires unreliably or runs too long, use this reference to diagnose whether the issue is a weak description, sprawl, or a vague completion criterion, then apply the matching fix. ## Quick Start Ask the agent to review your SKILL.md using the writing-great-skills principles and suggest improvements to its description and structure.
