What problem does it solve? Writing effective skills for AI agents is hard: descriptions that never trigger, bloated SKILL.md files, agents that rush steps or ignore instructions. This Skill provides a shared vocabulary and a set of design principles for diagnosing and fixing these problems so skills behave predictably on every run. ## Core Features & Use Cases - Invocation design: Guidance on choosing between model-invoked and user-invoked skills, and how to write descriptions that trigger reliably. - Information hierarchy: A ladder model (steps, in-file reference, disclosed reference) for deciding what stays in SKILL.md and what moves behind a context pointer, as practiced by its own GLOSSARY.md disclosure. - Failure-mode diagnosis: Named failure modes — premature completion, duplication, sediment, sprawl, no-op, negation — each paired with its cure. - Use Case: When an agent keeps skipping steps in your skill, consult this reference to sharpen the completion criterion or split the sequence to hide post-completion steps. ## Quick Start Ask the agent to review your SKILL.md using the writing-great-skills principles and suggest concrete improvements.
