What problem does it solve? Writing skills for AI agents often produces bloated, unreliable instructions that fire inconsistently or steer the agent unpredictably. This Skill supplies a shared vocabulary and set of principles for authoring and editing skills so the agent follows the same process on every run. ## Core Features & Use Cases - Invocation Design: Guidance on choosing between model-invoked skills (with a description, agent-discoverable) and user-invoked skills (typed by hand, zero context load), including router skills for managing many user-invoked ones. - Information Hierarchy: A ladder model for arranging steps, in-file reference, and disclosed reference behind context pointers, with progressive disclosure and co-location rules. - Failure Mode Diagnosis: Named failure modes — premature completion, duplication, sediment, sprawl, no-op, and negation — each paired with its cure, plus a full glossary in GLOSSARY.md. - Use Case: When editing an existing skill that the agent triggers inconsistently, consult this reference to sharpen the description's trigger wording, prune no-op lines, and split sequences that cause premature completion. ## Quick Start Review my skill file and apply the writing-great-skills principles to make it more predictable.
