What problem does it solve? Writing effective skills for AI agents is hard: descriptions fail to trigger, instructions bloat, and agents behave inconsistently across runs. This Skill supplies a shared vocabulary and a set of principles for designing, structuring, and pruning skills so the agent follows the same process every run. ## Core Features & Use Cases - Invocation Design: Explains the trade-off between model-invoked skills (agent-discoverable, paying context load) and user-invoked skills (human-triggered, paying cognitive load), including router skills for managing many user-invoked skills. - Information Hierarchy: Defines how to rank content into steps, in-file reference, and disclosed reference behind context pointers, using progressive disclosure and co-location to keep SKILL.md legible. - Failure Mode Diagnosis: Catalogs predictable failure modes — premature completion, duplication, sediment, sprawl, no-ops, and negation — each paired with its cure. - Use Case: When editing a skill whose agent keeps skipping steps, consult the failure modes section to diagnose premature completion and apply the fix: 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 improvements to its description, structure, and pruning.
