What problem does it solve? Documents written for AI agents often fail unpredictably: weak descriptions never trigger, bloated files dilute attention, and vague steps invite premature completion. This Skill provides a reference framework for writing any document an agent consumes so the agent follows the same process reliably on every run. ## Core Features & Use Cases - Context pointer design: Rules for writing skill descriptions and AGENTS.md lines that front-load trigger words and list distinct branches so material is reached reliably. - Information hierarchy: A ladder model (in-file steps, in-file reference, disclosed reference) plus progressive disclosure and co-location guidance to fight document sprawl. - Completion criteria and splitting: Techniques for writing checkable, exhaustive step boundaries and deciding when to split documents by sequence or invocation. - Skill mechanics: A companion file covers frontmatter, model-invoked versus user-invoked skills, and router skills. - Use Case: When authoring a new skill or editing CLAUDE.md, apply the pruning, leading-word, and negation-avoidance rules to cut token load while sharpening agent behavior. ## Quick Start Ask the agent to review your draft skill or AGENTS.md file using the writing-for-agents guidelines and suggest improvements.
