What problem does it solve? Documents written for AI agents often fail unpredictably: agents miss referenced material, rush steps, or drown in bloated files. This Skill provides a systematic reference for writing agent-facing documents (skills, AGENTS.md, CLAUDE.md) so the agent follows the intended process reliably on every run. ## Core Features & Use Cases - Context pointer design: Rules for writing descriptions and pointer lines that reliably trigger the agent to reach out-of-context material, with branch-based trigger wording. - Information hierarchy guidance: A ladder model (in-file steps, in-file reference, disclosed reference) plus progressive disclosure and co-location principles to keep documents legible and focused. - Completion criteria and splitting: Techniques for writing checkable, exhaustive step completion criteria, and deciding when to split documents by sequence or invocation. - Use Case: When authoring a new agent skill, use this reference to write a sharp description, structure steps with clear completion criteria, push reference material behind pointers, and choose between model-invoked and user-invoked invocation via SKILL-MECHANICS.md. ## Quick Start Ask the agent to review your draft SKILL.md or AGENTS.md using the writing-for-agents guidance and suggest improvements to its description, structure, and step completion criteria.
