What problem does it solve? Documents written for AI agents often fail unpredictably: agents skip instructions, rush steps, or ignore buried reference material. This Skill provides a systematic reference for writing agent-facing documents so the agent follows the same process every run. ## Core Features & Use Cases - Context pointer design: Write descriptions and pointers whose wording reliably triggers the agent to reach the right material at the right branch. - Information hierarchy and progressive disclosure: Decide what stays inline as steps, what becomes in-file reference, and what moves behind a pointer into separate files. - Completion criteria and splitting: Define clear, demanding done-conditions for each step and split documents by sequence or invocation to prevent premature completion. - Use Case: When authoring a new skill or editing an AGENTS.md file, apply the leading-word, pruning, and co-location rules to produce a shorter document the agent follows more consistently. ## Quick Start Ask the agent to review your draft skill or AGENTS.md file using the writing-for-agents guidance and suggest improvements to its pointers, steps, and structure.
