What problem does it solve? Documents written for AI agents often fail unpredictably: bloated context, weak triggers that never fire, duplicated guidance, and instructions the model already follows by default. This Skill provides a systematic framework for writing any document an agent consumes so it behaves predictably on every run. ## Core Features & Use Cases - Context pointer design: Craft descriptions and references that reliably trigger the right material at the right branch, with front-loaded leading words and one trigger per branch. - Information hierarchy management: Apply progressive disclosure, co-location, and pruning to decide what stays inline versus what moves behind a pointer into disclosed reference files. - Completion criteria and splitting: Define clear, demanding completion criteria for steps and decide when to split documents by sequence or invocation. - Use Case: When authoring a new skill or editing an AGENTS.md file, use this Skill to sharpen the description trigger, push branch-specific detail into referenced files like SKILL-MECHANICS.md, and prune no-op sentences that add load without changing behavior. ## Quick Start Ask the agent to review your draft skill or AGENTS.md file using the writing-for-agents guidance to sharpen triggers, prune redundancy, and fix the information hierarchy.
