What problem does it solve? Documents written for AI agents often fail unpredictably: agents miss referenced material, rush steps, or get buried under bloated files. This Skill provides a systematic reference 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 descriptions and pointer lines that front-load trigger words, cover one branch per trigger, and control when agents reach out-of-context material. - Information hierarchy and progressive disclosure: A ladder model (in-file steps, in-file reference, disclosed reference) for deciding what stays inline versus what moves behind a pointer, plus co-location and sprawl guidance. - 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 creating a new skill or editing an AGENTS.md file, apply the leading-words, pruning, and negation-avoidance rules to produce a lean document the agent follows deterministically. ## Quick Start Use the writing-for-agents skill to review and improve the skill file I am drafting.
