What problem does it solve? Documents written for agents often produce inconsistent behavior: agents skip steps, finish prematurely, or ignore reference material. This Skill provides a reference framework for writing any document an agent consumes so the agent follows the same process 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 one trigger per branch. - Information hierarchy and progressive disclosure: A ladder for placing steps, in-file reference, and disclosed reference so documents stay legible without hiding needed material. - Completion criteria and splitting: Guidance on writing checkable, exhaustive completion criteria and deciding when to split documents by sequence or invocation. - Use Case: When authoring a new skill or editing an AGENTS.md file, apply the pruning, leading-word, and negation rules to remove no-op sentences and sharpen the agent's behavior. ## Quick Start Ask the agent to review your SKILL.md or AGENTS.md draft using the writing-for-agents reference and rewrite weak pointers and vague completion criteria.
