What problem does it solve? Documents written for AI agents often fail unpredictably: agents skip instructions, rush steps, or ignore reference material. This Skill provides a systematic reference for writing agent-facing documents — skills, AGENTS.md, CLAUDE.md — so the agent follows the same process reliably on every run. ## Core Features & Use Cases - Context pointer design: Write descriptions and pointer lines whose wording controls when the agent reaches out-of-context material, with one trigger per branch. - Information hierarchy: Organize content into in-file steps, in-file reference, and disclosed reference behind pointers, using progressive disclosure and co-location to prevent sprawl. - Completion criteria and splitting: Define clear, demanding completion criteria 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 pruning rules (single source of truth, no-op detection, leading words) to cut token load while sharpening agent behavior. ## Quick Start Ask the agent to review your SKILL.md or AGENTS.md draft using the writing-for-agents guidance and suggest improvements to its pointers, structure, and completion criteria.
