What problem does it solve? Documents written for agents often fail unpredictably: bloated files bury key steps, weak descriptions never trigger, and duplicated guidance drifts out of sync. This Skill provides a reference framework 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: Write descriptions and references whose wording controls when the agent reaches the material, with one trigger per branch. - Information hierarchy: Place content on the right tier — in-file steps, in-file reference, or disclosed reference behind a pointer — using progressive disclosure and co-location. - Completion criteria and splitting: End every step with a clear, demanding completion criterion, and split documents by sequence or invocation to prevent premature completion. - Skill mechanics: A companion file covers frontmatter, model-invoked versus user-invoked skills, and router skills. - Use Case: When authoring a new skill or editing an AGENTS.md, apply the pruning rules to remove no-op sentences, replace restatements with leading words, and keep a single source of truth for each behavior. ## Quick Start Ask the agent to review your SKILL.md or AGENTS.md using the writing-for-agents reference and tighten its description, structure, and pruning.
