What problem does it solve? Documents written for AI agents often fail unpredictably: weak descriptions never trigger, bloated files bury key steps, and vague completion criteria let agents stop early. This Skill provides a reference of writing principles that make agent-facing documents behave consistently across runs. ## Core Features & Use Cases - Context pointer design: Rules for writing skill descriptions and AGENTS.md pointers that reliably trigger the right material, with one trigger per branch and front-loaded leading words. - Information hierarchy: A ladder model (in-file steps, in-file reference, disclosed reference) plus progressive disclosure and co-location guidance to keep documents legible without hiding needed material. - Completion criteria and splitting: Techniques for sharpening step completion conditions, deciding when to split documents by sequence or invocation, and configuring model-invoked versus user-invoked skills. - Use Case: When authoring a new skill or editing an AGENTS.md file, consult this reference to prune no-op sentences, replace restatements with leading words, and structure frontmatter so the agent discovers the document at the right time. ## Quick Start Ask the agent to review your draft SKILL.md or AGENTS.md using the writing-for-agents principles and suggest concrete revisions.
