What problem does it solve? Documents written for AI agents often fail unpredictably: agents miss referenced material, rush steps, or get lost in bloated files. This Skill provides a systematic reference for writing agent-facing documents so the agent follows the same process every run. ## Core Features & Use Cases - Context pointer design: Rules for writing descriptions and references that reliably trigger the agent to reach out-of-context material at the right branch. - Information hierarchy: A ladder model (in-file steps, in-file reference, disclosed reference) plus progressive disclosure and co-location to keep documents legible and focused. - Completion criteria and splitting: Guidance on sharpening step completion conditions, preventing premature completion, and deciding when to split documents by sequence or invocation. - Use Case: When authoring a new skill or CLAUDE.md file, apply the leading-words, pruning, and negation-avoidance rules to produce a document the agent executes predictably. ## Quick Start Ask the agent to review your draft skill or AGENTS.md file using the writing-for-agents principles and suggest concrete revisions.
