What problem does it solve? Documents written for AI agents often produce inconsistent behavior: weak descriptions fail to trigger skills, bloated files bury key steps, and vague completion criteria let agents stop early. This Skill provides a reference of writing techniques that make agent-consumed documents predictable across runs. ## Core Features & Use Cases - Context pointer design: Write skill descriptions and AGENTS.md lines that reliably trigger the right material by front-loading leading words and mapping one trigger per branch. - Information hierarchy guidance: Decide what stays inline as steps or reference versus what gets disclosed behind pointers into separate files, preventing document sprawl. - Completion criteria and splitting: Sharpen step boundaries to prevent premature completion, and split documents by sequence or invocation when the cut earns its context or cognitive load. - Use Case: When authoring a new skill, use this reference to write a description that fires on the right prompts, prune no-op sentences the model already obeys, and consult SKILL-MECHANICS.md for frontmatter and model- versus user-invocation trade-offs. ## Quick Start Use the writing-for-agents skill to review and improve the description and structure of my new skill's SKILL.md file.
