What problem does it solve? Documents written for agents often fail unpredictably: weak descriptions never trigger, bloated files dilute attention, and vague steps invite premature completion. This Skill provides a reference framework for writing any agent-consumed document — skills, AGENTS.md, CLAUDE.md, or pointer-reached docs — so the agent follows the same process reliably every run. ## Core Features & Use Cases - Context pointer design: Rules for writing descriptions and pointer lines that front-load trigger words, carry one trigger per branch, and control when material gets loaded. - Information hierarchy: A ladder model (in-file steps, in-file reference, disclosed reference) plus progressive disclosure and co-location guidance to fight document sprawl. - Completion criteria and splitting: Techniques for writing checkable, demanding step boundaries and deciding when to split documents by sequence or invocation. - Skill mechanics reference: Companion file SKILL-MECHANICS.md covers frontmatter, model-invoked vs user-invoked skills, and router skills. - Use Case: When authoring a new agent skill, use this reference to write a description that triggers on the right branches, keep the body lean by disclosing reference material behind pointers, and choose the correct invocation mode. ## Quick Start Ask the agent to apply the writing-for-agents reference to review and improve the SKILL.md file you are currently drafting.
