writing-for-agents

原文涵盖的主题

• Context pointers
• The two loads
• Information hierarchy
• Steps and completion criteria
• When to split
• Leading words
• Pruning

Reference for writing any document an agent consumes: a skill, an AGENTS.md / CLAUDE.md, a doc reached by a pointer. The packaging differs; the writing does not: the same levers make each one predictable, since the agent takes the same process every run rather than producing the same output. When the document you're writing is a skill, read SKILL-MECHANICS.md for frontmatter, invocation choice, and router skills. A context pointer is a reference held in the agent's context that names some out-of-context material and encodes the condition for reaching it. A skill's description is one; a line in AGENTS.md naming a doc is the same object. The pointer's wording, not its target, decides when the agent reaches the material, and how reliably. A must-have target behind a weakly worded pointer is a variance bug: sharpen the wording first, and inline the material only if sharpening fails. A pointer does two jobs: state what the material is, and list the branches that should trigger reaching it (a branch is a distinct case the document handles, so different runs take different paths through it). Every word of an always-loaded pointer costs on every turn, so it earns even harder pruning than t

这里只展示节选，请以完整原文和当前要求为准。