Reference for writing any document an agent consumes: a skill, an AGENTS.md, a document reached by a pointer. The packaging differs; the writing principles aim for a predictable process across runs rather than identical output.

Before creating or editing a skill or its description, read Anthropic's skill authoring best practices for the current authoring and frontmatter guidance, and skill-mechanics.md for this collection's invocation conventions, splitting, and router skills. If the official page cannot be accessed, report that limitation rather than claiming to have checked its current requirements.

Context pointers

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 document 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 the body:

Front-load the leading word: the pointer is where it does its triggering work.
One trigger per branch. Synonyms that rename a single branch are one branch written twice; collapse them and keep only genuinely distinct branches.
Cut identity the body already carries.

The two loads

Every document and pointer you add spends one of two budgets:

write-for-agents

Context pointers

The two loads