skills sourced live from GitHub · all skills listed are free · each skill is provided under its author's license.
home / Agent Skills / Writing For Agents Skill by @mattpocock
The skill is the skills/productivity/writing-for-agents folder inside that repository. Copy it into the folder your agent loads skills from; check your agent's documentation for where that is.
Writing documents for agents.
Guidance for writing the documents agents read: skills, AGENTS.md and CLAUDE.md. It covers context pointers, information hierarchy, completion criteria, when to split a file and leading words.
The original SKILL.md is organised into these sections:
Written and maintained by @mattpocock. It is published under the MIT license, which allows reuse with attribution. See the author profile. SkillDirectory does not claim authorship: this page adds our own review and links back to the original, and the skill's text belongs to its author.
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`](SKILL-MECHANICS.md) for frontmatter, invocation choice, and router skills. ## 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 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. …
Excerpt only, quoted from the author's repository. Open the repository for the complete file.