> ## Documentation Index > Fetch the complete documentation index at: https://app.keystroke.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Create skills > Write a SKILL.md with clear task guidance. A skill is a folder under `src/skills/` containing a `SKILL.md` and any supporting references. This page covers the format and the conventions that keep a skill useful. ## Create the folder Make a folder named for the skill (the folder name is how you'll [attach it to an agent](/learn/skills/attach-skills-to-agents)) and add a `SKILL.md`: ``` src/skills/support/ SKILL.md references/ refund-policy.md ``` ## Write SKILL.md A `SKILL.md` follows the [Agent Skills specification](https://agentskills.io/specification): YAML frontmatter with a `name` and a `description`, then a focused body. ```md src/skills/support/SKILL.md theme={null} --- name: support description: Support playbook for product questions and refund policy. --- # Support skill Read this skill when answering customer support questions. Follow the refund policy in the product guide and keep replies concise. Escalate billing disputes over $500 to a human. ``` | Frontmatter | What it does | | ------------- | --------------------------------------------------------- | | `name` | The skill's name; match it to the folder name | | `description` | A short summary of *when* the agent should use this skill | The `description` matters: it's what an agent uses to decide whether a skill is relevant, so describe the situation it applies to, not just what it contains. ## Keep the body short, push detail to references Skills work by **progressive disclosure**: the agent reads the short `SKILL.md` first, then loads deeper material only when the task needs it. Keep `SKILL.md` to the essentials and put long policies, examples, and edge cases in a `references/` folder: ``` src/skills/support/ SKILL.md # when to use it + the key rules references/ refund-policy.md # the full policy escalation-matrix.md # detailed procedures ``` Reference files are a convention, not a fixed structure; name and organize them however reads best. Everything in the skill folder is materialized into the agent's workspace at `/workspace/agent/skills/{slug}/`, so the agent can open a reference by path when it decides it needs it. References aren't the only kind of supporting material. The whole folder is copied verbatim, so a skill can also ship helper scripts the agent runs with its shell tools, or assets like templates and fixtures it reads: ``` src/skills/report/ SKILL.md references/format.md scripts/build-report.ts assets/template.html ``` Point the agent at them by path from `SKILL.md`. ## Point the agent at the skill A skill is available to an agent once you attach it, but you'll often nudge the agent toward it in the `systemPrompt` so it knows the skill exists and when to reach for it: ```ts theme={null} systemPrompt: "Answer support questions. Use the support skill for policy and tone.", ``` ## Next steps Attach a skill to an agent by folder name. What project skills are and when to use them. Reuse skills from external registries. Add static reference documents to a workspace.