Agent Surface
Discovery & AEO

Agent Skills

Packaging reusable agent instructions, scripts, references, and assets.

Agent Skills are portable capability folders for agents. A skill teaches an agent how to do a specific task without putting every instruction into the base prompt.

Use Agent Skills when a workflow is repeatable, procedural, and specific enough that a general docs page is not enough. Good skills are narrow: "create a scoped API token", "run the design review workflow", "prepare a migration PR". They are not broad knowledge dumps.

Folder Shape

A portable skill is a folder with a SKILL.md entrypoint:

create-api-token/
├── SKILL.md
├── references/
│   └── scopes.md
├── scripts/
│   └── validate-token.ts
└── assets/
    └── token-flow.png

SKILL.md carries metadata and the primary instructions:

---
name: create-api-token
description: Use when an agent needs to create a scoped API token for automation.
---

# Create API Token

## Steps

1. Read `references/scopes.md`.
2. Ask for the minimum required scope.
3. Create the token through the settings API.
4. Run `scripts/validate-token.ts` before returning it to the caller.

## Safety

- Never create admin-scoped tokens unless explicitly requested.
- Never print token values into logs.

The name and description fields are the minimum portable metadata. Add scripts, references, and assets only when they help the agent perform the task correctly.

Progressive Disclosure

Skills work because agents can index a lightweight catalog first, then load the full skill only when needed.

That means descriptions matter. Write them as routing instructions:

WeakBetter
API tokensUse when an agent needs to create, validate, or rotate scoped API tokens for automation.
Design reviewUse when reviewing a rendered web page for visual, responsive, and interaction issues.
MigrationUse when preparing a database migration PR with schema diff, rollback notes, and verification steps.

Do not inline every workflow into a catalog file. Point to the skill and let the agent load details only when the task calls for it.

Publishing Skills

For public sites, expose a skill index:

{
  "skills": [
    {
      "id": "create-api-token",
      "name": "Create API Token",
      "description": "Use when an agent needs to create a scoped API token for automation.",
      "format": "agent-skill",
      "url": "https://example.com/.well-known/agent-skills/create-api-token/SKILL.md"
    }
  ]
}

Publish it at:

/.well-known/agent-skills/index.json

Only publish skills that are real, reviewed, and kept current with the product.

Skills Vs Other Files

FileRole
AGENTS.mdRepository-level operating instructions for coding agents.
llms.txtSite/docs index for retrieval.
SKILL.mdTask-specific instructions, scripts, references, and assets.
MCP server cardConnection metadata for a tool server.
OpenAPIHTTP API contract.

Skills complement MCP. MCP exposes callable tools; skills teach an agent when and how to use a workflow.

On this page