Documentation

edit-package-readme - Claude MCP Skill

Create or edit package README.md files in the AI SDK monorepo.

SEO Guide: Enhance your AI agent with the edit-package-readme tool. This Model Context Protocol (MCP) server allows Claude Desktop and other LLMs to create or edit package readme.md files in the ai sdk monorepo.... Download and configure this skill to unlock new capabilities for your AI workflow.

🌟164 stars • 5508 forks
📥0 downloads

Documentation

SKILL.md
# Package READMEs

Keep `README.md` files minimal; they must not contain documentation beyond simple starting points. Detailed documentation belongs exclusively in `content/` and lives under `https://ai-sdk.dev/docs`.

Every package `README.md` file must contain the following, in the given order:

1. An H1 on the first line that starts with `# AI SDK - `, followed by a descriptive package title rather than its npm identifier.
2. A 1–2 sentence description.
3. Optional note about compatibility, AI Gateway, or experimental nature. Consult similar packages and match their formatting; if in doubt, do not add one.
4. `## Setup`: only one fenced, one-line `npm i` command, including necessary related packages.
5. Optional `## Skill for Coding Agents` section between `## Setup` and `## Usage`, with a short recommendation and one fenced shell command to add the AI SDK skill to the repository.
6. `## Usage`: only one fenced, basic getting-started code example (TypeScript or a framework component with TypeScript).
7. A suitable docs link using `See the [<package title> documentation](<url>) for more information.` If none clearly fits, use 1–2 related docs links with custom phrasing.

You must not include anything else in the readme. Any additional documentation belongs in `content/`.

## Template

Omit the optional note and `## Skill for Coding Agents` section when they do not apply.

````markdown
# AI SDK - <Package Title>

A brief description of the package.

-> **Note**: <Optional compatibility or experimental notice.>

## Setup

```bash
npm i <npm-package>
```

## Skill for Coding Agents

If you use coding agents such as Claude Code or Cursor, we highly recommend adding the AI SDK skill to your repository:

```shell
npx skills add vercel/ai
```

## Usage

```ts
import { example } from '<npm-package>';

await example();
```

See the [<package title> documentation](https://ai-sdk.dev/...) for more information.
````

## Exceptions

These packages have special-case `README.md` files and do not follow this format:

- `ai`
- `codemod`
- `provider-utils`
- `provider`

Never consult these files for which `README.md` conventions to follow.

## Verification

Run the verification script to ensure all `README.md` files adhere to the conventions:

```bash
./tools/verify-package-readme-files.mjs
```

If this script shows errors, you must address them, then rerun the verification script until it passes.

Signals

Avg rating⭐ 0.0
Reviews0
Favorites0

Information

Repository
vercel/ai
Author
vercel
Last Sync
11/3/2026
Repo Updated
11/3/2026
Created
10/24/2026

Reviews (0)

No reviews yet. Be the first to review this skill!

Related Skills

firecrawl-build-onboarding

Get Firecrawl credentials and SDK setup into a project. Use when an application needs `FIRECRAWL_API_KEY`, when an agent should add Firecrawl to `.env`, when the user wants to authenticate Firecrawl for app code, or when choosing the first SDK and docs for a new Firecrawl integration. This skill includes its own browser auth flow, so it does not depend on the website onboarding skill.

⭐ 39648

firecrawl-build-scrape

Integrate Firecrawl `/scrape` into product code for single-page extraction. Use when an app already has a URL and needs markdown, HTML, links, screenshots, metadata, or structured page output. Prefer this skill over broader crawl patterns when the feature is page-level.

⭐ 39648

firecrawl-build-search

Integrate Firecrawl `/search` into product code and agent workflows. Use when an app needs discovery before extraction, when the feature starts with a query instead of a URL, or when the system should search the web and optionally hydrate result content.

⭐ 39648

firecrawl-build

Integrate Firecrawl into application code whenever a product, agent, or workflow needs web data inside the app — web search, live search results, page scraping, structured extraction, or browser interaction. Use when building any feature that needs data from the web in code, even if the user does not mention Firecrawl explicitly and only describes wanting web data, website content, search, scraping, or interaction in an application. Trigger for Firecrawl requests, "fire girl" shorthand, and generic app-level web-data needs that should map to `/scrape`, `/search`, or `/interact`. Do not use this skill for one-off terminal-only web tasks during the current session; use `firecrawl/cli` for those.

⭐ 39648

Related Guides