baoyu-danger-x-to-markdown: a skill that saves tweets and X articles as markdown

baoyu-danger-x-to-markdown makes your agent save an X (Twitter) tweet, thread or article as a markdown file with YAML front matter.

Installs: 28.2K; on skills.sh
Stars: 27.2K; on GitHub
Files: 19; besides SKILL.md
Updated: Nov 2026; last repo commit

Give your agent an x.com or twitter.com status URL, or an X Article URL, and it runs a bundled TypeScript script that fetches the post and writes markdown to ./x-to-markdown/{username}/.... It can also download images and videos next to the file and rewrite the links.

The word "danger" is in the name for a reason. SKILL.md says it uses a reverse-engineered API, not an official one. It requires your consent before the first conversion, and the README warns it may break and that account restrictions are possible. It needs X login cookies, either as environment variables or from a Chrome login window the script opens.

Good for

Researchers and writers who archive tweets and threads as notes
Developers feeding X posts into a notes or knowledge-base folder
Anyone who accepts the risks of an unofficial X API

Install baoyu-danger-x-to-markdown

Claude Code

Copy this prompt.

Install the baoyu-danger-x-to-markdown skill in Claude Code. Run this command:

npx skills add https://github.com/jimliu/baoyu-skills --skill baoyu-danger-x-to-markdown

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js.

From its listing on skills.sh. Source.

What's in the skill

When it loads

Converts X (Twitter) tweets and articles to markdown with YAML front matter. Uses reverse-engineered API requiring user consent. Use when user mentions "X to markdown", "tweet to markdown", "save tweet", or provides x.com/twitter.com URLs for conversion.

Sections in SKILL.md

User Input Tools
Script Directory
Consent Requirement
Consent Flow
Preferences (EXTEND.md)
First-Time Setup (BLOCKING)
Supported Keys
Usage
Options
Supported URLs
Output
Media Download Workflow
Ask-Each-Time Flow
Authentication
Extension Support

Key facts

Author: Jim Liu (JimLiu/baoyu-skills)
Repo: JimLiu/baoyu-skills, path skills/baoyu-danger-x-to-markdown
Installs on skills.sh: 28,151 (as of Nov 2, 2026)
GitHub stars: 27,159 (shared repo, Nov 2, 2026)
License: MIT unless otherwise noted
Version in SKILL.md: 1.117.3
Last repo commit: Nov 1, 2026
skills.sh audits: Gen Agent Trust Hub: pass. Socket: warn. Snyk: fail.
Files: 20 including SKILL.md: a references/config/first-time-setup.md and 18 files under scripts/ (TypeScript, package.json, bun.lock)
Needs: Node.js with npx or bun; X cookies (X_AUTH_TOKEN and X_CT0) or Chrome login

What it includes

Asks you to accept the unofficial-API disclaimer first
Checks a consent.json under your user data folder. If it is missing, shows a disclaimer and creates the file only after you accept.
Write · Consent check
Asks 3 questions and saves an EXTEND.md
Media handling (ask, always, never), default output folder, and whether to save preferences for all projects or this one.
Write · First-time setup
Converts a tweet, thread or X Article to markdown
Runs with bun, or `npx -y bun` when bun is not installed. Accepts x.com or twitter.com status URLs and x.com/i/article URLs.
Runs code · main.ts <url>
Choose the output file or folder
Default is x-to-markdown/{username}/{tweet-id}/{content-slug}.md.
Write · -o <path>
Print JSON output
Includes the markdown path.
--json
Download images and videos locally
Saves to imgs/ and videos/ next to the markdown and rewrites links to relative paths. With the default setting the agent asks first.
Write · --download-media
Refresh cookies only
Opens Chrome so you can log in to X and caches the cookies.
Runs code · --login

From the official docs

Permissions

High risk

It uses your X login cookies with an unofficial API, runs a TypeScript script and can open Chrome. X may restrict an account it sees using this, so use a throwaway account.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

It uses an unofficial X API with your login
SKILL.md and the README say the API is reverse-engineered, may break, and account restrictions are possible. Use a throwaway X account rather than your main one. github.com
It handles X session cookies
The script reads X_AUTH_TOKEN, X_CT0 and related variables, or logs in through a Chrome window and caches cookies in a file. Treat those cookies like a password. github.com
It runs third-party code
Scripts run with bun, or `npx -y bun` if bun is missing. scripts/package.json depends on the npm package baoyu-chrome-cdp, which launches Chrome. github.com
It writes files and downloads media
It saves markdown, a consent file and preferences in EXTEND.md, and with --download-media it saves images and videos from the post. github.com

Technical details

Talks to	x.com and twitter.com. X media hosts when downloading media
Sign-in and keys	Cookies come from the X_AUTH_TOKEN and X_CT0 environment variables or a Chrome login. The script writes a cookie file and a Chrome profile folder under your user data folder.
Scopes	X login cookies (auth_token, ct0)

Questions

What does baoyu-danger-x-to-markdown do?

It makes your agent turn an X tweet, thread or article into a markdown file with YAML front matter (url, author, tweet count, cover image). It can also download the media.

How do I install it in Claude Code?

Use the install command in the box above. The README also lists a plugin marketplace route that brings every skill in the repo, which it says adds context overhead, so installing only the skills you need is the README's advice.

Does it need an X API key?

No key, but it needs your X login. Set X_AUTH_TOKEN and X_CT0 as environment variables, or let it open Chrome so you can log in and it caches the cookies.

Is it safe?

It is high risk by the author's own wording: an unofficial API, X session cookies and a script that opens Chrome. Use a throwaway account, read the disclaimer it shows and keep the cookie file private.

Why is there a consent prompt?

SKILL.md requires consent before any conversion. It stores your acceptance in a consent.json under your user data folder and shows a warning each time.

Where does it save files?

By default in ./x-to-markdown/{username}/{tweet-id}/, or where you point -o. Your first-run answers are saved in an EXTEND.md in the project or your home folder.

What does it support?

Tweets and threads at x.com or twitter.com status URLs, and X Articles at x.com/i/article/<id>.

Information

updated Nov 2, 2026

Repository: jimliu/baoyu-skills
Folder: skills/baoyu-danger-x-to-markdown

jimliu/baoyu-skills skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 4

SKILL.md · github.com
baoyu-skills README · github.com
first-time-setup.md · github.com
scripts/main.ts · github.com