Baoyu Danger X To Markdown

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...

Security Scan

The skill largely does what it says (convert X/Twitter content to markdown), but it reads/writes sensitive local files and environment variables that the registry metadata does not declare and will execute bundled TypeScript via bun/npx (which may fetch code at runtime). Review consent, cookie handling, and any tokens before installing.

Purpose & Capability

The name/description match the code: the repository contains TypeScript that fetches X/Twitter content (via reverse-engineered GraphQL endpoints), formats it to Markdown, and optionally downloads media. Requiring access to cookies or a bearer token is coherent with the stated purpose (to access protected or rate-limited content). However, the registry metadata lists no required environment variables while the code reads multiple X_* env vars (e.g., X_AUTH_TOKEN, X_CT0, X_BEARER_TOKEN, X_USER_AGENT, X_CLIENT_TRANSACTION_ID) — that mismatch is a transparency issue.

Instruction Scope

Runtime instructions and code perform actions beyond simple HTTP fetches: they read and write consent and preference files in user config directories (~/.baoyu-skills, ~/.local/share or macOS Library paths), read cookie files, may launch or attach to Chrome via CDP to capture cookies, and can write a cookie file containing auth tokens. The SKILL.md requires an interactive consent/first-time setup flow, but the code also loads credentials from environment variables and logs partial cookie values. All of this is within the functional scope but raises privacy concerns because sensitive credentials and local files are accessed and created.

Install Mechanism

There is no formal install spec, but the skill ships executable TypeScript in scripts/ and expects to be run with bun or via `npx -y bun`. That means if bun isn't installed the runtime will invoke npx which can pull packages from npm at execution time. There are no remote download URLs in the manifest itself and no use of obscure download hosts, but the npx fallback implies runtime downloading of tooling (moderate risk) and the shipped code will be executed on the user's machine.

Credentials

Registry metadata declares no required environment variables, yet the code reads many X_* environment variables (X_AUTH_TOKEN, X_CT0, X_GUEST_TOKEN, X_TWID, X_BEARER_TOKEN, X_USER_AGENT, X_CLIENT_TRANSACTION_ID, X_CHROME_PATH, X_DEBUG_PORT). Those env vars are sensitive (auth tokens/cookies) and the skill will use them if present. The skill also writes cookie and preference files to user directories. The requested/used environment surface is significant and not documented in the metadata — a transparency and privilege concern.

Persistence & Privilege

always:false and user-invocable:true (normal). The skill writes consent/EXTEND.md and a cookie file to user config locations and may persist cookies captured via CDP. It does not appear to modify other skills or system-wide agent settings, but it will store credentials locally and can relaunch/attach to Chrome. This persistent storage of auth cookies is expected for the functionality but increases the attack surface and requires user care.

What to consider before installing

This skill implements a reverse‑engineered X/Twitter client and will try to obtain/use auth cookies and tokens to fetch content. Before installing or running: - Don't supply real account tokens to untrusted code; prefer a throwaway account if you need to log in. - Expect the skill to write files to your home config dirs (~/.baoyu-skills, ~/.local/share, or macOS Library paths) and to create a cookie file containing X auth cookies. It will also create EXTEND.md and a consent file. - If bun is not installed the skill will use `npx -y bun`, which downloads code from npm at runtime — be aware of this behavior. - The SKILL.md declares a consent prompt, but the registry metadata does not list the environment variables the code will read; assume the skill will honor any X_* env vars present. - If you need this functionality but are uncomfortable with cookie persistence, inspect the code locally, run it in an isolated environment (container or VM), or avoid providing credentials and accept limited/no-auth operation. If you want me to, I can point to the exact file paths the skill will create, list the env vars the code checks for, or highlight the lines where cookie handling and file writes occur.

X to Markdown

Converts X content to markdown:

• Tweets/threads → Markdown with YAML front matter
• X Articles → Full content extraction

User Input Tools

When this skill prompts the user, follow this tool-selection rule (priority order):

1. Prefer built-in user-input tools exposed by the current agent runtime — e.g., AskUserQuestion, request_user_input, clarify, ask_user, or any equivalent.
2. Fallback: if no such tool exists, emit a numbered plain-text message and ask the user to reply with the chosen number/answer for each question.
3. Batching: if the tool supports multiple questions per call, combine all applicable questions into a single call; if only single-question, ask them one at a time in priority order.

Concrete AskUserQuestion references below are examples — substitute the local equivalent in other runtimes.

Script Directory

Scripts located in scripts/ subdirectory.

Path Resolution:

1. {baseDir} = this SKILL.md's directory
2. Script path = {baseDir}/scripts/main.ts
3. Resolve ${BUN_X} runtime: if bun installed → bun; if npx available → npx -y bun; else suggest installing bun

Consent Requirement

Before any conversion, check and obtain consent.

Consent Flow

Step 1: Check consent file

# macOS
cat ~/Library/Application\ Support/baoyu-skills/x-to-markdown/consent.json

# Linux
cat ~/.local/share/baoyu-skills/x-to-markdown/consent.json

Step 2: If accepted: true and disclaimerVersion: "1.0" → print warning and proceed:

Warning: Using reverse-engineered X API. Accepted on: <acceptedAt>

Step 3: If missing or version mismatch → display disclaimer:

DISCLAIMER

This tool uses a reverse-engineered X API, NOT official.

Risks:
- May break if X changes API
- No guarantees or support
- Possible account restrictions
- Use at your own risk

Accept terms and continue?

Use AskUserQuestion with options: "Yes, I accept" | "No, I decline"

Step 4: On accept → create consent file:

{
  "version": 1,
  "accepted": true,
  "acceptedAt": "<ISO timestamp>",
  "disclaimerVersion": "1.0"
}

Step 5: On decline → output "User declined. Exiting." and stop.

Preferences (EXTEND.md)

Check EXTEND.md in priority order — the first one found wins:

Priority	Path	Scope
1	.baoyu-skills/baoyu-danger-x-to-markdown/EXTEND.md	Project
2	${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-danger-x-to-markdown/EXTEND.md	XDG
3	$HOME/.baoyu-skills/baoyu-danger-x-to-markdown/EXTEND.md	User home

Result	Action
Found	Read, parse, apply settings
Not found	MUST run first-time setup (see below) — do NOT silently create defaults

EXTEND.md supports: Download media by default, default output directory.

First-Time Setup (BLOCKING)

CRITICAL: When EXTEND.md is not found, you MUST use AskUserQuestion to ask the user for their preferences before creating EXTEND.md. NEVER create EXTEND.md with defaults without asking. This is a BLOCKING operation — do NOT proceed with any conversion until setup is complete.

Use AskUserQuestion with ALL questions in ONE call:

Question 1 — header: "Media", question: "How to handle images and videos in tweets?"

• "Ask each time (Recommended)" — After saving markdown, ask whether to download media
• "Always download" — Always download media to local imgs/ and videos/ directories
• "Never download" — Keep original remote URLs in markdown

Question 2 — header: "Output", question: "Default output directory?"

• "x-to-markdown (Recommended)" — Save to ./x-to-markdown/{username}/{tweet-id}.md
• (User may choose "Other" to type a custom path)

Question 3 — header: "Save", question: "Where to save preferences?"

• "User (Recommended)" — ~/.baoyu-skills/ (all projects)
• "Project" — .baoyu-skills/ (this project only)

After user answers, create EXTEND.md at the chosen location, confirm "Preferences saved to [path]", then continue.

Full reference: references/config/first-time-setup.md

Supported Keys

Key	Default	Values	Description
download_media	ask	ask / 1 / 0	ask = prompt each time, 1 = always download, 0 = never
default_output_dir	empty	path or empty	Default output directory (empty = ./x-to-markdown/)

Value priority:

1. CLI arguments (--download-media, -o)
2. EXTEND.md
3. Skill defaults

Usage

${BUN_X} {baseDir}/scripts/main.ts <url>
${BUN_X} {baseDir}/scripts/main.ts <url> -o output.md
${BUN_X} {baseDir}/scripts/main.ts <url> --download-media
${BUN_X} {baseDir}/scripts/main.ts <url> --json

Options

Option	Description
<url>	Tweet or article URL
-o <path>	Output path
--json	JSON output
--download-media	Download image/video assets to local imgs/ and videos/, and rewrite markdown links to local relative paths
--login	Refresh cookies only

Supported URLs

• https://x.com/<user>/status/<id>
• https://twitter.com/<user>/status/<id>
• https://x.com/i/article/<id>

Output

---
url: "https://x.com/user/status/123"
author: "Name (@user)"
tweetCount: 3
coverImage: "https://pbs.twimg.com/media/example.jpg"
---

Content...

File structure: x-to-markdown/{username}/{tweet-id}/{content-slug}.md

When --download-media is enabled:

• Images are saved to imgs/ next to the markdown file
• Videos are saved to videos/ next to the markdown file
• Markdown media links are rewritten to local relative paths

Media Download Workflow

Based on download_media setting in EXTEND.md:

Setting	Behavior
1 (always)	Run script with --download-media flag
0 (never)	Run script without --download-media flag
ask (default)	Follow the ask-each-time flow below

Ask-Each-Time Flow

1. Run script without --download-media → markdown saved
2. Check saved markdown for remote media URLs (https:// in image/video links)
3. If no remote media found → done, no prompt needed
4. If remote media found → use AskUserQuestion:
   • header: "Media", question: "Download N images/videos to local files?"
   • "Yes" — Download to local directories
   • "No" — Keep remote URLs
5. If user confirms → run script again with --download-media (overwrites markdown with localized links)

Authentication

1. Environment variables (preferred): X_AUTH_TOKEN, X_CT0
2. Chrome login (fallback): Auto-opens Chrome, caches cookies locally

Extension Support

Custom configurations via EXTEND.md. See Preferences section for paths and supported options.