agentleFS
claude-worldclaude-world/claude-agent/.claude/skills/x-twitter/SKILL.md

x-twitter

Skill5 starsChanged 8 months agoMITView on GitHub

Post, reply, quote, search, and manage content on X (Twitter) using the xurl CLI for X API v2. Use when user wants to tweet, reply to a post, search X, check mentions, upload media, or send DMs.

  • Reads credentials
  • Installs packages

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Always check that xurl is installed and credentials are configured: which xurl && xurl users/me

    line 144
  2. Distinctive:

    If not installed, show install instructions and stop

    line 145
  3. Distinctive:

    If credentials are missing, guide user to https://developer.twitter.com and stop

    line 146
  4. Distinctive:

    NEVER log or store API keys/tokens in memory or workspace files

    line 147
  5. Distinctive:

    When drafting tweets, show the text to the user and confirm before posting

    line 150
  6. Distinctive:

    Keep responses concise: confirm post with "Posted: <first 50 chars of tweet>..." and the tweet URL

    line 152

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

X (Twitter)

Interact with X (Twitter) using xurl, a CLI for the X API v2.

Prerequisites

# Install xurl
brew install xurl
# or
npm install -g xurl-cli

Configure credentials (X API v2 keys):

export X_API_KEY="your_api_key"
export X_API_SECRET="your_api_secret"
export X_ACCESS_TOKEN="your_access_token"
export X_ACCESS_SECRET="your_access_token_secret"
export X_BEARER_TOKEN="your_bearer_token"

Get credentials from https://developer.twitter.com/en/portal/dashboard (requires a developer account and an app with OAuth 1.0a + Read/Write permissions)

Verify:

xurl users/me

Commands

Posting

# Post a tweet
xurl -X POST tweets -d '{"text": "Hello world!"}'

# Reply to a tweet
xurl -X POST tweets -d '{"text": "Great point!", "reply": {"in_reply_to_tweet_id": "<TWEET_ID>"}}'

# Quote tweet
xurl -X POST tweets -d '{"text": "Interesting take:", "quote_tweet_id": "<TWEET_ID>"}'

# Post with media (upload image first, then attach media_id)
xurl -X POST tweets -d '{"text": "Check this out!", "media": {"media_ids": ["<MEDIA_ID>"]}}'

Search

# Search recent tweets (last 7 days, free tier)
xurl "tweets/search/recent?query=<query>&max_results=10"

# Search with expansions
xurl "tweets/search/recent?query=<query>&tweet.fields=created_at,author_id&max_results=20"

Timelines & Mentions

# Get own user ID
xurl "users/me"

# Get mentions timeline
xurl "users/<USER_ID>/mentions?max_results=20"

# Get home timeline
xurl "users/<USER_ID>/timelines/reverse_chronological?max_results=20"

Media Upload

# Upload media (uses v1.1 endpoint)
xurl -X POST "https://upload.twitter.com/1.1/media/upload.json" \
  --form media=@image.png \
  --form media_category=tweet_image

DMs (Direct Messages)

# Send a DM
xurl -X POST dm_conversations/with/<USER_ID>/messages \
  -d '{"text": "Hey, wanted to reach out!"}'

# List DM conversations
xurl dm_conversations

Engagement

# Like a tweet
xurl -X POST "users/<MY_USER_ID>/likes" -d '{"tweet_id": "<TWEET_ID>"}'

# Retweet
xurl -X POST "users/<MY_USER_ID>/retweets" -d '{"tweet_id": "<TWEET_ID>"}'

# Delete a tweet
xurl -X DELETE "tweets/<TWEET_ID>"

Usage Examples

Post a simple tweet:

xurl -X POST tweets -d '{"text": "Just shipped a new feature! 🚀 Check it out at example.com"}'

Search for mentions of a topic:

xurl "tweets/search/recent?query=%23ClaudeCode&tweet.fields=created_at&max_results=10"

Reply to a specific tweet:

xurl -X POST tweets -d '{"text": "Thanks for sharing! Here is more context...", "reply": {"in_reply_to_tweet_id": "1234567890"}}'

Check recent mentions:

MY_ID=$(xurl "users/me" | jq -r '.data.id')
xurl "users/$MY_ID/mentions?max_results=10&tweet.fields=created_at"

Rules

  • Always check that xurl is installed and credentials are configured: which xurl && xurl users/me
  • If not installed, show install instructions and stop
  • If credentials are missing, guide user to https://developer.twitter.com and stop
  • NEVER log or store API keys/tokens in memory or workspace files
  • Tweet character limit is 280 characters — count and warn if the user's text exceeds it
  • URL-encode query parameters for search; use jq -r '@uri' if needed
  • When drafting tweets, show the text to the user and confirm before posting
  • For media posts, upload the media first, extract the media_id, then attach to the tweet
  • Keep responses concise: confirm post with "Posted: <first 50 chars of tweet>..." and the tweet URL
  • Note: X API free tier limits search to last 7 days and 500k reads/month; warn if user is likely to hit limits

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.