Tweetclaw

What it does

When your agent uses it

• The user asks about Twitter
• Social media automation
• Tweet analytics
• Giveaway management

Example prompts

• “post tweet”
• “search tweets”
• “extract followers”
• “/tweetclaw”

Requirements

• A credential in XQUIK_API_KEY
• Compatibility (from SKILL.md): Designed for Claude Code
• Pre-approved tools (allowed-tools): Read, Bash(curl:*), WebFetch

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Search tweets: GET /x/tweets/search?query=AI+agents&count=50
2. 2Analyze engagement: Check likes, retweets, reply counts in results
3. 3Compose optimized tweet: POST /compose with topic and tone
4. 4Score the draft: POST /compose with step: "score"
5. 5Post the tweet: POST /x/tweets with the final text

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Bash(curl:*)
  • WebFetch

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • curl

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • xquik.com
  • x.com

  Also links to:

  • docs.xquik.com
  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • XQUIK_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Designed for Claude Code

  From compatibility in the SKILL.md frontmatter.

Context cost

Tweetclaw loads about 1.7k tokens when it runs. Until then it costs about 127 tokens; SKILL.md has 422 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~127

When it runs · the whole SKILL.md, loaded when a task matches

~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 422 words, ~1,671 tokens.

name

tweetclaw

description

X/Twitter automation plugin. Post tweets, reply, like, retweet, follow, unfollow, send DMs, search tweets, look up users, extract bulk data, monitor accounts, run giveaway draws, and compose algorithm-optimized tweets via Xquik REST API. Use when the user asks about Twitter, X, tweets, followers, social media automation, tweet analytics, or giveaway management. Trigger with "post tweet", "search tweets", "extract followers", "run giveaway", "monitor account", "compose tweet", "trending topics".

allowed-tools

Read, Bash(curl:*), WebFetch

compatibility

Designed for Claude Code

version

1.5.3

author

Burak Bayir <burak@xquik.com>

license

MIT

tags

twitter, x, automation, social-media, giveaway, monitoring, scraping, mcp

# Search tweets
curl -H "x-api-key: $XQUIK_API_KEY" \
  "https://xquik.com/api/v1/x/tweets/search?query=AI+agents&count=20"

# Get user profile
curl -H "x-api-key: $XQUIK_API_KEY" \
  "https://xquik.com/api/v1/x/users/elonmusk"

# Get tweet by ID
curl -H "x-api-key: $XQUIK_API_KEY" \
  "https://xquik.com/api/v1/x/tweets/1234567890"

# Post a tweet
curl -X POST -H "x-api-key: $XQUIK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello from TweetClaw!"}' \
  "https://xquik.com/api/v1/x/tweets"

# Like a tweet
curl -X POST -H "x-api-key: $XQUIK_API_KEY" \
  "https://xquik.com/api/v1/x/tweets/1234567890/like"

# Follow a user (requires numeric user ID)
curl -X POST -H "x-api-key: $XQUIK_API_KEY" \
  "https://xquik.com/api/v1/x/users/44196397/follow"

# Estimate extraction cost
curl -X POST -H "x-api-key: $XQUIK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type": "reply_extractor", "params": {"tweetId": "1234567890"}}' \
  "https://xquik.com/api/v1/extractions/estimate"

# Create extraction
curl -X POST -H "x-api-key: $XQUIK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type": "reply_extractor", "params": {"tweetId": "1234567890"}}' \
  "https://xquik.com/api/v1/extractions"

# Retrieve results (poll status first)
curl -H "x-api-key: $XQUIK_API_KEY" \
  "https://xquik.com/api/v1/extractions/{id}/results"

curl -X POST -H "x-api-key: $XQUIK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "tweetUrl": "https://x.com/handle/status/1234567890",
    "winnerCount": 3,
    "filters": {"mustRetweet": true, "mustFollow": "handle", "minFollowers": 10}
  }' \
  "https://xquik.com/api/v1/draws"

# Create monitor
curl -X POST -H "x-api-key: $XQUIK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"username": "openai"}' \
  "https://xquik.com/api/v1/monitors"

# Create webhook
curl -X POST -H "x-api-key: $XQUIK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com/webhook", "events": ["tweet.new"]}' \
  "https://xquik.com/api/v1/webhooks"

curl -X POST -H "x-api-key: $XQUIK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"step": "compose", "topic": "AI productivity", "tone": "professional"}' \
  "https://xquik.com/api/v1/compose"

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/.curated/tweetclaw of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287