Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

X Spam Reply Cleaner (Hide + Mute)

Finds promo/spam replies under your X (Twitter) posts, hides them, and mutes the accounts behind them.

AutomationIntermediate★ 131⑂ 23AI score 7/10Last updated: Aug 20, 2026

What it does

  • Pulls replies from the last 7 days via the X API and splits them into flagged (clear spam) and borderline (needs human eyes).
  • Runs hide reply + mute account on flagged items; borderline items are reviewed one by one by Claude before action.
  • Detects spam signals such as decorative emoji in display names, local-hookup/promo phrasing, and invisible characters (U+034F, zero-width) used to dodge filters.
  • Keeps state/cleaned.jsonl so a 429 rate-limit stop is resumable: rerun the same command after 15 minutes and processed IDs are skipped.

Who it's for

  • X users buried under promo-bot replies (especially Chinese-language spam rings).
  • People who already have the xurl CLI and X API access with write scopes.
  • Anyone who wants a manual review gate so real human comments aren't hidden by mistake.

Examples

  1. "Clean the spam replies under my tweets" → dry-run report of flagged/borderline, confirm, then bulk hide + mute.
  2. Hit the ~50 hides/15 min limit → wait, rerun the identical command, already-handled replies are skipped.
  3. Asked to block an account → the skill explains the API block endpoint is gone and points you to manual blocking on the web.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/jianshuo/claude-skills/HEAD/wjs-cleaning-spam/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the wjs-cleaning-spam folder from the GitHub repo jianshuo/claude-skills into my ~/.claude/skills/wjs-cleaning-spam/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/jianshuo/claude-skills.git /tmp/claude-skills && cp -r /tmp/claude-skills/wjs-cleaning-spam ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/jianshuo/claude-skills.git /tmp/claude-skills
  3. Copy the skill: cp -r /tmp/claude-skills/wjs-cleaning-spam ~/.claude/skills/
  4. Install the xurl CLI for the X API and authenticate with a token that can hide replies and mute accounts.
  5. Edit scripts/clean_spam.py to point the search query (to:...) at your own handle and adjust the keyword/invisible-character lists.
  6. Restart Claude Code, then ask "clean spam replies" or run /wjs-cleaning-spam.
  7. Always review the dry-run output and the borderline list yourself before running the --apply step.
View source on GitHub ↗License: MIT