AugmentClaude

Twitter Spam Cleaner

Hide and mute spam replies on your X/Twitter posts automatically.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.

    This copies the whole skill folder into ~/.claude/skills/wjs-cleaning-spam-jianshuo/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Use when spam replies pile up on your X/Twitter posts — hides and mutes them automatically.

What this skill does

This skill automates the removal of spam replies on your X/Twitter posts by hiding them from your timeline and muting the accounts behind them. X's API restricts direct deletion of others' replies, so this tool uses the two available actions: hiding replies (removing them from your thread view) and muting accounts (silencing their notifications). It includes safeguards to flag borderline cases for your review before taking action.

What it does

  • Analyzes replies to identify spam using heuristics (profile decorations like 💕🌸♥, same-city recruitment language, invisible Unicode characters, pure emoji)
  • Generates two lists in dry-run mode: flagged spam (auto-processed) and borderline cases (requires your review)
  • Hides replies from your thread view and mutes accounts simultaneously
  • Handles rate limits automatically (roughly 50 hide actions per 15 minutes); pauses and resumes on restart without reprocessing
  • Tracks processed replies in a state file to ensure idempotent operation across multiple runs
  • Reports results: shows how many replies were hidden, failures with reasons, and accounts muted

How to use it

Run the script in dry-run mode first to preview flagged and borderline replies. Review the borderline list to confirm which are actually spam versus genuine comments. Then apply the changes with the --apply flag, optionally specifying IDs from your review using --ids. The skill works only on replies from the past 7 days and requires you to manually block accounts via X's web interface if needed.

Related skills