All skills
superx-so avatar

/superx

@2276277
by SuperXsuperx-so/superx-agent27 stars
6

Grow a Twitter/X account with SuperX. Use when someone asks for a weekly growth recap or account analytics, wants to find leads or buyers on X, needs draft posts or threads written and scheduled, wants replies drafted or reply history reviewed, asks who engages with them most, wants inspiration from high-performing posts, or wants X Articles written and published. Also covers contact lists, signal agents (automated lead finders), Engage feeds, tagging, media attachments, AI cover images, and the Context settings (profile, interests, rules, reply settings, favorite creators, style guide, products) that steer SuperX writing. Everything runs through the superx CLI or the SuperX API; nothing is posted without a person saying so.

Use this Skill: https://skilld.dev/gh/superx-so/superx-agent/superx

This session only. Nothing lands on disk.

referencesskillsviral-score-iteraterecipe.md

≈437 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Viral Score Loop

Score a draft against the account's own recent posts, rewrite one thing at a time, rescore, and stop when the score stops rising.

superx posts:viral-score --text "<the draft>"                       # add --image, --video or --quote to match what will be attached
superx posts:viral-score --text "<rewrite keyed on the top hurt item>"
superx posts:viral-score --text "<next rewrite>"                    # repeat; six scored versions at most

Read score, helped, hurt and warnings from each result. Rewrite ONE thing per round, keyed on the top hurt item, and keep the person's facts, claims and voice; never add a request for replies, follows, links or DMs, never pad with hashtags or emoji, and pass the same media flags every round. Stop when a rewrite introduces a warning (go back to the last clean version and say which warning fired), when the score has not risen for two rounds in a row, or after six scored versions. If the first score already warns, name it and offer one rewrite that removes the ask, then score that once. The score is the chance the post beats the account's own normal post, so say "72 means it beats your usual post about 72 times in 100", never a reach or like count; the likes and replies multiples are relative to the account's median post, and reposts+quotes and views are low confidence, so never chase them.

MCP: predict_viral_score (repeat per version) -> schedule_post only when the person asks

Stops at: a table of every version with its score and what changed, plus the best version, for the person to pick. Nothing is posted. Most scores charge no credits, one in ten charges 1, and the first score for an account charges 1 more while its baseline is read.

Source: SKILL.md on GitHub

2 warnings12d3 checks · Risk SAFE
  • Gen Agent Trust Hub12d

    The SuperX skill enables an AI agent to manage X (Twitter) account growth through a specialized CLI tool provided by a recognized vendor (superx-so). The skill uses shell commands to perform analytics, scheduling, and content generation. The primary security risk is Indirect Prompt Injection, as the agent is instructed to process and respond to untrusted data from X (such as post replies and keyword feeds) without explicit instructions for data sanitization or boundary management. The skill also requires the installation of an external CLI tool and the management of API credentials.

  • Socket12d

    1 alert: gptAnomaly

  • Snyk12d

    Risk: MEDIUM · 1 issue

Signed by skilld at 2276277. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 weeks ago.

Activeupdated 2 weeks ago
homepage
https://docs.superx.so
Other metadata
metadata
{
  "openclaw": {
    "emoji": "🚀",
    "requires": {
      "bins": [
        "superx"
      ],
      "env": []
    }
  }
}

README badge

README badge for superx-so/superx-agent