Skip to content
TrustedSkillsbeta
Back to all skills

Social Push

Checked
jihe520·vlatest·other

Social Push generates engaging social media content prompts to help users brainstorm and create compelling posts for various platforms.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add jihe520/social-push --skill social-push -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

jihe520

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned jihe520/social-push at f7cd0d0e5c.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
f7cd0d0e5c
Manifest
skills/social-push/SKILL.md
Scanned
9 files, 404 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The Social Push skill assists AI agents in uploading articles, images, and other content to various social media platforms. It leverages a browser automation tool (agent-browser) to interact with websites, following pre-defined workflows for each platform. The agent will prepare drafts but will not automatically publish; user confirmation is required before final posting.

When to use it

  • To upload articles or images to social media platforms like Xiaohongshu (Little Red Book), X (Twitter), Weibo, WeChat Official Accounts, Juejin, and LinuxDo.
  • When you need assistance with the technical steps of posting content on a specific platform.
  • For users who want to automate parts of their social media publishing process while retaining control over final publication.

Key capabilities

  • Supports multiple social media platforms: Xiaohongshu, X (Twitter), Weibo, WeChat Official Accounts, Juejin, and LinuxDo.
  • Handles various content types including short articles with images, long-form text posts, and more.
  • Uses pre-defined workflows for each platform to guide the posting process.
  • Allows users to add new platforms by creating and testing interaction paths.
  • Provides a mechanism for self-evolution: correcting workflow errors by inspecting webpage elements using agent-browser.

Example prompts

  • "Upload this article to Xiaohongshu."
  • "Post this image on X (Twitter)."
  • "Can you help me publish this long text post to WeChat Official Accounts?"
  • “I want to add a workflow for Mastodon.”

Tips & gotchas

  • Requires the agent-browser tool and its associated dependencies.
  • The agent will not automatically click "publish"; user confirmation is always needed.
  • Page element references may change, requiring occasional updates to workflows using agent-browser snapshot.