agentleFS
shali10shali10/awesome-agent-skills/skills/multi-platform-distribution/SKILL.md

multi-platform-distribution

Skill1 starsChanged 2 months agoMITView on GitHub

Use when adapting a single piece of Markdown content into tailored, platform-compliant formats for Telegram, WeChat, Zhihu, Twitter/X, and QQ.

The file

Files
SKILL.md

Multi-Platform Content Distribution & Formatting

Overview

An intelligent content syndication and adaptation engine. It takes a master Markdown article and automatically transforms it into 5 platform-native formats, strictly adhering to each platform's distinct syntax quirks, character limits, escaping rules, and visual style.

When to Use & When NOT to Use

When to Use

  • Cross-posting technical articles, product announcements, or newsletters to multiple platforms.
  • Formatting Telegram posts with MarkdownV2 escaping and rich tables.
  • Splitting long-form essays into structured Twitter/X threads.
  • Optimizing codeblocks and image layouts for WeChat Official Accounts and Zhihu.

When NOT to Use

  • Single-target internal notes or local documentation.
  • Automated spamming or unreviewed bulk posting.

Platform Formatting Rules Matrix

PlatformSyntax SupportKey Adaptation RulesMax Length / Limits
TelegramHTML / MarkdownV2Escape special chars (_, *, [, ]); convert wide tables to cards; use native pipe tables4,096 chars per message
WeChat (公众号)Rich Text HTMLInline CSS styles; codeblocks inside distinct containers; high-contrast headingsUnlimited (Rich editor)
Zhihu (知乎)GFM MarkdownStandard headers; convert unsupported HTML tags; ensure code fences specify languageStandard article format
Twitter / XPlain text + MediaSplit into numbered thread (1/N); extract key hook & stats in tweet 1; keep hashtags to ≤2280 chars (free) / thread
QQ / QQBotMarkdown (Subset)Avoid nested blockquotes; keep tables ≤4 columns; use emoji badges for visual hierarchy2,000 chars per message

Multi-Platform Generation Pipeline

  1. Input: Master source Markdown text with images and tables.
  2. Analysis: Detect target platforms requested by user.
  3. Transformation:
    • Apply platform-specific parser rules and delimiter cleaners.
    • Truncate / split long text at logical section boundaries.
  4. Verification: Confirm zero unescaped MarkdownV2 errors for Telegram and valid thread sequencing for Twitter.

Common Pitfalls

  1. Unescaped entities in Telegram MarkdownV2: Characters like . and - in plain text outside codeblocks will trigger Bad Request if unescaped; use proper entity escaping or raw HTML mode.
  2. Missing language tags in Zhihu code blocks: Bare without language specification degrades syntax highlighting on Zhihu.
  3. Overcrowded tweets in threads: Each tweet in a thread should deliver a standalone insight or takeaway, not cut sentences mid-thought.

Verification Checklist

  • Telegram output passes character escaping checks.
  • Twitter thread output splits at paragraph ends with (1/N) numbering.
  • Zhihu / WeChat outputs have formatted code fences.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.