Content Factory for five platforms skill

Content Factory

An OpenCode skill with four subagents: turns a lesson topic into a post for Telegram, VK, Dzen, a blog and LinkedIn with a cover image

  • 0 ★ on the repository
  • Last commit
  • MIT
Skill

Extended access

Why this level

  • Publishes messages to a Telegram channel on behalf of a bot
  • Uses external OpenAI or ProxyAPI keys for text and cover generation
All reasons and checks
Russian stack

larik7lolik/content-factory

Install

Services

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/content-factory

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • Publishes messages to a Telegram channel on behalf of a bot
  • Uses external OpenAI or ProxyAPI keys for text and cover generation

This is third-party code. Review the repository files before installing.

What it does

The orchestrator skill for OpenCode coordinates four subagents: researcher gathers facts and trends on a topic from the web, content-writer adapts the text for five platforms at once (Telegram, VK, Dzen, a blog, LinkedIn) respecting each one's limits and hashtags, image-creator draws a unique cover via gpt-image-2, and publisher sends out the finished content. The output is a content/output.json with per-platform text and a cover file. Real publishing only works for Telegram through the Bot API: the publish_vk tool in the bundled MCP server merely formats the text with hashtags and returns a ready string without sending it anywhere, and the README explicitly places Dzen publishing on the roadmap.

Who it is for. For online-school marketers and language tutors preparing regular content for several platforms from one lesson topic.

Good fit when

  • You need text for five platforms at once from one lesson topic
  • You need a cover for the topic without a separate design tool
  • You need real publishing to a Telegram channel via the Bot API

Not a fit when

  • You need real autoposting to VK or Dzen rather than just prepared text: that is not there yet, only Telegram is
  • You need a Claude Code skill, the project is built for OpenCode's subagent format

Example request

@content-factory create content on the topic of the difference between Passe Compose and Imparfait

Limitations

VK publishing is not implemented: the publish_vk tool in the MCP server only assembles text with hashtags and returns it without sending it anywhere, even though the README's feature list claims VK autoposting as working. Dzen publishing is explicitly listed as a roadmap item, not a finished feature. It needs OpenAI or ProxyAPI keys and a Telegram bot token. The project is small, has no releases, and is MIT licensed.

How to disable. Delete the .opencode/skills/content-factory folder and .opencode/agents from the project.

FAQ

Does the skill actually publish to VK?

No, the publish_vk tool only prepares text with hashtags and returns it as a result; there is no real VK send in the code.

Which platforms does text generation cover?

Five: Telegram, VK, Dzen, a blog and LinkedIn, each with its own format in content/output.json.

Discussion

No questions or reviews yet.

VK Ads skill for agencies

claude-skill-vk-ads

Russian stack

A Claude Code skill for VK Ads built for agencies: bulk operations, hashed remarketing audiences, ad-marking compliance and Google Sheets reports

SkillBroad access2Repository stars

Marketing skills for coding agents: SEO, content, email campaigns, ads, analytics and publishing through service APIs

SkillBroad access738Repository stars

BotHelp analytics skill

claude-skill-bothelp

Russian stack

A Claude Code skill for the BotHelp Open API: a bot map, step-by-step drop-off, subscriber export and limited management via the open API

SkillExtended access

A Telegram bot for OpenCode: send coding tasks, watch progress and switch models from your phone while OpenCode keeps running on your own computer

CLIBroad access1.4KRepository stars
Russian stack

Claude Code skill: collects semantics for VK Ads from real Wordstat via browser, without Direct or paid APIs

SkillExtended access

README in short

The README presents the project as a multi-agent content-factory case study for EdTech marketers, cutting post prep from 2-3 hours to 5 minutes. It shows an architecture of an orchestrator and three subagents plus a publisher, installation via pip and OpenCode, a step-by-step call example, and a resulting content/output.json with text for five platforms and a cover. Its roadmap separately names VK API and Dzen API autoposting support as still to be built.

README badge

Report a problem