AI Skill

CodivUpload Generic Skill

The catch-all skill that gives any AI client (Claude, ChatGPT, Cursor, Zed) full context for using CodivUpload across YouTube, Instagram, Facebook, X, TikTok, LinkedIn, Threads, Pinterest, Bluesky, Google Business, and Snapchat. Pair this skill with the CodivUpload MCP server (`npx codivupload-mcp`) and your AI agent gets ~30 social media posting tools natively, plus the platform-specific intuition baked into the skill markdown.

YouTubeInstagramFacebookX (Twitter)TikTokLinkedInThreadsPinterestBlueskyGoogle Business ProfileSnapchat

Best for:AI engineers, agentic app builders, and any user who wants their LLM to handle social media end-to-end.

Install MCP serverAll skills

What this skill teaches the LLM

The skill is a markdown file the LLM reads when activating. Below is the focused context this skill bakes in — so Claude/ChatGPT/Cursor doesn't have to learn from API errors.

  • Full API contract: profile_name + platforms array model (no fictional social_account_id)
  • All 50+ platform-specific override parameters with exact field names and value enums
  • Required vs optional fields per post_type (text / image / video / document)
  • Three first-class interfaces: dashboard, REST API, MCP server — when to recommend which
  • Common error patterns and fix recipes (partially_failed retry, rate-limit handling, missing profile)
  • Cross-post recipes: Reel-to-3-platforms, blog announcement to text-friendly platforms, agency whitelabel pattern
  • Plan-tier limits and pricing summary for the recommend-decision matrix

Example prompts

These are real prompts you can give an AI client with this skill installed. The skill provides the LLM with the right tool calls, parameter names, and platform-specific quirks so the response is correct on the first try.

1

“Schedule this video to TikTok and Instagram for tomorrow at 10am ET, with caption 'Quick productivity tip'.”

What the LLM does

Claude calls create_post with profile_name + platforms=["tiktok","instagram"] + scheduled_date in UTC. Picks correct overrides automatically.

2

“Show me which client's posts had the highest engagement last week.”

What the LLM does

Claude calls get_analytics with date range, sorts by engagement, returns top 5 with platform breakdown.

3

“Re-queue the failed destinations from post abc123.”

What the LLM does

Claude calls retry_failed without re-publishing successful destinations (idempotent).

4

“What's the best way to publish a 60-second Reel to Instagram, TikTok, and YouTube Shorts simultaneously?”

What the LLM does

Claude explains the single create_post pattern with platforms=["instagram","tiktok","youtube"] + youtube_type=shorts + instagram_share_to_feed=true. Generates working cURL/Python code.

Install in 2 steps

The skill itself is a markdown file. The MCP server is the runtime. Install both for the full experience.

  1. 1Configure MCP server in your AI client

    Paste this configuration into Claude Desktop / Cursor / Zed's MCP config file. Replace cdv_your_api_key with your real key from pricing.

    {
  "mcpServers": {
    "codivupload": {
      "command": "npx",
      "args": ["-y", "codivupload-mcp"],
      "env": {
        "CODIVUPLOAD_API_KEY": "cdv_your_api_key"
      }
    }
  }
}

  2. 2Add the skill markdown

    Download npmjs/skills/generic/SKILL.md from the GitHub repo and place it under ~/.claude/skills/codivupload-generic/SKILL.md (Claude Desktop) or your project's .claude/skills/ directory.

    For ChatGPT: paste the SKILL.md content into a Custom GPT's Instructions field at gpts.openai.com/editor.

    github.com/Codivion

Frequently asked

Do I need the per-platform skills if I have this one?+

No — this generic skill alone handles every endpoint. Per-platform skills (Instagram, YouTube, etc.) are optional specializations that give the LLM extra context on platform-specific quirks. Install them when you want sharper LLM behavior on a specific platform.

Can I use this with ChatGPT?+

Yes — the SKILL.md content is portable. Either paste it into a Custom GPT's Instructions field with the OpenAPI Action pointing at api.codivupload.com/public-openapi.json, OR register the MCP server as a Connector in ChatGPT Pro.

Does this skill work offline?+

The skill itself is a local markdown file (always available). The MCP server it pairs with needs internet to call CodivUpload's API. Without network, you can use the skill as documentation but can't actually post.

Related skills

Claude Instagram Skill

Specialized AI skill that gives Claude, ChatGPT, and Cursor deep context for Instagram posting via Meta Graph API. Reels, carousels, custom cover frames, alt text, geotagging.

Claude YouTube Skill

Specialized AI skill for YouTube uploads via Claude, ChatGPT, and Cursor. Standard OAuth + BYOP setup, Shorts auto-classification, 24/7 RTMP live streams. MIT licensed.

Claude TikTok Skill

AI skill for TikTok automation via Claude, ChatGPT, Cursor. Direct Post / Draft modes, brand content disclosure, AI-generated content flag, comment/duet/stitch toggles.

Claude Agency + Workspace Skill

AI skill for agency operations — multi-tenant workspaces, branded team invites, role-based access (Admin/Editor/Viewer), profile move, billing cascade. For Claude, ChatGPT, Cursor.

Ready to give your AI agent posting tools?

Free CodivUpload plan covers 30 posts/month. Skills are MIT licensed.

Get an API key