Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    social media skill

    2

    Unified TikTok and Instagram agent skill for automated short-form video orchestration, analytics, and repurposing.

    $36

    /mo

    Subscription · cancel anytime

    Secure checkout via Stripe

    • Always the latest version
    • Delivered live to your agent via MCP
    • Cancel anytime, access ends at period end
    Security scanned
    social media skill

    social media skill

    Example session with this skill installed

    Analyze the performance of my last Reel and TikTok video, then repurpose the master file 'promo_vid.mp4' for both platforms based on those insights.

    • Read your context and instructions
    • Compiled the social media

    I have retrieved the engagement metrics for your recent posts and prepared the repurposing plan. The TikTok video showed a high completion rate (62%), while the Instagram Reel excelled in shares and saves. I have adapted the master media to lean into these specific strengths.

    Social Media Analysis and Execution Plan

    PlatformPost IDCompletion RateEngagement TypeRepurposing Strategy
    TikToktk_9823462.4%Hook-driven9s cut, high-velocity edit, 9:16 vertical, safety-zone text
    Instagramig_5501241.2%Community/Save15s cut, aesthetic cover, 4:5 aspect, "Save for later" CTA

    Proposed Repurposing Parameters

    {
      "operation": "repurpose_across_platforms",
      "master_media_url": "assets/promo_vid.mp4",
      "configurations": [
        {
          "platform": "tiktok",
          "aspect_ratio": "9:16",
          "duration_target": 9,
          "hashtags": ["#techtips", "#automation", "#trending"],
          "safe_zone_padding": {"top": 0.15, "bottom": 0.25}
        },
        {
          "platform": "instagram",
          "aspect_ratio": "4:5",
          "duration_target": 15,
          "hashtags": ["#softwaredevelopment", "#productivity", "#agenticworkflows"],
          "cta": "Save this for your next sprint"
        }
      ]
    }
    

    Next steps

    1. Review the safe_zone_padding for the TikTok export to ensure text overlays don't conflict with the UI.
    2. Confirm the Instagram grid harmony check against the last 9 posts before final dispatch.
    3. Call social_upload via the SocialAgentSkill facade to execute the publishing sequence.
    $36/mo

    Subscription · always the latest version

    • Secure checkout via Stripe
    • Cancel anytime
    • Delivered live via MCP

    About this skill

    Managing cross-platform social media presence often results in fragmented tool definitions and inconsistent engagement data. This skill merges TikTok and Instagram operations into a unified Platform-Skill-Action architecture, providing a single interface for short-form video orchestration across major LLM frameworks.

    What it does

    • Unified Media Upload: Dispatches content to TikTok or Instagram through a normalized facade, handling platform-specific requirements like aspect ratios and UI safe zones.
    • Cross-Platform Repurposing: Adapts master media for specific platform philosophies, adjusting duration for TikTok velocity or grid harmony for Instagram Reels.
    • Normalized Analytics: Aggregates engagement metrics like watch time, completion rates, and shares into a single Pydantic-validated schema.
    • Autonomous OTA Loop: Implements an Observe-Think-Act cycle with isolated platform namespaces and shared strategic memory.
    • Framework-Ready Exports: Generates canonical JSON schemas for immediate integration with OpenAI, Anthropic, Llama 3, and LangChain tools.

    How it works

    1. Initialize Registry: Register the TikTok and Instagram adapters within the SocialAgentSkill entry point to enable unified access.
    2. Platform Optimization: Tailor parameters like 9:16 ratios for TikTok velocity or 4:5 portrait crops for Instagram feed harmony.
    3. Execute OTA Loop: Ingest metrics via get_video_stats, evaluate against campaign goals in isolated namespaces, and dispatch actions through the skill facade.
    4. Export Tool Bindings: Use the provided scripts to output framework-specific tool definitions for your chosen LLM.

    Frameworks & tools

    Built for Python environments using Pydantic for schema validation. Compatible with GPT-4o, Claude 3.5, Llama 3, LangChain, AutoGen, and CrewAI via standardized tool exports.

    Why this beats prompting it yourself

    Manual prompting often fails to account for technical platform constraints like TikTok's UI overlays or Instagram's grid palette consistency. This skill enforces these rules programmatically through validated schemas and normalized error envelopes, preventing failed API calls and poor algorithmic performance.

    Use cases

    • Automating a daily posting schedule that adapts the same core video into high-velocity TikToks and aesthetic Instagram Reels.
    • Building an autonomous agent that monitors completion rates and triggers a re-cut if initial TikTok engagement is low.
    • Auditing a brand's Instagram grid harmony before publishing new carousel content.
    • Creating a centralized dashboard for cross-platform video performance analysis.

    Known limitations

    Does not support raw platform exception exposure to the LLM. Memory must be partitioned by platform ID to prevent cross-contamination. Binary cuts should not be posted identically across platforms.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    Requires PlatformRegistry initialization. Returns SkillEnvelope wrappers instead of raw HTTP traces. Memory must be partitioned by platform_id to avoid cross-contamination.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 9 days ago

    Permissions

    Terminal / Shell
    Network Access
    Listed9 days ago

    What's inside

    Frequently Asked Questions

    This skill provides a unified Platform-Skill-Action architecture that normalizes technical constraints like aspect ratios and UI safe zones, ensuring your content is optimized for each platform's unique algorithm and layout.

    The skill includes standardized tool exports and canonical JSON schemas specifically designed for seamless integration with OpenAI (GPT-4o), Anthropic (Claude 3.5), Llama 3, LangChain, and CrewAI.

    Yes, it features a normalized analytics engine that aggregates metrics like watch time and completion rates into a single Pydantic-validated schema for unified cross-platform reporting.

    You receive the complete Python-based skill package, including the TikTok and Instagram adapters, Pydantic schemas for validation, and scripts for exporting tool bindings to various LLM frameworks.

    Setup involves registering the platform adapters within the `SocialAgentSkill` entry point and configuring your platform credentials to enable the automated Observe-Think-Act (OTA) cycle.

    The skill uses isolated platform namespaces and shared strategic memory, allowing your agent to learn from overall performance while keeping platform-specific actions and data separate.

    New in Agents & Orchestration