SRT Social Summary logo

SRT Social Summary

Community
dean9703111
SRT Social Summary

This skill should be used when the user asks to "generate social media summary from srt", "create platform-specific descriptions", "generate Facebook post from transcript", "create YouTube description from srt", "write Thread post from subtitles", "生成影片介紹", "根據逐字稿生成貼文", or needs to create engaging social media content from SRT subtitle files for Facebook, Thread, or YouTube platforms.

Overview

Publisherdean9703111
Repositoryai-agent-skill-for-video-workflow
Skill nameSRT Social Summary
Stars
219
Forks
49
Bundled files
3
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by dean9703111 on GitHub. Read the source before you install it.

Installation

Install the SRT Social Summary AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/dean9703111/ai-agent-skill-for-video-workflow/tree/master/.agent/skills/srt-social-summary
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/dean9703111/ai-agent-skill-for-video-workflow.git /tmp/ai-agent-skill-for-video-workflow
mkdir -p .claude/skills
cp -r /tmp/ai-agent-skill-for-video-workflow/.agent/skills/srt-social-summary .claude/skills/dean9703111-srt-social-summary
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable SRT Social Summary in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads SRT Social Summary on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so SRT Social Summary is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

SRT Social Summary Generator

Generate compelling social media summaries from SRT subtitle files, optimized for different platform characteristics to maximize engagement and reach.

Purpose

This skill analyzes SRT transcript files and generates platform-specific summaries that:

  • Capture the core message and key insights
  • Match platform-specific best practices (tone, length, format)
  • Create emotional resonance with target audiences
  • Highlight the value proposition clearly
  • Include strategic hashtags for discoverability

When to Use

Use this skill when:

  • Converting video transcripts into social media posts
  • Promoting video content across multiple platforms
  • Creating platform-optimized descriptions for the same content
  • Need to extract key points from lengthy transcripts
  • Want to maximize engagement through platform-specific formatting

Platform Characteristics

Facebook

  • Tone: Conversational, community-focused, relatable
  • Length: 100-250 characters for high engagement (can go longer for storytelling)
  • Format: Hook in first line, value proposition, call-to-action
  • Hashtags: 2-3 relevant hashtags (not overused)
  • Goal: Spark conversation, encourage shares and comments

Thread (Twitter-like)

  • Tone: Concise, punchy, thought-provoking
  • Length: 280 characters max per post (can use thread format for longer content)
  • Format: Strong hook, key insight, intrigue/question
  • Hashtags: 1-2 highly relevant hashtags
  • Goal: Quick attention grab, encourage retweets and replies

YouTube

  • Tone: Informative, SEO-friendly, comprehensive
  • Length: 150-300 words (first 2-3 lines are critical)
  • Format: Hook + detailed value breakdown + timestamps (if applicable) + CTA
  • Hashtags: 3-5 strategic hashtags for search
  • Goal: Improve searchability, set viewer expectations, encourage watch time

Usage Workflow

Step 1: Analyze the SRT Content

Read the SRT file to understand:

  • Main topic and core message
  • Key insights or takeaways (3-5 points)
  • Emotional tone (educational, inspirational, entertaining, etc.)
  • Target audience signals
  • Unique value propositions

Extract the essence without getting lost in filler words or repetition common in spoken content.

Step 2: Identify Platform Requirements

Ask the user which platform(s) they need:

  • Facebook only
  • Thread only
  • YouTube only
  • All three platforms

If not specified, generate for all three platforms by default.

Step 3: Generate Platform-Specific Summaries

For each platform, create content following these principles:

Facebook Summary Structure
[Hook - 1 compelling sentence that stops scrolling]

[Value Proposition - What will the audience learn/gain?]

[Key Insights - 2-3 bullet points or short sentences]

[Call-to-Action - Encourage engagement]

#Hashtag1 #Hashtag2 #Hashtag3
Thread Summary Structure
[Punchy Hook - Maximum impact in minimum words]

[Core Insight - The "aha" moment]

[Intrigue/Question - Make them want to watch]

#Hashtag1 #Hashtag2
YouTube Summary Structure
[Strong Hook - First 2 lines appear in search results]

[Detailed Overview - What this video covers]

[Key Topics/Timestamps - If applicable]
🎯 Topic 1
🎯 Topic 2
🎯 Topic 3

[Value Statement - Why watch this]

[Call-to-Action - Like, subscribe, comment]

#Hashtag1 #Hashtag2 #Hashtag3 #Hashtag4 #Hashtag5

Step 4: Craft Strategic Hashtags

Select hashtags based on:

  • Relevance: Directly related to content
  • Search Volume: Balance popular and niche tags
  • Competition: Mix high-traffic and specific tags
  • Trending: Include timely topics when relevant
  • Branding: Include brand/creator tags if applicable

Avoid:

  • Generic hashtags (#love, #instagood)
  • Overused hashtags that drown content
  • Irrelevant trending tags
  • Too many hashtags (looks spammy)

Step 5: Output Format

Generate output in this format:

markdown
# 社群平台摘要

## Facebook
[Facebook content]

---

## Thread
[Thread content]

---

## YouTube
[YouTube content]

---

## 分析說明
- **核心主題**: [Main topic]
- **目標受眾**: [Target audience]
- **情感基調**: [Emotional tone]
- **關鍵賣點**: [Key value propositions]

Save the output as summary.md in the same directory as the source SRT file.

Best Practices

Content Analysis

  • Focus on transformation/outcome, not just information
  • Identify the "so what?" factor - why should audience care?
  • Look for quotable moments or surprising insights
  • Consider the audience's pain points and desires

Writing Hooks

  • Use numbers ("3 ways to...", "5 secrets...")
  • Ask provocative questions
  • Make bold statements
  • Create curiosity gaps
  • Use power words (discover, revealed, proven, secret)

Emotional Resonance

  • Tap into aspirations (what they want to become)
  • Address frustrations (what they want to avoid)
  • Create relatability (shared experiences)
  • Inspire action (achievable next steps)

Platform Optimization

  • Facebook: Prioritize shareability and discussion
  • Thread: Maximize retweet potential with quotability
  • YouTube: Optimize for search and watch time

Hashtag Strategy

  • Research platform-specific trending tags
  • Use a mix of broad and specific tags
  • Include branded hashtags for tracking
  • Test and iterate based on performance

Common Patterns

Educational Content

  • Hook: "Most people don't know..."
  • Value: "Learn the [X] framework for [outcome]"
  • CTA: "Which tip will you try first?"

Inspirational Content

  • Hook: "What if I told you..."
  • Value: "Discover how [person/method] achieved [result]"
  • CTA: "Tag someone who needs to hear this"

Entertainment Content

  • Hook: "[Surprising fact or statistic]"
  • Value: "Watch as we [interesting activity]"
  • CTA: "Drop a 🔥 if you agree"

Tutorial Content

  • Hook: "Stop doing [common mistake]"
  • Value: "Here's the right way to [achieve goal]"
  • CTA: "Save this for later"

Additional Resources

Reference Files

For detailed platform specifications and advanced techniques:

  • references/platform-specs.md - Detailed platform requirements, character limits, and algorithm insights
  • references/hook-formulas.md - Proven hook templates and copywriting formulas
  • references/hashtag-research.md - Hashtag research methodology and tools

Quality Checklist

Before finalizing summaries:

  • Hook grabs attention in first 5 words
  • Value proposition is crystal clear
  • Content matches platform tone and length
  • Hashtags are relevant and strategic
  • Call-to-action is specific and compelling
  • No jargon or unclear terms
  • Emotional resonance is present
  • Unique angle or insight is highlighted
  • Grammar and formatting are polished

Example Usage

User: "根據這個 SRT 生成影片介紹"

Process:

  1. Read and analyze the SRT file
  2. Extract core message and key insights
  3. Identify target audience and tone
  4. Generate platform-specific summaries
  5. Select strategic hashtags
  6. Output formatted markdown file

The result will be engaging, platform-optimized content that drives views and engagement.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the SRT Social Summary AI skill do?

This skill should be used when the user asks to "generate social media summary from srt", "create platform-specific descriptions", "generate Facebook post from transcript", "create YouTube description from srt", "write Thread post from subtitles", "生成影片介紹", "根據逐字稿生成貼文", or needs to create engaging social media content from SRT subtitle files for Facebook, Thread, or YouTube platforms.

Why use SRT Social Summary on TypingMind?

Because you install it once and use it with any model. SRT Social Summary is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install SRT Social Summary in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dean9703111/ai-agent-skill-for-video-workflow/tree/master/.agent/skills/srt-social-summary. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use SRT Social Summary?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with SRT Social Summary?

As many as you like. As long as a model supports skills, you can use SRT Social Summary with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the SRT Social Summary AI skill free?

It is published on GitHub by dean9703111. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇