TypingMindTypingMindThe best frontend for AI
Video Overview Generator logo

Video Overview Generator

Community
simonmesmith
video-overview-generator

Create narrated video overviews from source documents using editable storyboard rows, OpenAI text-to-speech audio, OpenAI image generation, captions, and deterministic ffmpeg assembly. Use when Codex needs to turn PDFs, DOCX files, Markdown, text notes, research, meeting materials, briefs, or folders of documents into a NotebookLM-style static-image video overview with voiceover, or when the user wants to edit/regenerate individual narration or image rows without rebuilding the whole project.

Overview

Publishersimonmesmith
Repositoryagent-skills
Skill namevideo-overview-generator
Stars
51
Forks
5
Bundled files
13
LicenseGPL-3.0
Links
Skill sourceRepository
  • 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.

  • 13 bundled files

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

  • Open source

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

Installation

Install the Video Overview Generator 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/simonmesmith/agent-skills/tree/main/skills/video-overview-generator
  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/simonmesmith/agent-skills.git /tmp/agent-skills
mkdir -p .claude/skills
cp -r /tmp/agent-skills/skills/video-overview-generator .claude/skills/video-overview-generator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Video Overview Generator 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 Video Overview Generator 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 Video Overview Generator 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.

Video Overview Generator

Create document-grounded narrated videos from static generated images, voiceover, captions, and deterministic video assembly. Do not imply this skill generates motion-video footage. It creates an editable storyboard and renders a conventional video file from still images and audio.

Default Decisions

  • Project folder: create all work in a new video-overview/ folder unless the user names another destination.
  • Source ingestion: extract source text into source_map.json before writing a storyboard.
  • Storyboard source of truth: use storyboard.json. Export storyboard.csv only for easier human editing.
  • Image default: gpt-image-2, 2048x1152, medium, PNG, 16:9.
  • Audio default: gpt-4o-mini-tts, voice alloy, MP3.
  • Brand/icon default: start with #2563EB, then update agents/openai.yaml to match the final icon accent after sampling the generated PNG.
  • Disclosure: include a brief note in user-facing deliverables when the audio is AI-generated.
  • Cohesion default: define one project-level visual_direction and narration_direction before writing rows, then make every image prompt and spoken segment follow those directions.

Workflow

  1. Set up project files

    • Copy or reference the user's documents.
    • Run scripts/ingest_sources.py <source paths...> --out video-overview/source_map.json.
    • Read references/storyboard_schema.md before drafting or editing storyboard.json.

  2. Create the storyboard

    • Write a concise, source-grounded sequence of rows in storyboard.json.
    • Add a project-level visual_direction describing palette, composition, rendering style, lighting, recurring motifs, and avoid-list.
    • Add a project-level narration_direction describing tone, pacing, audience, voice continuity, and pronunciation notes if needed.
    • Keep each narration_text under 4096 characters for the speech endpoint; prefer 20-80 spoken words per row.
    • Write image prompts that describe a single strong 16:9 still image and explicitly inherit the same visual direction. Avoid precise in-image text unless the user explicitly needs it.
    • Keep speech elements aligned: same voice, tone, cadence, audience, and vocabulary level unless the user asks for a format shift.
    • Include source_refs for traceability.
    • Run scripts/create_storyboard.py --validate storyboard.json --csv storyboard.csv.

  3. Generate media

    • Require OPENAI_API_KEY for live OpenAI API calls.
    • Run scripts/generate_media.py storyboard.json --media-dir media.
    • The script writes one image and one audio file per row and skips unchanged assets using hashes in manifest.json.
    • Use --ids row_001,row_004 to regenerate selected rows.

  4. Render the video

    • Run scripts/render_video.py storyboard.json --media-dir media --out output/video-overview.mp4.
    • The renderer uses actual audio durations, creates captions, and concatenates row clips.
    • If only timing, captions, or transitions changed, rerender without regenerating API assets.

  5. Iterate safely

    • For narration edits, regenerate only affected audio rows.
    • For image prompt edits, regenerate only affected image rows.
    • For timing/caption edits, skip API calls and rerender.
    • Preserve old assets unless the user explicitly wants cleanup.

Resource Map

  • references/storyboard_schema.md: required storyboard fields, defaults, and edit rules.
  • scripts/ingest_sources.py: extract text from TXT, Markdown, JSON, CSV, PDF via pdftotext, and DOCX via OOXML.
  • scripts/create_storyboard.py: validate JSON, normalize defaults, export/import CSV.
  • scripts/generate_media.py: call OpenAI image and speech endpoints row by row with caching.
  • scripts/render_video.py: assemble still images, row audio, and captions into MP4 with ffmpeg.
  • scripts/regen_item.py: patch one row from CLI flags and regenerate only needed assets.
  • assets/icon_prompts.json: prompts used to generate this skill's icon family.
  • assets/brand.json: provisional and sampled brand color metadata.

Quality Checks

  • Validate storyboard.json before media generation.
  • Confirm every row has an image, audio file, and measured audio duration before final render.
  • Confirm images are 16:9 when rendered into the final video.
  • Confirm the image sequence feels like one designed system, not five unrelated generations.
  • Confirm narration sounds like one coherent host/script, not disconnected row snippets.
  • Confirm final video duration roughly matches the sum of row audio durations.
  • Report any missing external tools (ffmpeg, ffprobe, pdftotext) plainly.

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 Video Overview Generator AI skill do?

Create narrated video overviews from source documents using editable storyboard rows, OpenAI text-to-speech audio, OpenAI image generation, captions, and deterministic ffmpeg assembly. Use when Codex needs to turn PDFs, DOCX files, Markdown, text notes, research, meeting materials, briefs, or folders of documents into a NotebookLM-style static-image video overview with voiceover, or when the user wants to edit/regenerate individual narration or image rows without rebuilding the whole project.

Why use Video Overview Generator on TypingMind?

Because you install it once and use it with any model. Video Overview Generator 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 Video Overview Generator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/simonmesmith/agent-skills/tree/main/skills/video-overview-generator. 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 Video Overview Generator?

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 Video Overview Generator?

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

Is the Video Overview Generator AI skill free?

Yes. It is published on GitHub by simonmesmith under the GPL-3.0 license. 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.

Related AI Skills

View all
openclaw logo

Camsnap

openclaw
OrganizationPopular

Capture frames or clips from RTSP/ONVIF cameras and local webcams, including USB pan/tilt/zoom control.

82.2K
391K
Instructions
View
affaan-m logo

Content Engine

affaan-m
CommunityPopular

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content…

40.4K
270.2K
1 files
View
affaan-m logo

Fal Ai Media

affaan-m
CommunityPopular

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio…

40.4K
270.2K
1 files
View
affaan-m logo

Video Editing

affaan-m
CommunityPopular

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in…

40.4K
270.2K
1 files
View

Set up your own AI workspace now

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