- Home
- Skills
- Workflow Automation
- clipvault
More screenshots
Works with the AI Agents you already use
clipvault
Index video footage into Obsidian and generate social media clip packs with hooks, captions, and posting plans.
$39.99
clipvault
Example session with this skill installed
I need to index my podcast folder at /Users/dev/podcasts into Obsidian and find the best 3 hooks for TikTok.
- Read your context and instructions
- Compiled the clipvault
I have initiated the indexing process for your podcast folder. The videos have been scanned shot-by-shot, and the metadata has been synced to your Obsidian vault. I have identified three high-impact segments suitable for TikTok based on hook strength and visual clarity.
ClipVault Content Index & Hooks
| Clip ID | Timestamp | Hook Text | Visual Description | Platform Priority |
|---|---|---|---|---|
| POD_042_01 | 04:12 - 04:45 | "The one mistake every junior dev makes..." | Close-up on speaker, high energy. | TikTok, Reels |
| POD_042_02 | 12:05 - 12:50 | "Why your CI/CD pipeline is actually slowing you down." | Screen share showing complex YAML. | TikTok, X |
| POD_043_01 | 08:30 - 09:15 | "Stop using em-dashes in your documentation." | Mid-shot, pointing at screen. | TikTok, Shorts |
Social Media Metadata
Clip POD_042_01
- Caption: Avoid this common career trap. #coding #career #webdev
- Thumbnail Idea: Bold text "DEV TRAP" with a shocked facial expression overlay.
- Platform Plan: Post Tuesday at 10 AM EST.
Next steps
- Open your Obsidian vault to view the full shot-by-shot breakdown.
- Run
python clipvault.py pack POD_042_01to generate the final asset folder. - Import the identified timestamps into your editor for final export.
Connects securely to your tools. The creator never sees your data.
About this skill
Managing a massive library of raw video footage is a bottleneck for content creators and editors. ClipVault automates the transition from raw files to an indexed Obsidian vault, enabling shot-by-shot search and automated social media clip preparation.
What it does
- Shot-by-shot indexing scans video files to create a searchable database within Obsidian.
- Moment ranking identifies and highlights the best segments based on specific criteria.
- Clip pack generation prepares cut clips with hooks, captions, and platform-specific metadata.
- Thumbnail planning suggests visual concepts for each clip to improve click-through rates.
- Posting schedules creates organized plans for distributing content across various social platforms.
How it works
- Run the
doctorcommand with the--jsonflag to verify the environment and dependencies. - Index your video directory to populate the Obsidian vault with shot metadata.
- Use the search or rank commands to identify high-value segments for social media.
- Execute the clip pack command to generate captions, hooks, and thumbnail concepts for the selected segments.
Frameworks & tools
This skill uses a Python-based CLI tool, clipvault.py, and integrates directly with Obsidian for documentation and indexing.
Why this beats prompting it yourself
Generic prompts cannot interact with local video files or maintain a persistent, searchable index of visual shots. This skill bridges the gap between raw video assets and structured content planning, ensuring no high-quality moment is lost in the editing process.
Use cases
- Content repurposing by finding viral moments in long-form podcasts or streams.
- Video asset management through a searchable Obsidian vault of all owned footage.
- Social media automation by generating hooks and captions for multi-platform posting.
- Thumbnail ideation based on specific shot data and visual hooks.
Known limitations
Requires a local Python environment and the Obsidian application to be installed. Initial indexing time depends on total video duration and hardware specs.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Workflow Automation.
Requires local Python 3 environment. Indexing speed depends on local hardware and video length. External video editing software is required to perform the physical cuts suggested.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 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
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed today
- Accounts
Hugging Face
- Software
Python
Permissions
Allowed Hosts