Hmdb Database
CheckedAccess and query a comprehensive human motion database (HMDB) for detailed video analysis and action recognition.
Install on your platform
Showing Claude Code. One command installs this skill into any of the agents below.
- 1
Run this in your project
terminal$ npx skills add jimmc414/kosmos --skill hmdb-database -a claude-code Uses the open-source
skillsCLI and needs Node.js. Add-gto install it for your user instead of this project.
What we know about this skill
Publisher
jimmc414
Taken from the source listing. We haven't verified who controls this account.
Install target
Live repository
Not pinned. Installing fetches whatever the repository holds at the time you run the command.
Automated safety checks
This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No undeclared network calls: passed
Makes no network calls.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
No pipe-to-shell installers: passed
No pipe-to-shell or download-and-run installers.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
Pinned to a commit: passed
Scanned jimmc414/kosmos at 6cfe7f690d.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- 6cfe7f690d
- Scanned
- 2 files, 457 lines
About this skill
What it does
This skill provides access to the Human Movement Database (HMDB), a large video database of human actions. It allows AI agents to query and retrieve videos based on action categories, making it useful for tasks like activity recognition or generating training data for computer vision models. The HMDB contains over 360 different human actions performed by multiple individuals in various settings.
When to use it
- Activity Recognition Training: Generate a dataset of video clips for training an AI model to recognize specific human activities (e.g., "playing guitar," "jumping jacks").
- Video Search & Retrieval: Quickly find relevant videos from the HMDB based on action descriptions or keywords.
- Content Generation Research: Explore and analyze a diverse collection of human actions for research purposes related to biomechanics, sports analysis, or robotics.
- AI Agent Demonstration: Showcase an AI agent's ability to understand and interact with video data by querying the database.
Key capabilities
- Access to the HMDB video dataset
- Video retrieval based on action categories
- Support for a wide range of human actions (over 360)
- Multiple performers per action category
Example prompts
- "Find videos of people 'playing guitar'."
- "Show me examples of 'jumping jacks' from the HMDB."
- “Retrieve all videos categorized as ‘boxing’."
Tips & gotchas
The HMDB contains a wide variety of actions, so be specific with your queries to get relevant results. Understanding the HMDB action categories will improve search accuracy.