Skip to content
Agentmart
Submit a tool

video_text_to_text

Describe/transcribe video content (such as .mp4, .mkv, .avi) into text.

Skill by lasertsole

IndexedMIT★ 5
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/lasertsole-video-text-to-text

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Describe/transcribe video content (such as .mp4, .mkv, .avi) into text. Use whenever the user uploads or refers to a video file and expects you to understand what happens in it. Enables non-multimodal LLMs to understand video by running this skill's script via the terminal tool.

Use cases: writing

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/video-text-to-text

What's inside

Skill name
video_text_to_text
Description
Describe/transcribe video content (such as .mp4, .mkv, .avi) into text. Use whenever the user uploads or refers to a video file and expects you to understand what happens in it. Enables non-multimodal LLMs to understand video by running this skill's script via the terminal tool.
License
MIT
Instructions
14 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Agent Skills spec issues

  • name: only lowercase letters, digits and single hyphens allowed

Files (5)

  • SKILL.md
  • __init__.py
  • __init__.py · scripts/
  • core.py · scripts/
  • fallback.py · scripts/

SKILL.md (first lines)

## Usage

This skill provides the VTT recognition logic. Use skill discovery to load this SKILL.md, then run the script with the **`terminal` tool** (the `python_repl` tool cannot import skill modules because its builtins are restricted).

- When video needs describing, call `skill_view` with name `video_text_to_text` (this file), then run:

```bash
python -c "from skills.builtin.core.video_text_to_text.scripts import vtt; print(vtt(video_path='{replace with the video location}', query='{replace with the question about the video}'))"
```

- `video_path` accepts a local absolute file path.
- `query` defaults to "what happen in the video?" when omitted.
- The script automatically falls back to frame-level image extraction when needed. The printed output is the ground-truth description — base your reply on it.

From lasertsole/sherry_agent, MIT.

More from lasertsole/sherry_agent

Signals

Stars
5
Forks
1
Open issues
0
Last commit (this folder)
Oct 18, 2026 (10 days ago)
Last release
Oct 18, 2026 (10 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/lasertsole/sherry_agent
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from lasertsole

Cite this page

video_text_to_text skill. Agent Mart. https://agentmart.dev/skills/lasertsole-video-text-to-text (last updated 2026-10-24)