Skip to content
Agentmart
Submit a tool

media

Audio, image and video work: text-to-speech through an OpenAI-compatible endpoint (with a Russian fallback), audio/video transcription, image generation and…

Skill by youlianvr

IndexedCC-BY-4.0★ 14
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/youlianvr-media

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

Audio, image and video work: text-to-speech through an OpenAI-compatible endpoint (with a Russian fallback), audio/video transcription, image generation and editing, quick ffmpeg screenshot demo videos (while HyperFrames handles motion graphics and promos), YouTube transcript/content extraction, and the 4-stage novel-* short-drama pipeline.

Use cases: data, 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 8

  • api.link-ai.tech · found in code
  • api.minimaxi.com · found in code
  • api.openai.com · found in code
  • ark.cn-beijing.volces.com · found in code
  • codeload.github.com · found in install command
  • dashscope.aliyuncs.com · found in code
  • generativelanguage.googleapis.com · found in code
  • github.com · found in code

Files it touches

  • ~/.claude/skills/media

What's inside

Skill name
media
Description
Audio, image and video work: text-to-speech through an OpenAI-compatible endpoint (with a Russian fallback), audio/video transcription, image generation and editing, quick ffmpeg screenshot demo videos (while HyperFrames handles motion graphics and promos), YouTube transcript/content extraction, and the 4-stage novel-* short-drama pipeline.
License
CC-BY-4.0
Instructions
37 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Agent Skills spec issues

  • files: referenced but missing: scripts/generate.py

Files (86)

  • SKILL.md
  • LICENSE-shuohao · parts/
  • SKILL.md · parts/demo-video/
  • scene-design-system.md · parts/demo-video/references/
  • SKILL.md · parts/image-generation/
  • generate.py · parts/image-generation/scripts/
  • README.en.md · parts/novel-art/
  • README.md · parts/novel-art/
  • SKILL.md · parts/novel-art/
  • report.webp · parts/novel-art/assets/
  • 渡口-art.json · parts/novel-art/examples/
  • prop-pass.md · parts/novel-art/references/
  • report-style.md · parts/novel-art/references/
  • scene-pass.md · parts/novel-art/references/
  • schema.md · parts/novel-art/references/
  • sheet.md · parts/novel-art/references/
  • novel-art.mjs · parts/novel-art/scripts/
  • selftest.mjs · parts/novel-art/scripts/
  • README.en.md · parts/novel-characters/
  • README.md · parts/novel-characters/
  • SKILL.md · parts/novel-characters/
  • report.webp · parts/novel-characters/assets/
  • sheet.jpg · parts/novel-characters/assets/
  • 渡口-cast.json · parts/novel-characters/examples/
  • 渡口-cast.md · parts/novel-characters/examples/
  • 渡口.txt · parts/novel-characters/examples/
  • profile-pass.md · parts/novel-characters/references/
  • report-style.md · parts/novel-characters/references/
  • roster-pass.md · parts/novel-characters/references/
  • schema.md · parts/novel-characters/references/
  • sheet.md · parts/novel-characters/references/
  • style-presets.md · parts/novel-characters/references/
  • novel-characters.mjs · parts/novel-characters/scripts/
  • selftest.mjs · parts/novel-characters/scripts/
  • README.en.md · parts/novel-outline/
  • README.md · parts/novel-outline/
  • SKILL.md · parts/novel-outline/
  • report.webp · parts/novel-outline/assets/
  • 渡口-outline.json · parts/novel-outline/examples/
  • episode-pass.md · parts/novel-outline/references/
  • outline-pass.md · parts/novel-outline/references/
  • report-style.md · parts/novel-outline/references/
  • schema.md · parts/novel-outline/references/
  • volume-pass.md · parts/novel-outline/references/
  • novel-outline.mjs · parts/novel-outline/scripts/
  • selftest.mjs · parts/novel-outline/scripts/
  • README.en.md · parts/novel-script/
  • README.md · parts/novel-script/
  • SKILL.md · parts/novel-script/
  • report.webp · parts/novel-script/assets/
  • 渡口-script.json · parts/novel-script/examples/
  • report-style.md · parts/novel-script/references/
  • schema.md · parts/novel-script/references/
  • script-pass.md · parts/novel-script/references/
  • novel-script.mjs · parts/novel-script/scripts/
  • selftest.mjs · parts/novel-script/scripts/
  • SKILL.md · parts/ru-tts-fallback/
  • LICENSE.txt · parts/speech/
  • SKILL.md · parts/speech/
  • openai.yaml · parts/speech/agents/
  • …and 26 more

SKILL.md (first lines)

# media — speech, image, video, and story production

> Home branch in Memora: `root/skill/media`.
>
> For motion graphics, animated explainers, and product promos, use the
> `hyperframes` skill first; use `parts/demo-video/` here when you need a fast
> `ffmpeg` stitch of existing screenshots with TTS narration.

## Choosing a part

| Task | Part |
|---|---|
| Russian & multilingual TTS fallback (`edge-tts` / local pipeline, default voice path) | `parts/ru-tts-fallback/` |
| Speech synthesis via an OpenAI-compatible `/v1/audio/speech` endpoint | `parts/speech/` |
| Audio/video transcription to text | `parts/transcribe/` |
| Generate or edit images via `scripts/generate.py` (a local gateway or provider keys from the root `.env`) | `parts/image-generation/` |
| Fast `ffmpeg` + `edge-tts` video stitch from HTML scenes or screenshots | `parts/demo-video/` |
| Extract transcripts from YouTube videos | `parts/youtube-transcripts/` |
| Extract full structured content from YouTube videos | `parts/youtube-full/` |
| Short-drama stage 1: adaptation brief, cast, hook/beat table → `outline.json` | `parts/novel-outline/` |
| Short-drama stage 2: character profiles, image/voice prompts, character sheets | `parts/novel-characters/` |
| Short-drama stage 3: scene sets, consistency anchors, lighting variants | `parts/novel-art/` |
| Short-drama stage 4: timed screenplay with dialogue and beat flows → `script.json` | `parts/novel-script/` |

## Rules

- Walk `root/skill/media` in Memora before starting; record working voice/image models and pipeline parameters as nodes.
- Route TTS and image calls through the OpenAI-compatible base URL in the root
  `.env` (`OPENAI_API_BASE` and its key). Never pay or create an external account
  without the owner's approval through the host's question channel.
- Save generated images, audio, and video inside the target project's directory, and open the deliverable for the owner with `reveal_file`.

## Related

`ai-image-prompts-skill` (prompt engineering and style libraries), `decks` (slide presentations), `design` (visual composition).

From youlianvr/oper-share, CC-BY-4.0.

More from youlianvr/oper-share

Signals

Stars
14
Forks
4
Open issues
0
Last commit (this folder)
Oct 20, 2026 (9 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
CC-BY-4.0
Repository
github.com/youlianvr/oper-share
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from youlianvr

Cite this page

media skill. Agent Mart. https://agentmart.dev/skills/youlianvr-media (last updated 2026-10-24)