LibTV image & video creation: AI generation and editing via the LibTV platform
Create sessions, send natural-language prompts (text-to-image, text-to-video, edits), upload references, poll progress and download results through the LibTV OpenAPI
- What
- Create sessions, send natural-language prompts (text-to-image, text-to-video, edits), upload references, poll progress and download results through the LibTV OpenAPI
- Cost
- Free
- Needs
- a LIBTV_ACCESS_KEY from the LibTV platform (paid service β save it in the vault, never paste it here); Python 3 stdlib only, no extra dependencies
- Install
- Copy the installer prompt below into your Muse β your agent does the rest.
π³ **Paid API required** β the skill drives the LibTV platform and requires a `LIBTV_ACCESS_KEY` (paid image/video generation service). Curated by Skill Harbor β @libtv-labs' agent-im skill for creating and editing images and videos through the LibTV (LiblibAI) platform: text-to-image, text-to-video, image-to-video, video continuation, local edits, element replacement, style transfer, video replication, plus complex creations like one-sentence short dramas (script β storyboard β finished piece), music MVs, product ad films, storyboard design and educational videos, powered by models such as Seedance 2.0, Kling 3.0/O3, Wan 2.6, NanoBanana, Midjourney and Seedream 5.0. The agent acts as a courier: upload reference files to OSS, pass the user's raw description verbatim to the session, poll progress, auto-download results, and present result links plus the project canvas link β it must never rewrite, expand or self-decompose the user's prompt (the backend agent is the specialist). Five operations via stdlib-only Python scripts: create_session/send message, query session progress (8-second incremental polling, 3-minute timeout), switch project, upload files (200MB max), batch-download results. Honest caveats: **the skill is written in Chinese**; complex generations (short dramas, MVs) take a long time β budget patience. MIT-licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: a LIBTV_ACCESS_KEY from the LibTV platform (paid service β save it in the vault, never paste it here); Python 3 stdlib only, no extra dependencies Install "LibTV image & video creation: AI generation and editing via the LibTV platform" for me. It gives my agent the LibTV agent-im skill: create sessions and send natural-language messages (text-to-image, text-to-video, edits, style transfer, short dramas, MVs), upload reference images/videos to OSS, poll session progress every 8 seconds with incremental seq pulling, switch projects, and batch-download results β the agent acts as a courier and must pass the user's raw description verbatim, never rewriting or expanding it. Paid API. Written in Chinese; MIT-licensed. Repository: https://github.com/libtv-labs/libtv-skills/blob/main/skills/libtv-skill/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "libtv-skill". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. save my LIBTV_ACCESS_KEY in the vault, then ask the agent to generate or edit an image/video). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you β no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the sellerβs own page, usually Stripe.
What does the β next to a creatorβs name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself β always check a build before installing it.