AI-powered image and video creation through natural language, supporting generation, editing, style transfer, and complex multi-step workflows.
Works with
Covers text-to-image, text-to-video, image-to-video, video continuation, style transfer, and advanced tasks like one-prompt short film generation, music video creation, and product showcase production
Integrates top-tier models including Seedance 2.0, Kling 3.0/O3, Wan 2.6, and Midjourney, with automatic workflow orchestration by backend agents
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionlibtv-skillExecute the skills CLI command in your project's root directory to begin installation:
Fetches libtv-skill from libtv-labs/libtv-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate libtv-skill. Access via /libtv-skill in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
14
total installs
14
this week
464
GitHub stars
0
upvotes
Run in your terminal
14
installs
14
this week
464
stars
通过 agent-im 的 OpenAPI 创建会话、发送消息(生图、生视频、编辑视频等)、上传图片/视频文件,并查询会话消息进展。
LibTV 是 LiblibAI 推出的 AI 视频创作平台,同时为人类创作者和 Agent 设计。Agent 通过 Skill 入口理解任务、调用模型并自动编排工作流。
平台核心能力:
用户的所有创作和编辑需求都通过发送自然语言消息来完成,Agent 会自主编排工作流。复杂任务(短剧、MV)耗时较长,需耐心轮询。
export LIBTV_ACCESS_KEY="your-access-key"
可选:OPENAPI_IM_BASE 或 IM_BASE_URL,默认 https://im.liblib.tv。
无需安装额外依赖,仅使用 Python 标准库。
# 创建新会话并发送「生一个动漫视频」
python3 {baseDir}/scripts/create_session.py "生一个动漫视频"
# 向已有会话发送消息
python3 {baseDir}/scripts/create_session.py "再生成一张风景图" --session-id SESSION_ID
# 只创建/绑定会话,不发消息
python3 {baseDir}/scripts/create_session.py
# 查询会话消息列表
python3 {baseDir}/scripts/query_session.py SESSION_ID
# 增量拉取(只返回 seq 大于 N 的消息)
python3 {baseDir}/scripts/query_session.py SESSION_ID --after-seq 5
# 附带项目地址(传入 create_session 返回的 projectUuid,结果中带 projectUrl)
python3 {baseDir}/scripts/query_session.py SESSION_ID --project-id PROJECT_UUID
# 切换当前 accessKey 绑定的项目(后续创建会话将使用新项目)
python3 {baseDir}/scripts/change_project.py
当用户提供了参考的文件地址时,进行上传,仅支持图片、视频,文件大小必须在200M以下。
# 上传图片
python3 {baseDir}/scripts/upload_file.py /path/to/image.png
# 上传视频
python3 {baseDir}/scripts/upload_file.py /path/to/video.mp4
生成完成后,可以将会话中的所有图片/视频批量下载到本地。
# 从会话自动提取并下载所有结果
python3 {baseDir}/scripts/download_results.py SESSION_ID
# 指定输出目录
python3 {baseDir}/scripts/download_results.py SESSION_ID --output-dir ~/Desktop/my_project
# 指定文件名前缀(如 storyboard_01.png, storyboard_02.png ...)
python3 {baseDir}/scripts/download_results.py SESSION_ID --prefix "storyboard"
# 直接下载指定 URL 列表(不需要 session_id)
python3 {baseDir}/scripts/download_results.py --urls URL1 URL2 URL3 --output-dir ./output
理解这些工作流,才能正确组合上面的脚本完成用户需求。
1. create_session.py "用户的描述" → 拿到 sessionId + projectUuid
2. 每隔 8 秒调用 query_session.py SESSION_ID --after-seq 0 轮询
3. 检查 messages:当出现 assistant 角色的消息且包含图片/视频 URL → 任务完成
4. 自动下载:download_results.py SESSION_ID --output-dir ~/Downloads/项目名 --prefix 有意义的前缀
5. 向用户展示:本地文件列表 + projectUrl(画布链接)
生成完成后自动执行下载,不需要用户额外请求。下载目录和前缀根据任务语义自动命名(如分镜用 storyboard,角色设定用 character 等)。
1. upload_file.py /path/to/video.mp4 → 拿到 OSS URL
2. create_session.py "把四周的纸船都换成白色的纸爱心 参考视频:{oss_url}"
3. 后续同场景 1 的步骤 2-5
用户给了文件路径 + 编辑指令 = 先上传文件,再把编辑指令和 OSS URL 一起发送。
1. upload_file.py /path/to/ref.png → 拿到 OSS URL
2. create_session.py "根据参考图生成xxx,参考图:{oss_url}"
3. 后续同场景 1 的步骤 2-5
1. create_session.py "新的描述" --session-id SESSION_ID
2. 后续同场景 1 的步骤 2-5
--after-seq 0,后续用上次拿到的最大 seq 值create_session 返回:
{
"projectUuid": "aa3ba04c5044477cb7a00a9e5bf3b4d0",
"sessionId": "90f05e0c-...",
"projectUrl": "https://www.liblib.tv/canvas?projectId=aa3ba04c5044477cb7a00a9e5bf3b4d0"
}
query_session 返回:
{
"messages": [
{"id": "msg-xxx", "role": "user", "content": "生一个动漫视频"},
{"id": "msg-yyy", "role": "assistant", "content": "..."}
],
"projectUrl": "https://www.liblib.tv/canvas?projectId=..."
}
(projectUrl 仅在传入 --project-id 时存在)
change_project 返回:
{
"projectUuid": "新项目UUID",
"projectUrl": "https://www.liblib.tv/canvas?projectId=新项目UUID"
}
upload_file 返回:
{
"url": "https://libtv-res.liblib.art/claw/{projectUuid}/{uuid}.png"
}
download_results 返回:
{
"output_dir": "/Users/xxx/Downloads/libtv_results",
"downloaded": ["/Users/xxx/Downloads/libtv_results/01.png", "..."],
"total": 9
}
query_session 返回的 messages 中 assistant 消息的 content 或结果里的视频/图片 URL,即「返回的结果」。create_session 返回的 projectUrl,或自行拼接 https://www.liblib.tv/canvas?projectId= + projectUuid。查询进展时若传入 --project-id PROJECT_UUID,query_session 会直接返回 projectUrl,便于一并展示。在任务完成时,同时给出:视频/图片结果链接 + 项目画布链接(projectUrl)。 过程中,不要给出 项目画布链接(projectUrl)。
你(用户侧 Agent)的职责是搬运工,不是创作者。后端有专门的 Agent 负责理解需求、拆解分镜、编排工作流、选模型、写 prompt。你要做的只有三件事:
upload_file.py 拿到 OSS URLcreate_session.py绝对不要做的事:
后端 Agent 对模型能力、参数配置、prompt 工程远比用户侧更专业。用户侧越俎代庖只会降低生成质量,换个弱模型更是灾难。
正确示例:
用户说:「帮我推演后续的故事,来个分镜大爆炸,帮我出一个16:9的九宫格的图。新建一个任务。」
用户给了参考图:/path/to/ref.png
→ upload_file.py /path/to/ref.png → 拿到 oss_url
→ create_session.py "帮我推演后续的故事,来个分镜大爆炸,帮我出一个16:9的九宫格的图。参考图:{oss_url}"
→ 轮询 → 下载 → 展示
错误示例:
❌ 用户侧自己先写了个九宫格分镜表(对峙、交锋、危机...)
❌ 然后把自己编的描述发给后端
❌ 或者拆成9次 create_session 分别发送
Authorization: Bearer <LIBTV_ACCESS_KEY>message,仅创建/绑定会话,不会调用 SendMessage--after-seq 做增量拉取,便于轮询新消息(含 assistant 回复与生图/生视频结果)https://www.liblib.tv/canvas?projectId= + projectUuidhttps://libtv-res.liblib.art/claw/{projectUuid}/{uuid}{ext}Make data-driven prioritization decisions faster
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Prerequisites
Time Estimate
30-60 minutes to see productivity improvements
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
mattpocock/skills
parcadei/continuous-claude-v3
cursor/plugins
ailabs-393/ai-labs-claude-skills
pproenca/dot-skills
mattpocock/skills
libtv-skill has been reliable in day-to-day use. Documentation quality is above average for community skills.
libtv-skill reduced setup friction for our internal harness; good balance of opinion and flexibility.
libtv-skill reduced setup friction for our internal harness; good balance of opinion and flexibility.
libtv-skill is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
Solid pick for teams standardizing on skills: libtv-skill is focused, and the summary matches what you get after install.
We added libtv-skill from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
Keeps context tight: libtv-skill is the kind of skill you can hand to a new teammate without a long onboarding doc.
I recommend libtv-skill for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
I recommend libtv-skill for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Useful defaults in libtv-skill — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
showing 1-10 of 45