跳到正文
cccskills
免费在 GitHub 公开

video-generator

Turn a short description into a planned video shot with clear subject movement, camera behavior, lighting, and pacing. Receive a generated clip when generation is available, or a ready-to-use prompt with a target aspect ratio and duration.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Create short videos and motion clips from a text description using AI video generation.

查看安装方法

适用场景

  • Creating short clips for social media
  • Planning product motion shots
  • Preparing supplementary footage
  • Creating animated backgrounds

包含的文件(1)

  • SKILL.md2.6 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Video Generator

Act as the director who briefs the video model. A video prompt has to carry everything a still image does plus time — what moves, how the camera behaves, and what changes between the first frame and the last. Your job is to turn a one-line request into a shot that reads as deliberate rather than as a wobbling still.

When to use this skill

Use Video Generator for short social clips, product motion, b-roll, animated backgrounds, and any request that names a video, clip, animation, or motion. Reach for it whenever the deliverable moves.

Anatomy of a strong video prompt

Build the shot deliberately rather than describing a picture and hoping it animates. Cover:

  • Subject — who or what is in frame, concretely, including how it is framed at the start.
  • Motion — what the subject actually does, as one continuous action. One clear action beats three vague ones.
  • Camera — static, pan, tilt, dolly in/out, tracking, orbit. Name it; "cinematic" is not a camera move.
  • Setting & lighting — where this happens and how it is lit, including time of day.
  • Style & mood — live-action / 3D / anime / stop-motion, plus the feeling and pacing.
  • Duration fit — what can plausibly complete in the clip's length. A four-second shot holds one beat, not a sequence.

Be specific where it matters and silent where it doesn't. Contradictory motion (a static camera that also orbits) is the most common cause of a smeared result.

Working within the clip's length

  • Short clips (4–6s): one subject, one action, one camera move.
  • Longer clips (8–12s): a single action that develops — an approach, a reveal, a turn — not a cut between scenes.
  • Never ask for cuts, scene changes, or on-screen text; generate separate clips and assemble them instead.

How to work

  1. Clarify the subject, the motion, the camera, and the target platform's aspect ratio and length.
  2. Compose a prompt covering the anatomy above, in one paragraph.
  3. Generate, then judge the result against the brief before offering it — a clip that ignored the camera move is a prompt problem, not a taste problem.
  4. Offer variations that change a meaningful axis (camera, pacing, or lighting), not trivial reworks.

Output format

Return the generated clip when generation is available; otherwise return the finished, ready-to-use prompt. For each, note the aspect ratio and duration it targets and one line on the directorial choice. When delivering variations, label each by the axis it explores.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Build holaOS apps for connecting external services or managing work through a dashboard. The skill uses shared SDK building blocks for stored records, actions, and synchronization, with the dashboard and agent tools working on the same data.

中文简介正在准备中。当前显示英语简介。

  • Building an external service integration
  • Creating a CRM dashboard
  • Building a content planning workspace
holaboss-ai/holaOS1.1万2026年8月21日 更新

Analyze audience demographics and engagement to identify distinct groups, understand what they want, and prioritize valuable segments. Turn those findings into recommendations for content topics, formats, posting times, and tone, while explaining limits in the data.

中文简介正在准备中。当前显示英语简介。

  • Identify distinct groups within an audience
  • Prioritize groups that engage or convert
  • Plan topics and formats for each audience group
holaboss-ai/holaOS1.1万2026年8月21日 更新

Guide an agent through efficient use of an embedded browser by choosing targeted actions, searches, and waits. Reduce repeated tool calls and unnecessary page snapshots, while using more detailed inspection when the target or result remains unclear.

中文简介正在准备中。当前显示英语简介。

  • Act on known buttons or fields with fewer browser calls
  • Locate a known target on a large page
  • Wait for navigation or downloads to finish
holaboss-ai/holaOS1.1万2026年8月21日 更新

Validate workflows and reproduce issues in an embedded browser. Distinguish application problems from incorrect targets, missing waits, or session state, then report the shortest reliable reproduction steps with only the evidence needed to support the finding.

中文简介正在准备中。当前显示英语简介。

  • Reproducing a browser workflow failure
  • Checking for regressions after a fix
  • Distinguishing timing issues from application failures
holaboss-ai/holaOS1.1万2026年8月21日 更新

Build the user interface for a holaOS app whose data resources are already connected through the SDK. Choose a feed, table, kanban board, form, or calendar layout using shared components and workspace styling.

中文简介正在准备中。当前显示英语简介。

  • Display scheduled items in a chronological feed
  • Show CRM contacts or tickets in a table
  • Organize issues by status on a kanban board
holaboss-ai/holaOS1.1万2026年8月21日 更新

Package workspace skills and their required service integrations into one named, installable capability. Create a manifest that references existing skills, install the capability, and report which integrations still need to be connected.

中文简介正在准备中。当前显示英语简介。

  • Bundle multiple skills for a shared outcome
  • Declare required external service integrations
  • Create a manifest that references existing skills
holaboss-ai/holaOS1.1万2026年8月21日 更新

查看 holaboss-ai 的全部技能

报告此技能的问题