본문으로 건너뛰기
cccskills
무료GitHub에 공개

rn-motion-director

Motion-first AI video director for topic-to-video creation. Use when the user gives a theme, idea, article, script, or brief and wants AI to freely create a real animated video instead of a PPT/slideshow-style explainer; when deciding visual metaphors, motion grammar, scene beats, component choices, generated image needs, HyperFrames/Remotion implementation strategy, and anti-PPT QC.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(4)

  • SKILL.md6.2 KB
  • agents/openai.yaml258 B
  • references/anti-ppt-gate.md1.6 KB
  • references/motion-grammar.md2.5 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

AI 动效导演元 Skill

Role

Act as the director layer that turns a topic into a motion-first video concept and controls execution until the result behaves like video, not a deck.

This skill does not replace ra-video-production-director, hyperframes, remotion, image generation, or QC tools. It runs before and above them: define the motion language, choose the visual system, reject PPT-like plans, then hand off to the right production lane and keep the anti-PPT gate active.

Core Doctrine

Do not start from pages, slides, or cards. Start from movement.

For every topic, first find a visual metaphor that can move: a river, network, branching tree, orbit, factory line, swarm, collapse, compression, scanner, handoff, growth loop, map route, stack, wave, clock, lens, or machine.

Text is an anchor, not the main carrier. If a beat depends on reading a long paragraph, convert the idea into motion, structure, symbols, or images.

Workflow

1. Intake

Capture only decisions that change the creative path:

  • topic or source material
  • audience and platform if known
  • desired ratio and length; default to 16:9 and 30-60 seconds if unspecified
  • narration, silent motion graphic, or captioned explainer
  • factual accuracy level: casual, source-backed, or reference-replica
  • required style, reference video, component library, or image-generation skill

If the user simply gives a topic and asks for a video, proceed with best judgment. Do not ask for a full brief unless the missing answer changes the production route.

2. Source and Truth Gate

For factual, historical, scientific, legal, medical, financial, current, or named-entity topics, verify the core claims before writing the motion plan. Prefer primary or authoritative sources. Use absolute dates when dates matter.

Keep facts short. The video should not become an encyclopedia; facts exist to support the motion narrative.

3. Motion Thesis

Write one sentence:

This video moves by showing <visual metaphor> transforming from <start state> to <end state>, proving <core claim>.

Examples:

  • Human evolution: a time river branches, lights up tools, then becomes a migration network.
  • AI agents: one cursor splits into autonomous task nodes that route through tools and return as completed work.
  • Economic inflation: a stable price grid stretches, leaks, and rebalances.

If no moving metaphor is found, stop and invent one before planning scenes.

4. Beat Graph

Plan a continuous timeline, not pages. Each beat must include:

  • time: start-end seconds
  • narrative job: hook, reveal, contrast, mechanism, consequence, proof, close
  • main moving object: the element carrying motion
  • state change: what physically changes on screen
  • camera/layer motion: push, pan, parallax, orbit, crop, or stable base
  • text role: title, label, caption, counter, or none
  • asset need: code/SVG, generated image, screenshot, icon, footage, or none
  • PPT risk: what would make this beat feel like a slide

At least 80% of beats must have a visible state change beyond fade/slide-in.

5. Motion Grammar

Read references/motion-grammar.md before choosing primitives. Combine 2-4 motion primitives per video and reuse them with variation. Do not stack every effect everywhere.

6. Image and Asset Direction

Use generated images only when they carry narrative work: a character, scene, object, historical visual, metaphor, or visual texture that code cannot express well enough. Avoid decorative stock-like images.

If image generation is used, specify:

  • what the image must explain
  • where it appears in the timeline
  • how it moves after generation
  • whether it must match an existing visual system

Static images must be animated with crop, mask, parallax, reveal, light sweep, depth layers, or transformation. A still image plus text is not enough.

7. Implementation Route

Default to HyperFrames for authored motion videos in this workspace. Read and follow the relevant HyperFrames skills before writing composition code.

Use Remotion when the project is already React/Remotion-based or when React component reuse is the main advantage. Use Lottie/Rive/Three.js only for the specific visual layer that benefits from them.

If the user asks for a complete production, continue into production instead of stopping at a plan:

  • create source project under <WORKSPACE>/01-内容生产/视频工作台/动效项目/
  • render final MP4
  • archive to <WORKSPACE>/legacy-archive/
  • put contact sheets and QC artifacts under the same project 质检/ folder

8. Anti-PPT Gate

Read references/anti-ppt-gate.md before implementation and again before final delivery. If the plan fails, rewrite the motion plan before coding.

Hard fail conditions:

  • the plan is a list of pages/slides
  • most beats are title + bullets + fade
  • objects appear but do not transform or travel
  • there is no continuous visual system across beats
  • the same card layout repeats without meaningful motion changes
  • the user asked for a video but the output is only a storyboard

9. QC and Completion

Before calling a video done:

  • run the toolchain checks required by the selected renderer
  • extract keyframes at meaningful beat midpoints
  • inspect whether motion continuity is visible across the contact sheet
  • check text fit, resolution, duration, and archive paths
  • state remaining limitations honestly, especially if no audio or no generated images were used

Output Contract

For planning-only requests, output:

  1. Motion thesis
  2. Beat graph
  3. Component and asset plan
  4. Anti-PPT risks
  5. Production route

For production requests, use the same structure internally, then produce the actual video and final QC artifacts.

References

  • references/motion-grammar.md: visual metaphors and motion primitives.
  • references/anti-ppt-gate.md: checklist for rejecting slide-like videos.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

口播视频转录和口误识别。生成审查稿和删除任务清单。触发词:剪口播、处理视频、识别口误

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Pluviobyte/rnskill1.7천2026년 9월 21일 업데이트

将法天象地、同源巨大法相或角色力量显现的视觉参考制作成连续关键帧,再使用用户选择或可用的图生视频工具分段生成、检查和合成动作视频,不绑定成片平台。适用于本体与法相同框、领域展开、凝实与同步出招;不负责整部小说改编或普通图片轮播。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Pluviobyte/rnskill1.7천2026년 9월 21일 업데이트

口播基础素材包生成。转录口播、识别口误、生成审核页;用户确认后剪出新视频,Agent 再基于剪后视频重新转写、AI 校对字幕,输出后续口播成片可用的 source_cut.mp4 和 subtitles.srt。触发词:剪口播、处理口播素材、准备口播素材、识别口误、基础素材包

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Pluviobyte/rnskill1.7천2026년 9월 21일 업데이트

口播视频成片 Skill。把文章/口播稿/SRT、剪后视频和 HTML/图片素材串成分镜稿、时间线预览和最终 MP4;成片比例和动画风格从用户配置读取,动画默认使用小黑风格。触发词:口播成片、做分镜稿、时间线预览、合成口播视频、导出竖屏MP4

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Pluviobyte/rnskill1.7천2026년 9월 21일 업데이트

自进化 skills。记录用户反馈,更新方法论和规则。触发词:更新规则、记录反馈、改进skill

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Pluviobyte/rnskill1.7천2026년 9월 21일 업데이트

dbs

무료

dontbesilent 商业工具箱主入口。双模式:任务前路由(你的问题该用哪个 skill)+ 任务后导航(刚做完诊断,下一步该干什么)。 触发方式:/dbs、/商业、「帮我看看」、「下一步怎么走」 Main entry point for dontbesilent business toolkit. Dual mode: pre-task routing + post-task navigation. Trigger: /dbs, "help me with my business", "what's next"

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Pluviobyte/rnskill1.7천2026년 9월 21일 업데이트

Pluviobyte의 스킬 모두 보기

이 스킬의 문제 신고