Communitygithub.com

CleanExpo/Pi-Dev-Ops:Remotion 编排器

用于一次生成 Remotion 视频的单命令技能,也是 Remotion 技能包的入口。支持说明视频、广告、宣传片、营销素材等。读取简报、分类意图、强制单一 Synthex ElevenLabs 语音、生成生产/波形计划,并按拓扑顺序调度子技能。

Pi-Dev-Ops:Remotion 编排器 是什么?

Remotion 编排器(remotion-orchestrator)是 Pi-Dev-Ops 中 Remotion 技能包的入口点,通过 `/remotion-video` 单命令通道将粗略的简报转化为结构化的生产包、渲染路径和最终报告。该技能强制使用单一 Synthex ElevenLabs 语音,禁止多语音转换或新供应商集成,并首先执行“发现简报门”(mandatory discovery brief gate),要求填写品牌、类型(当前仅支持 Explainer)、渠道、时长和具体主题等字段,拒绝模糊请求。输出是一个 JSON 波形计划,包含最多 8 个波次(根据视频时长),按拓扑顺序调度 10 个兄弟子技能(如 remotion-brand-research、remotion-designer、remotion-composition-builder 等),最终通过 Linear 票据追踪渲染的 MP4。支持品牌解析(如 ra、dr、nrpg、carsi、ccw),缩略图生成优先使用已连接的 Canva MCP,避免凭据探测,并可选择从渲染的 MP4 中提取帧。该技能在 Claude Code、Cursor 和其他兼容 MCP 的 AI 代理平台上运行,通过全局 symlink 的 `~/.claude/skills/remotion-*` 可用。

兼容平台✓Claude Code✓Codex CLI~Cursor✓Gemini CLI
npx skills add https://github.com/CleanExpo/Pi-Dev-Ops/tree/HEAD/skills/remotion-orchestrator

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

remotion-orchestrator — Remotion 技能包入口点

/remotion-video 单命令

/remotion-video 是 Remotion 营销视频的单命令通道。它将粗略的简报转化为一个受管的生产包、一个渲染路径和一个最终证据报告。

此命令路径的硬性规则:

  • 仅限单一语音;不支持多语音角色或每场景语音切换。
  • 仅使用现有的 Synthex ElevenLabs 凭据和语音配置。
  • 不引入新的供应商、新帐户或连接平台。
  • 除非操作者明确要求生产渲染,否则从 dry-run 开始。
  • 写入 .harness/remotion/<jobId>/production-packet.json、script.md、preflight-report.md 和 render-command.sh。
  • 绝不提交生成的 MP4。

该命令路由通过 remotion-script、remotion-production、remotion-direction、remotion-editing、remotion-integrations 和 remotion-professionalism,同时保留下面的现有 Remotion 技能包工作流。

Remotion 技能包的单一入口点 — 一组 10 个兄弟技能(remotion-orchestrator、remotion-brand-research、remotion-brand-codify、remotion-designer、remotion-colour-family、remotion-motion-language、remotion-screen-storyteller、remotion-marketing-strategist、remotion-composition-builder、remotion-render-pipeline)全局安装在 ~/.claude/skills/remotion-*(符号链接到 ~/Pi-Dev-Ops/skills/remotion-*)。在每个项目中都可使用,不仅限于 Pi-Dev-Ops。

发现简报门(turn 1,强制)

改编自 nexu-io/open-design (Apache-2.0)。在生成任何波形计划之前,先锁定简报。拒绝继续,直到所有必填字段都已填写 — 模糊的简报会导致过长的波形计划和偏离品牌的渲染。

必填字段

字段类型说明
brandBrandSlug必须在 src/brands/ 中解析。未知 → 首先调度 remotion-brand-research。
compositionExplainer | Intro | SocialAd | NIRReport | ProductDemov1 支持 Explainer;其他类型会回退并附上说明。
channellinkedin | youtube | instagram | tiktok | training驱动宽高比和时长纪律。
aspectRatio1920x1080 | 1080x1920 | 1080x1080如果省略,从 channel 推断默认值。
durationSec15 | 30 | 60 | 90 | 120驱动波次数量上限。
topic字符串一句话说明视频内容。“品牌宣传视频”会被拒绝 — 必须指明具体观点。
audience字符串如果省略,从 BrandConfig.audience.primary 继承,但创始人必须确认。

可选:school(颜色生成器的视觉风格覆盖)、voiceoverScript(如果已预编写则跳过讲故事技能)、referenceComposition(用于混音现有任务)。

硬性停止条件

  • topic 读起来像类别(“我们的产品”、“发布”)而不是具体声明 → 阻塞。
  • v1 中 composition ≠ Explainer 且没有显式的回退确认 → 阻塞。
  • 一个简报中提到了多个品牌 → 拆分为 N 个并行任务(每个品牌一个);绝不混用。

该门在计算波形计划之前运行。被阻塞的简报永远不会到达调度器。

调用

用户可以通过以下方式调用该包:

  • 说出以下任何短语:“使用 Remotion 技能包”、“remotion 包”、“使用 remotion”。
  • 命名任何单个技能(例如“使用 remotion-designer 检查此布局”)。
  • 提交一个分类为 intent: "video" 的简报(通过 app/server/brief.py)。

将自由文本的简报转化为结构化的渲染任务和波形计划,Pi-Dev-Ops 编排器(app/server/orchestrator.py 通过 P3-B 扇出进行调度)。

Remotion 项目

所有合成、品牌配置、运动/颜色助手以及渲染入口位于:

../../remotion-studio/

当从任何其他项目工作时,子技能在读取或编辑品牌/合成文件之前 cd 到该路径。渲染入口是从 remotion-studio 内部运行的 npx tsx render/render.ts ...。

触发器

简报包含以下任何词语:video、explainer、promo、ad、reel、intro、outro、cta、social cut、60s/30s/15s、render、marketing video、training video、release video、feature video,并与以下品牌标识符之一配对:dr / disaster recovery / nrpg / ra / restoreassist / carsi / ccw / carpet cleaners warehouse。

输入

Pi-Dev-Ops 规划器(Opus 4.7)调用此技能时提供:

  • brief — 原始自由文本请求
  • repo_url — 通常是 local:Pi-Dev-Ops/remotion-studio
  • linear_team_id、linear_project_id — 从 config/harness/projects.json 预解析

输出

写入 remotion-studio/.research/wave-plans/{job_id}.json 的波形计划 JSON,格式如下:

{
  "jobId": "ra-nir-explainer-2026-04-28T15-30-00",
  "brand": "ra",
  "composition": "Explainer",
  "channel": "linkedin",
  "durationSec": 60,
  "topic": "RestoreAssist NIR Phase 1 standardisation",
  "linear": { "teamId": "...", "projectId": "..." },
  "outputPath": "output/ra-nir-explainer-2026-04-28T15-30-00.mp4",
  "waves": [
    { "id": 1, "parallel": [ {"skill":"remotion-brand-research","if":"brands/ra.ts missing or stale"}, {"skill":"remotion-marketing-strategist"} ] },
    { "id": 2, "parallel": [ {"skill":"remotion-screen-storyteller"}, {"skill":"remotion-colour-family","if":"palette incomplete"}, {"skill":"remotion-motion-language","if":"motion missing"} ] },
    { "id": 3, "parallel": [ {"skill":"remotion-brand-codify","if":"any new brand artifacts"}, {"skill":"remotion-designer"} ] },
    { "id": 4, "serial":   [ {"skill":"remotion-composition-builder"}, {"skill":"remotion-render-pipeline"} ] }
  ]
}

波次数量纪律

  • ≤3 个波次用于输出 <30s
  • ≤5 个波次用于输出 ≤120s
  • ≤8 个波次用于输出 >120s

过度分解是此纪律防范的失败模式。

合成路由(简报 → 合成 ID)

简报信号合成
"explainer", "feature video", "how it works"Explainer
"intro", "title card", "channel opener"Intro (v1.1)
"ad", "promo", "reel", "social cut", "Instagram", "TikTok"SocialAd (v1.1)
"NIR report", "inspection report", RA + "report"NIRReport (v1.1)
"demo", "product walkthrough"ProductDemo (v1.1)

v1 仅支持 Explainer。其他合成 ID 返回:“{Composition} 将在 v1.1 中推出 — 回退到 Explainer,使用特定渠道框架”。

品牌解析

匹配关键词 → BrandSlug:

  • disaster recovery, dr → dr
  • nrpg → nrpg
  • restoreassist, ra, nir → ra
  • carsi → carsi
  • ccw, carpet cleaners warehouse → ccw

如果简报中提到了多个品牌,要求规划器拆分为 N 个并行任务(每个品牌一个)并发出 N 个波形计划。绝不将品牌混入一个合成中。

Linear 路由

渲染技能写入 MP4 后,此技能(或渲染技能)在从 config/harness/projects.json 映射的项目中打开一个 Linear 票据:

品牌Linear 团队项目
raa8a52f07-63cf-4ece-9ad2-3e3bd3c15673 (RA)3c78358a-b558-4029-b47d-367a65beea7b
dr / nrpg43811130-ac12-47d3-9433-330320a76205 (DR)d2c1d63b-1e85-424d-9278-efff15b0d46b
carsi91b3cd04-... (GP)运行时解析
ccw运行时运行时

缩略图和静态图像生成(首选 Canva — 切勿凭据探测)

对于视频缩略图、海报或任何营销静态图像,可靠路径是已连接的 Canva MCP,而不是原始图像生成 API 密钥:

  1. generate-design(design_type: your_story 用于 9:16,youtube_thumbnail 用于 16:9),附带详细的品牌对齐查询 — 在查询中传递调色板/标题;Canva 能可靠地渲染标题文本。
  2. 下载候选预览并选择最佳;create-design-from-candidate → export-design(PNG,目标 WxH,export_quality: pro)。

硬性规则(从 2026-07-01 的教训中学到):

  • 切勿为图像生成密钥进行凭据探测。 不要扫描 .env 文件或跨项目/环境运行 vercel env pull 寻找 GEMINI_API_KEY / OPENAI_API_KEY / AI_GATEWAY_API_KEY。自动模式分类器会将其阻塞为凭据探测,这会浪费整个会话。
  • Vercel “敏感”环境变量是只写的 — vercel env pull 返回它们为 EMPTY。不要试图拉取一个;从原始来源获取值或使用 Canva。
  • 如果没有连接图像工具且没有密钥在一次定向检查中可达,停止并一次性询问创始人 — 首先提供 Canva。
  • 从渲染的 MP4 中抓取帧(位于 node_modules/@remotion/compositor-*/ffmpeg 的捆绑 ffmpeg)是离线回退方案。注意:在 macOS 上,将兄弟 *.dylib 文件符号链接到 cwd,以便捆绑的 ffprobe/ffmpeg 能解析(SIP 会剥离 DYLD_*)。

此技能不做的事情

  • 不编写合成 — 那是 remotion-composition-builder。
  • 不运行 npx remotion render — 那是 remotion-render-pipeline。
  • 不编辑 BrandConfig 文件 — 那是 remotion-brand-codify。

它只规划 + 委托。

按项目使用模型

该包是共享基础设施;每个调用项目提供自己的运行时配置和 API 密钥。

关注点位置
技能定义~/.claude/skills/remotion-*(符号链接 → Pi-Dev-Ops/skills/remotion-*)— 全局可用。
Remotion Node 项目(合成、品牌配置、渲染入口)../../remotion-studio/ — 单个共享基板。
品牌配置Synthex/packages/brand-config/src/brands/{slug}.ts — 每个品牌单一事实来源,由每个为该品牌渲染的项目使用。(根据 RA-1985 / Synthex SYN-897 从 Pi-Dev-Ops/remotion-studio/src/brands/ 迁移。)
API 密钥(ElevenLabs、Telegram、Supabase、Linear、Remotion 许可证)调用项目的 .env / .env.local。技能在渲染时读取 process.env。
渲染的 MP4 输出默认在调用项目的 .remotion-renders/ 目录中。使用 --out= 覆盖。

为您的项目添加新品牌

如果您的项目(例如 Synthex)需要为尚未存在于 src/brands/ 中的品牌进行渲染:

  1. 针对该品牌的公开来源运行 remotion-brand-research。
  2. 运行 remotion-brand-codify 生成 Synthex/packages/brand-config/src/brands/{slug}.ts。
  3. 在 Synthex/packages/brand-config/src/types.ts 中扩展 BrandSlug 联合类型。
  4. 在 Synthex/packages/brand-config/src/brands/index.ts 中注册。
  5. 从 Synthex/packages/brand-config/ 运行 npm run typecheck(然后运行 npm run build 重新生成 dist/)。

当前已注册的品牌:dr、nrpg、ra、carsi、ccw、synthex、unite。

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

CleanExpo/Pi-Dev-Ops

Produce one or many consistent, on-brand faceless marketing videos from a topic: script, ElevenLabs voiceover with timestamps, one styled illustration per beat, ffmpeg stitch to 1080p, optional Unlisted YouTube upload. The look is a named style from styles.md (flat-line, hand-doodle, bold-kinetic, cinematic-photoreal, minimal-corporate, retro-print), so one command yields repeatable output per brand. The automated pipeline; distinct from faceless-video and video-director.

CleanExpo/Pi-Dev-Ops

Produce a faceless YouTube-style video (hand-drawn doodle / simple-illustration channels like Zen, Nick Invest) end-to-end from a single topic. ASKS FACT-vs-STORY mode first (non-fiction educational vs fiction storytelling) and branches the whole run — built to serve multiple clients/channels, not one fixed format. Reverse-engineers a proven reference video's script format, writes a new script in that format, generates an ElevenLabs voiceover with timestamps, creates one styled Artlist (AI Toolkit) image per timestamp, and stitches everything with FFmpeg — fully automated, no human recording. Use when the user says "faceless video", "/faceless-video", "doodle video", "make a YouTube short/long-form in the Zen style", or wants an organic faceless-channel content piece. Composes with video-distribution-strategist (channel/launch) and video-director (when motion/edit polish is wanted instead of stills).

CleanExpo/Pi-Dev-Ops

The 15+ year brand director extension of `brand-guardian` specifically for video — frame-by-frame audit of brand-mark integrity, Gun Metal `#1a1a1a` + Candy Red `#dc143c` consistency, NO AI slop, NO Lucide icons, custom geometric marks ONLY, real logos correctly placed. PASS / FAIL gate before any client-facing video ships. Use after `video-colorist` completes the grade pass.

CleanExpo/Pi-Dev-Ops

The 15+ year Director-of-Photography persona (Roger Deakins / Emmanuel Lubezki / Hoyte van Hoytema-tier) that owns shot composition, lens psychology, motion language, and the decision of which source (Remotion / Hyperframes / stock cinematic) each scene uses. Extends the existing `remotion-designer` + `remotion-motion-language` skills with a frame-by-frame shot-language framework. Use when the user says "cinematography", "shot list", "framing", "DoP", "lens choice", or invoked by `video-director` Phase 2.

CleanExpo/Pi-Dev-Ops

The 15+ year colorist persona (Light Iron / Company 3 / The Mill-tier) that applies per-brand LUT + grade pass to every Unite-Group video. Closes the "raw Remotion render colours" gap — today Remotion outputs whatever colours BrandConfig declares with zero cinematic grade. Use when the user says "colour", "grade", "LUT", "look", "cinematic finish", or invoked by `video-director` Phase 3 (post-production) after `video-sound-designer` mixes audio.

CleanExpo/Pi-Dev-Ops

The Creative Director persona that owns brief intake, composition selection and narrative POV for every Unite-Group video. ENTRY POINT for the Video Agency: use for any video creation brief (explainer, promo, social cut, demo reel, case study, testimonial, client video). Dispatches the full production team: script-writer, cinematographer, editor, sound designer, colorist, brand-guardian.

CleanExpo/Pi-Dev-Ops

The 15+ year platform-native distribution expert (early TikTok creator economy + YouTube algorithm + LinkedIn organic reach + IG Reels native specialist) that owns per-platform aspect ratio + duration cap + caption format + hook density + thumbnail composition. Extends `remotion-marketing-strategist` with platform-native specs locked per BrandConfig. Use when the user says "which platform", "distribution", "channel-fit", "thumbnail", "captions", or invoked by `video-director` Phase 4 (QA + Delivery) for per-platform cuts.

CleanExpo/Pi-Dev-Ops

The 15+ year screenwriter persona (Pixar / Apple keynote / Nike spot tier) that engineers hooks (0-3s), retention beats (7-15s), narrative tension curves, and CTA placement. Extends the existing `remotion-screen-storyteller` skill with a structural framework lifted from Pixar's 22 Rules + Apple keynote architecture. Use when the user says "script", "voiceover", "narration", "hook", "story arc", or invoked by `video-director` Phase 2.

CleanExpo/Pi-Dev-Ops

The 15+ year sound designer persona (Skywalker Sound / Sound Lounge / Audio Network-tier) that mixes ElevenLabs voiceover with music bed, sound effects, ambient texture, and audio polish. Closes the single biggest gap in the existing Remotion pipeline — today voiceover is the ONLY audio; this skill adds music + SFX + mix. Use when the user says "sound design", "audio mix", "music bed", "SFX", "score this", or invoked by `video-director` Phase 3 (post-production).

CleanExpo/Pi-Dev-Ops

Converts a BrandResearch dossier into THREE artifacts — (1) typed BrandConfig TypeScript at Synthex/packages/brand-config/src/brands/{slug}.ts (runtime/behaviour — voice, voiceover, motion, audience, channel, forbiddenWords); (2) spec-conformant {slug}.design.md at Synthex/packages/brand-config/src/brands/{slug}.design.md (visual tokens — colour, typography, spacing, components, layout, elevation); (3) human-readable 9-section .md projection at Pi-Dev-Ops/remotion-studio/src/brands/{slug}.md derived from BOTH. Boundary contract at Pi-Dev-Ops/remotion-studio/src/brands/CONTRACT.md. Triggered after remotion-brand-research, or when the user pastes brand assets and says "codify". PRs are auto-merge:false — a human reviews before merge.

CleanExpo/Pi-Dev-Ops

Researches a portfolio company's visual identity from public sources (homepage, about page, marketing copy, GitHub README) and produces a structured BrandResearch dossier. Triggered when `Synthex/packages/brand-config/src/brands/{slug}.ts` (canonical home per RA-1985 / Synthex SYN-897) is missing, older than 90 days, or the user explicitly says "refresh brand for {brand}". Output feeds remotion-brand-codify.

CleanExpo/Pi-Dev-Ops

Generates a complete, accessible palette (primary, secondary, accent, 4-step neutral, semantic, and dark variant) from one to three hex anchors plus a colour-family classification. Validates WCAG-AA contrast for all text-on-background pairs. Triggered when a BrandConfig has fewer than 5 defined colours or contrast fails.

CleanExpo/Pi-Dev-Ops

Authors or extends a Remotion composition (.tsx) wired to BrandConfig + Storyboard + layout spec + motion. The actual builder skill — runs as a Sonnet-tier worker. Triggered after brand, storyboard, designer, and motion-language outputs are ready. Produces the file under remotion-studio/src/compositions/ and registers it in src/Root.tsx.

CleanExpo/Pi-Dev-Ops

Visual-design specialist for Remotion compositions. Sets layout grid, typography hierarchy, white-space, scene framing, and visual rhythm for a given composition + brand. Triggered after remotion-composition-builder for QA, or upfront when authoring a new composition type. Produces a layout spec consumed by remotion-composition-builder.

CleanExpo/Pi-Dev-Ops

Use when a Remotion video needs creative direction — hook, visual sequence, scene purpose, motion restraint, and CTA direction before render.

CleanExpo/Pi-Dev-Ops

Use when a Remotion video has timing, sync, transition, caption, pacing, or audio-fit risk and needs editing discipline before render.

CleanExpo/Pi-Dev-Ops

Use when /remotion-video needs existing Synthex ElevenLabs, brand-config, Remotion, output storage, Claude, or Hermes integration without adding vendors.

CleanExpo/Pi-Dev-Ops

Tunes a video's format and message for the target channel — LinkedIn, YouTube, Instagram Reel, internal training. Sets aspect ratio, total duration, hook timing, CTA timing, and pacing. Triggered when the brief mentions a specific channel or campaign goal. Output feeds remotion-screen-storyteller and remotion-composition-builder.

CleanExpo/Pi-Dev-Ops

Designs a brand-specific motion vocabulary — easing curves, default scene durations, signature entry/exit, transition frames. Each brand gets one signature move (rise / sweep / pulse / iris / whip) that recurs across compositions to build motion-recognition. Triggered when BrandConfig.motion is empty.

CleanExpo/Pi-Dev-Ops

Use when a Remotion video job needs production gates, render evidence, output discipline, and pass/fail validation before it can be called shippable.

相关技能