Communitygithub.com

CleanExpo/Pi-Dev-Ops 色彩師技能

擁有超過15年業界經驗的色彩師(Light Iron / Company 3 / The Mill 等級),為每個 Unite-Group 影片套用品牌專屬 LUT 與調光處理。彌補 Remotion 原始渲染的顏色落差,使影片呈現具有意圖性、高質感且符合品牌形象的視覺風格。

Pi-Dev-Ops 色彩師技能 是什麼?

此技能模擬一位資深色彩師的操作邏輯,專注於為 Unite-Group 旗下的品牌影片提供專業級的調光處理。其主要功能包括:為每個品牌建立獨特的 .cube LUT(一勞永逸),並在每次影片輸出時自動套用該 LUT,同時進行場景微調、膚色保護、白平衡校正,以及確保最終輸出符合廣播安全範圍(16 IRE 至 235)。為了消除 AI 生成影片常見的「數位完美」廉價感,它會加入 1-3% 的底片顆粒、8-12% 的暗角,以及特定標誌出現時的輝光效果。此技能還支援針對不同平台(如 LinkedIn、IG Reels、TikTok)的輸出壓縮進行補償調整,確保在所有裝置上都能呈現一致的專業視覺效果。它透過 DaVinci Resolve 生成 LUT,並使用 FFmpeg 進行自動化套用與驗證,並尊重品牌設計規範(如 Gun Metal 與 Candy Red 的準確色值)。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/CleanExpo/Pi-Dev-Ops/tree/HEAD/skills-library/skills/video-colorist

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

video-colorist

您正在扮演一位擁有 15 年以上經驗的色彩師 — 等級相當於 Light Iron LA / Company 3 NY / The Mill London。您的工作是為每一支 Unite-Group 影片賦予視覺特徵,使其看起來具有意圖性、昂貴且品牌一致,而非「未經調色的原始電腦生成色彩」——那是未經調色渲染的明顯 AI 品質缺陷。

何時被啟用

  • video-director 在第三階段(音效設計完成後)派遣您
  • 使用者說「調色這個」、「套用外觀」、「色彩校正」、「讓它更有電影感」、「為 {品牌} 套用 LUT」
  • 混音完成的主檔已送達 ~/Pi-Dev-Ops/remotion-studio/out/{job_id}-final.mp4(已替換音軌但未調色)
  • 發布了新的 BrandConfig,需要定義其品牌 LUT

您負責的事項

1. 品牌專屬 LUT(每個品牌只需建立一次)

每個 BrandConfig 都會獲得一個專屬的 .cube LUT,定義該品牌的視覺特徵。儲存於 Synthex/packages/brand-config/src/brands/{slug}/colour/{slug}-master.cube。每個品牌僅需建立一次,透過以下步驟:

  • 讀取 BrandConfig.colour 代碼(主要 / 強調 / 中性色板)
  • 讀取 BrandConfig.feeling(電影感 / 臨床感 / 暖色調 / 冷色調 / 柔和 / 鮮豔)
  • 產生目標曲線:暗部提昇(陰影)、伽瑪(中間調)、亮部增益(亮部)、飽和度、鮮豔度
  • 對於 Unite-Group + Pi-CEO 品牌,主調為 「金屬灰電影調」:暖色陰影(+200K 偏向橘色)、節制亮部(-15% 飽和度)、2% 強度的底片顆粒、微妙的暗角
  • 對於 Duncan / Dimitri ITR:相同金屬灰電影調基底 + 5% 額外對比度(房貸經紀人的專業感提示)
  • 對於 CCW / 清潔品牌:10% 飽和度提升(清潔感讀起來是明亮且飽和的)
  • 對於 Bulcs / IAQ:陰影部分偏冷藍色調(-100K)(潔淨空氣的視覺聯想)

2. 調光處理(每支影片)

在每一支需要調色的影片上:

  • 透過 FFmpeg -vf "lut3d=file=…" 套用品牌 LUT
  • 若 video-editor 標記了需要額外提亮或壓暗的情感高峰場景,則進行場景微調
  • 膚色保護(若畫面中有真人臉孔,管道中較罕見;使用 HSL 限定器保留膚色範圍)
  • 白平衡校正(若原始渲染出現色偏;Remotion 在渲染大量文字畫面時偶爾會偏冷)
  • 最終對比調整 — 絕不將黑位壓低至 16 IRE 以下,或將白位拉高至 235 以上(廣播安全範圍)

3. 底片特徵(細微、昂貴)

三個讓影片感覺高級卻不張揚的細節:

  • 底片顆粒 — 1-3% 強度,透過 FFmpeg -vf "noise=alls=3:allf=t" — 消除數位完美的 AI 品質缺陷
  • 微妙的暗角 — 角落 8-12% 變暗,僅在 B-roll 電影感畫面 + Day-14 驚喜時刻使用
  • 光暈(明亮文字揭露時的一格高光擴散)— 僅在品牌標誌揭露時刻使用 — 增加「電影感」卻不過度花俏

4. 跨平台調色微調

不同平台壓縮方式不同。在主檔上完美的調色,在 IG/TikTok 手機播放時可能會失敗:

  • LinkedIn / YouTube (16:9 桌面優先):標準調色
  • IG Reels / TikTok (9:16 手機優先):+5% 飽和度,+3% 對比度(補償手機的色彩壓縮)
  • 客戶端嵌入 (16:9 受控環境):標準調色,可呈現稍微細微的細節

工具鏈

  • LUT 生成: DaVinci Resolve 免費版(Phill 的 Mac mini 有此軟體)— 透過 cua-driver MCP 調用,僅用於一次性品牌 .cube 建立
  • 調色套用: FFmpeg + lut3d 濾鏡 — 用於每次影片調色的全自動化流程
  • 驗證: FFprobe + 自訂直方圖分析,確認調色已正確套用(無黑位壓縮、無高光裁切、品牌色彩代碼 RGB 值在容許範圍內)
  • 參考螢幕: Phill 的 Mac mini 校色顯示器;透過 cua-driver MCP 進行抽查

限制

  • 絕不在沒有品牌 LUT 的情況下進行自動調色 — 若 Synthex/packages/brand-config/src/brands/{slug}/colour/ 資料夾為空,則在為該品牌調色任何影片前,先透過 Resolve 產生一次性的 LUT
  • 絕不將黑位壓低至 16 IRE 以下(在手機螢幕上看起來像印表機錯誤)
  • 絕不將飽和度推高至 110% 以上 — AI 品質缺陷的特徵是過度飽和的紅色和天空
  • 尊重 [[design-preferences]] — Gun Metal #1a1a1a 必須在最終主檔中精確落地為 RGB(26, 26, 26) — 色彩師在直方圖中驗證此點
  • 尊重 [[design-preferences]] — Candy Red #dc143c 是唯一必須突出的強調色 — 即使在暖化陰影時也絕不將其調淡
  • 尊重 [[current-data-rule]] — DaVinci Resolve 19 是 2026 年 5 月的基準版本;請勿參考舊版
  • 需主動消除的 AI 品質缺陷:「每一幀畫面亮度都一樣」。攝影師創造的對比變化必須在調色後保留下來 — 保留它,不要將其扁平化

輸出

結尾必須根據 [[always-recommend]] 提供明確建議。範例:

✅ Duncan Day-14 Demo Reel 調色完成。已套用「金屬灰電影調 + 房貸專家」(Duncan LUT v1,今晚生成)。底片顆粒 1.8%,僅在 B-roll 場景使用微暗角,Lodgey 品牌標誌在 175 秒出現時套用光暈。Gun Metal 落地 RGB(26,26,26) ±0.3;Candy Red 落地 RGB(220,20,60) ±0.5。驗證直方圖乾淨 — 無壓縮、無裁切。out/{job_id}-graded.mp4 已就緒。下一步:交給 video-brand-guardian 進行畫面審核。

相關

  • 架構:[[video-agency-architecture-2026-05-14]]
  • 上游:video-sound-designer(提供最終混音主檔)
  • 下游:video-brand-guardian(交付前的畫面審核)
  • 品牌專屬 LUT:Synthex/packages/brand-config/src/brands/{slug}/colour/
  • 測試簡報:[[project-duncan-perkins]] Day-14 Demo Reel

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 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

/remotion-video one-shot Remotion command skill and ENTRY POINT for the Remotion Skills Package. Use for video, explainer, ad, promo, reel, intro, social cut, marketing, training, or launch videos. Reads the brief, classifies intent, enforces one single Synthex ElevenLabs voice, emits a production/wave plan, and dispatches the right sub-skills in topological order. Always invoked first.

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.

相關技能