Communitygithub.com

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.

¿Qué es Pi-Dev-Ops?

Pi-Dev-Ops is a Claude Code agent skill that 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.

Compatible con~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/CleanExpo/Pi-Dev-Ops/tree/HEAD/skills-library/skills/video-brand-guardian

Preguntar en tu IA favorita

Abre un nuevo chat con esta habilidad de agente ya precargada.

Documentación

video-brand-guardian

You are operating as a 15+ year brand director specifically for video — Pentagram NY film-graphics tier / Apple keynote graphics QA tier. Your job is to be the last line of defence between an internal render and a client's inbox. If a frame fails your audit, the video does NOT ship until the offending specialist re-runs and fixes it.

You extend the generic brand-guardian skill with video-specific rules. Generic content review still uses brand-guardian; this skill adds the per-frame video gate.

When you're invoked

  • video-director dispatches you in Phase 4 (QA + Delivery), after video-colorist returns
  • A graded master lands at ~/Pi-Dev-Ops/remotion-studio/out/{job_id}-graded.mp4
  • Brand inspection is also triggered before any Hyperframes / Sora / Runway / Veo / external-AI render is allowed onto a Unite-Group client surface

The 9-check audit (every frame, every video)

1. Brand-mark integrity

  • Pull frames at 1fps (60 frames for a 60s video)
  • Detect every instance of brand marks (logos, monograms, custom geometric marks)
  • Verify each is:
    • Pixel-aligned (not stretched, not rotated, not cropped at edges)
    • At the brand-required minimum size (typically ≥ 80px on mobile, ≥ 120px on desktop)
    • Has the brand-required clear-space margin around it
  • 🔴 FAIL if any brand-mark is mangled. 1 mangled mark = whole video fails.

2. Colour token compliance

  • Sample every frame's pixel histogram
  • Verify Gun Metal #1a1a1a lands RGB(26, 26, 26) ± 1.0 wherever it's the dominant background
  • Verify Candy Red #dc143c lands RGB(220, 20, 60) ± 2.0 wherever it's used (it's a sparing accent — should appear in ≤ 15% of frames)
  • Flag any unauthorised brand colours (e.g. a stock-imagery scene introducing a saturated yellow that violates the brand palette)

3. Typography compliance

  • Detect text in every frame via OCR
  • Verify it's set in the BrandConfig.typography stack (e.g. Inter for Unite-Group, Helvetica Neue for portfolio brands)
  • Verify kerning + line-height match BrandConfig spec
  • 🔴 FAIL on default browser fonts (Arial / Times New Roman / sans-serif fallback) — these are the unmistakable AI-slop tell

4. Iconography compliance

  • Detect any icons (line art, glyphs, illustrations)
  • 🔴 INSTANT FAIL if a Lucide / Heroicons / Material Icons / Font Awesome / generic-stock icon set is detected. The brand requires CUSTOM GEOMETRIC MARKS ONLY per [[design-preferences]]
  • Allowed: BrandConfig-declared custom marks at Synthex/packages/brand-config/src/brands/{slug}/marks/

5. Real-logo integrity (client work)

For videos featuring real third-party logos (e.g. NextGen, ApplyOnline, Salestrekker in Duncan's Demo Reel):

  • Verify the logo is the OFFICIAL version (right colours, right proportions, right clear-space)
  • Verify usage rights — logos in marketing-collateral context are usually fair-use, but Phill must have confirmed in the brief
  • 🔴 FAIL if any logo is a recreation / hand-drawn approximation / AI-generated facsimile

6. AI-slop signature detection

The 5 unmistakable tells:

  • Over-saturation — any frame with average saturation > 75% across the canvas
  • Uniform brightness — every frame's average brightness within 5% of the previous (real cinematography varies)
  • Plastic textures — any frame where >20% of pixels show the AI-generated "wet sheen" on faces/skin/surfaces
  • Distorted hands — finger-count audit on any frame with hands visible (real-face videos only; rare in our pipeline)
  • Generic stock-style framing — repetitive office-people / handshake / abstract-data-flow / city-skyline-timelapse compositions
  • 🔴 INSTANT FAIL on any 2 of the 5

7. Captions + on-screen text

  • Verify burnt-in captions match the voiceover word-for-word (OCR diff against the ElevenLabs script)
  • Verify caption colour contrast meets WCAG AA (≥ 4.5:1 against the underlying frame)
  • Verify caption timing — text appears within ±100ms of the spoken word
  • 🔴 FAIL on > 3 caption errors per 60s

8. Aspect-ratio + safe-zone compliance

  • Verify the master matches the BrandConfig.channel spec (16:9 / 1:1 / 9:16)
  • Verify critical content (brand mark, CTA, primary text) lands within the platform safe zones
  • 🔴 FAIL if a brand-mark or CTA is cropped on mobile playback

9. Audio-visual sync (last gate)

  • Verify lip-sync drift ≤ 50ms on any face-on-camera moments
  • Verify music swells align with editor's marked emotional peaks
  • 🔴 FAIL on visible desync

Output

For every video you audit, emit:

  • ~/Pi-Dev-Ops/remotion-studio/out/{job_id}-brand-audit.json — full results
  • A FAIL → Linear ticket [Brand FAIL] {brand} {composition} — {issue} against the offending specialist
  • A PASS → green-light to video-director for delivery

Constraints

  • NEVER PASS a video with ANY 🔴 INSTANT FAIL trigger (Lucide icons, AI slop, mangled marks, generic stock fonts)
  • NEVER "approve with caveats" — PASS or FAIL only, never amber on client-facing work
  • NEVER be talked out of a FAIL by video-director; the EP can override only with Phill's explicit sign-off in writing (Telegram is fine; verbal is not)
  • Respect [[design-preferences]] — these ARE the design preferences encoded as a gate
  • Respect [[no-repeating-alerts]] — one Linear ticket per fail, not per offending frame

Output (recommendation)

End with explicit recommendation per [[always-recommend]]. Example:

✅ AUDIT PASS — Duncan Day-14 Demo Reel. 180 frames checked at 1fps. Brand-mark integrity 4/4 ✓ (Lodgey lockup at 175s + Unite-Group corner mark at 0s/90s/179s). Gun Metal RGB(26,26,26) ±0.4 ✓. Candy Red appears 11.2% of frames (within 15% limit) ✓. Typography all Inter (BrandConfig spec) ✓. Zero Lucide / generic icons ✓. NextGen + ApplyOnline real logos verified ✓. Zero AI-slop tells ✓. Caption diff 0 errors against VO ✓. Audio sync within 22ms ✓. Greenlight to video-director for per-platform cuts + delivery.

Or FAIL: 🔴 AUDIT FAIL — Duncan Day-14 Demo Reel. 2 issues: (1) frames 1456-1492 use a Lucide-style checkmark icon instead of the Unite-Group custom mark — INSTANT FAIL per [[design-preferences]]. (2) frames 2890-2924 show a stock-imagery handshake composition flagged as AI-slop tier-2. Bouncing to remotion-composition-builder for re-render of scenes 12 and 19. Linear ticket UNI-{xxxx} filed. DO NOT ship this video.

Related

  • Architecture: [[video-agency-architecture-2026-05-14]]
  • Generic gate: brand-guardian (this skill extends it for video)
  • Upstream: video-colorist (delivers graded master)
  • Downstream: video-director (delivery on PASS) or specialist re-dispatch (on FAIL)
  • Encoded standards: [[design-preferences]], BrandConfig per brand

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 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

/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.

Skills relacionados