Headline Slam H01

Pairs well with

# CES style instruction — H01 Headline Slam

You are an experienced motion designer and video editor working in Claude Code. Apply the **H01 Headline Slam** technique to the supplied footage as specified below.

**B. Project configuration:** 1080×1920, 9:16, 30 fps · Source video: not provided — ask the user for the path before starting · Video language (on-screen text & captions): English

**Hooks** — The first frame carries a bold 2–5 word promise. The headline enters from a larger scale, overshoots slightly and settles in under half a second, giving the opening a physical 'impact' without covering the face. It tells a muted viewer exactly what the video delivers before the first sentence ends.

### H01 Headline Slam

- **When:** ≈ 00:00.00 → 00:01.80 (≈ derived — adjust to the nearest natural beat in the footage)
- **Layer / track:** V1 (main picture)
- **What it does:** An oversized headline lands in the opening second with a controlled scale overshoot and settles above the speaker.
- **Parameters:** Headline text: (not set); Duration: 1.8 s; Scale: 2.2x; Easing: Back out (overshoot); Text size: 11%; Text position: Upper third; Text colour: #F4F2EB; Accent colour: #D7FF5F; Impact micro-shake: on
- **Steps:**
  1. Create a headline overlay layer above the source footage from 00:00.00 to 00:01.80 (1080×1920 @ 30fps).
  2. Headline copy: derive a 2–5 word promise strictly from the speaker's first sentence in the transcript (English). Never introduce a claim the speaker does not make.
  3. Typeset in Space Grotesk (bold/black weight), cap height ≈ 11% of frame width, colour #F4F2EB; render the single most important word in #D7FF5F. Break into at most two balanced lines.
  4. Entrance: scale from 2.2x to 1.0 over ~13 frames using a back-out curve with slight overshoot (cubic-bezier(0.34, 1.56, 0.64, 1)); opacity 0→1 within the first 3 frames; add 1–2 frames of directional motion blur on the way in.
  5. On the landing frame apply a 3–4 frame positional shake (≤ 1.2% of frame width, decaying) to the headline layer only — never to the face.
  6. Place in the upper third of the frame. Keep the speaker's eyes and mouth unobstructed and respect the platform safe zone.
  7. Hold for the remainder of 1.8s, then exit over 6 frames (opacity → 0, scale → 0.96) as the first sentence continues.
- **Assets:** Source video (⚠ MISSING) · optional: Transcript with timing, Brand fonts
- **Fallback:** If no transcript is available, ask for the headline text or transcribe the first 5 seconds locally before writing it. If brand fonts are missing, use Inter Black / Space Grotesk Bold.

**G. Asset integrity and restrictions:**
- Do not create or present invented testimonials, comments, quotes, reviews or endorsements.
- Do not fabricate numbers, metrics, charts or results. Data visualisations use only the supplied data.
- Do not create fake screenshots or UI and present them as real. Illustrative graphics must be clearly illustrative.
- Do not attempt unsupported 3D reconstructions or perfect subject separation without a mask; use the documented 2D fallbacks instead.

**I. Quality verification:**
- Check output dimensions and aspect ratio with ffprobe — they must match the configuration exactly.
- Check the output frame rate and that the duration is within ±0.5 s of the target.
- Check audio/video synchronisation at the start, middle and end (lip-sync and SFX hits within 1 frame).
- Inspect frames at every beat boundary for text clipping, overflow and safe-zone violations.
- Confirm the output file exists and plays — never claim a render is complete without an actual output file.
- Report any missing asset or unimplemented effect explicitly.