One narrative, three deliverables: deck, narrated video, social cutdowns

STAFF LISA / FRAMES · V0.1.1

gemskills:deck-creatorgemskills:generate-videocreative:voice-clone

REQUIRES

claude plugin install gemskills@b-open-io
claude plugin install creative@b-open-io

WHEN TO REACH FOR THIS

Use this when a launch or fundraising story needs a presentation, a narrated video, and short vertical clips. The chain creates the deck first, uses its slides and copy for the video, then cuts the video into social clips.

REQUIRES

Claude Code: claude plugin install gemskills@b-open-io (skills: gemskills:deck-creator, gemskills:generate-video; roster: Lisa (gemskills:content))
Claude Code: claude plugin install creative@b-open-io (skills: creative:voice-clone; roster: Frames (creative:audio-specialist))
GEMINI_API_KEY - slide images and Veo video generation
ELEVENLABS_API_KEY - narration voice (voice-clone / TTS); IVC voice cloning needs a Starter-tier ElevenLabs account or above
ffmpeg (brew install ffmpeg) - audio prep and clip cutting; REPLICATE_API_TOKEN if you use Replicate-Veo features (reference frames, 9:16 at higher res)

CONTEXT INPUTS

{{STORY}}          The narrative in 3-5 sentences: what it is, who it is for, the ask.
{{AUDIENCE}}       Who watches/reads, e.g. "seed investors" or "developer users".
{{DECK_DIR}}       Working directory for the deck and its assets, e.g. ./launch-deck.
{{ART_STYLE}}      Optional style id from the library (e.g. pixl, deco) applied to every slide for consistency. Omit for a clean business theme.
{{VOICE}}          Narration voice: path/URL to reference audio to clone, or "default" for a stock TTS voice.
{{CLIP_TARGETS}}   Which social cutdowns you need, e.g. "3x 9:16 clips, 8s each, hook + one point + CTA".

THE PROMPT

PASTE INTO YOUR AGENT

EXPECTED OUTPUT

In {{DECK_DIR}}: deck.pdf and DECK-INDEX.md, one narrated master .mp4, and the set of vertical social clips named per {{CLIP_TARGETS}} - all telling the same story, produced from one brief.

FOLLOW-UP CHAIN

db-explainer-video - spin a dedicated feature-explainer off the same voice and style.
db-campaign-landing-chain - build the landing page these assets point to.
db-social-asset-batch - generate the still social posts that surround the video clips in the campaign.
db-custom-art-style - capture the deck's look as a reusable style so the next campaign matches this one.

← PACK CONTENTS

Run a three-link chain. Each link names who owns it, what it consumes, and what "done" means before the next link starts. Do not collapse the links - the whole point is that the deck is the single source the video and clips derive from. LINK 1 - Lisa (Visual Content Specialist) builds the deck. Load `gemskills:deck-creator` and follow its phased workflow in {{DECK_DIR}}. Discovery is already answered: topic/story = {{STORY}}, audience = {{AUDIENCE}}, ~10-12 slides, output mode html+pdf. Write THEME.md and DECK-PLAN.md, then apply {{ART_STYLE}} (pass --style to every slide generation so all slides match). Plan the copy with one message per slide and a problem -> solution -> proof -> ask arc. Generate slides, stitch the PDF, and write DECK-INDEX.md. DONE when: DECK-INDEX.md lists every slide, deck.pdf renders, and DECK-PLAN.md holds the per-slide headline + narration line. HANDOFF to Frames: the ordered slide PNGs plus the per-slide narration lines from DECK-PLAN.md. LINK 2 - Frames (Audio Producer) turns the deck into a narrated video. First, the voice. If {{VOICE}} is a reference clip, load `creative:voice-clone` and run its pipeline (source -> prepare -> clone) to get a voice_id; surface it. If {{VOICE}} is "default", skip cloning and use a known stock ElevenLabs voice_id from the account. Then generate the narration for each slide's line with voice-clone's test subcommand pointed at that voice_id (voice-clone.ts test --voice-id <id> --text "<line>" --output-dir <dir>), which is the skill's text-to-speech path; collect one audio file per slide. Then animate. Load `gemskills:generate-video` and, per slide, produce a short motion clip using the slide PNG as the starting frame (--input) at 16:9 so the aspect matches; keep motion subtle (slow push/parallax), let the narration drive timing. Run generation as a background task (Veo takes up to several minutes) and read only the output path. Assemble slides + narration into one video with ffmpeg. DONE when: a single narrated .mp4 plays start to finish and matches the deck order. HANDOFF to Lisa: the master .mp4 and the DECK-PLAN.md arc. LINK 3 - Lisa cuts social clips. From the master video and {{CLIP_TARGETS}}, cut vertical (9:16) clips with ffmpeg, each a self-contained hook + one point + CTA drawn from the deck arc - do not invent new claims, only reuse what the deck already says. Where a 9:16 reframe crops badly, regenerate that segment at --aspect 9:16 rather than letterboxing. DONE when: every clip in {{CLIP_TARGETS}} exists, is under the platform length, and reads on mute-then-unmute. Negative prompts: never read generated .mp4 or slide images back into context - report file paths and have me play them with `open <file>`. Do not re-brief the story between links; the deck copy is the script. Do not letterbox 16:9 into 9:16; reframe or regenerate. Do not fabricate metrics or quotes for the clips.