Agent Skills: video-scriptwriting
The craft of writing for the screen—from 6-second ads to 10-minute brand films. This skill bridges storytelling with the unique constraints and opportunities of video format: visual thinking, audio/visual interplay, pacing, and the relentless demand for attention in a scroll-past world. Video scripts aren't just written—they're engineered. Every second counts. Every word must earn its place. The first 3 seconds determine if anyone watches. The script must work as pure audio AND pure visual AND both together. This is writing that thinks in frames, scenes, and cuts. In the age of AI video generation, scriptwriting becomes even more critical. The script is the blueprint that AI follows. Garbage script in, garbage video out. Precise, visual, well-structured scripts enable AI to generate magic. Use when "script, video script, commercial script, ad script, TikTok script, YouTube script, explainer video, brand film, promo video, video ad, screenplay, storyboard, script, video, commercial, social-video, storytelling, visual, production" mentioned.
Install this agent skill to your local
Skill Files
The files that make up video-scriptwriting.
More agent skills
- spotify-playerTerminal Spotify playback/search via spogo (preferred) or spotify_player.
- create-atomic-context-providerBuild a `BaseDynamicContextProvider` that injects a named, titled block into an agent's system prompt at every `run()` — current time, user identity, retrieved RAG docs, session state, cached DB schema. Use when the user asks to "add a context provider", "inject X into the prompt", "give the agent dynamic context", "wire up RAG", "make a `BaseDynamicContextProvider`", or runs `/atomic-agents:create-atomic-context-provider`.
- analytics-trackingDesign, audit, and improve analytics tracking systems that produce reliable, decision-ready data.
- adr-checkCheck a code change against the repo's Accepted Architecture Decision Records (ADRs) in handbook/engineering/decisions/ and report violations with citations. Use before opening a PR, when reviewing a diff, or when the user asks to check ADR compliance, whether changes follow the architecture decisions, or to verify a change against the ADRs.
- rider-battleCreate and accept $RIDER wager battles in the Bankr CryptoRider game on Base, claim winnings or refunds, see open challenges, and view monthly & all-time leaderboards — all from a tweet. Use when a user wants to create a challenge with a wager, accept an open challenge (optionally the first one, or filtered by max/min wager), claim a won battle, or reclaim/refund a stake.
- ralph-loopRun, monitor, resume, merge, and debug Ralph loops. Use this skill whenever the user asks to operate `ralph run` or `ralph loops`, inspect loop state, recover suspended loops, analyze diagnostics, or unblock merge queue issues.