Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
pexoai avatar

Videoagent Director

  • 453 installs
  • 762 repo stars
  • Updated July 21, 2026
  • pexoai/pexo-skills

videoagent-director is an agent skill that turns a natural-language video brief into a shot storyboard and generates images, video clips, and audio via director.js for developers building automated video production workf

About

videoagent-director (version 1.1.0) in pexoai/pexo-skills acts as an AI creative director that converts a user's idea into a complete storyboard and produces all assets without surfacing prompt engineering details. The workflow infers concept, aspect ratio (9:16, 16:9, or 1:1), tone, and target length (15–60 seconds), shows a compact shot table for one-word approval, then calls director.js once per shot with internal image, video, and audio prompts. Shot counts scale from 3–4 shots for 15–20 seconds up to 7–9 shots for 45–60 seconds, with patterns for brand ads, social reels, and short-film teasers. Audio rules assign music to opening and closing shots, SFX to action beats, and TTS only when narration is requested. Developers reach for videoagent-director when building agent-driven brand videos, social reels, or product ads from a single natural-language brief. No API keys are required because the skill orchestrates existing hosted proxies.

  • Shot and scene sequencing orchestration
  • Prompt and creative brief structuring
  • Multi-agent video pipeline coordination
  • Consistency across generated scenes
  • Constraint-driven generative direction

Videoagent Director by the numbers

  • 453 all-time installs (skills.sh)
  • +11 installs in the week ending Aug 4, 2026 (Skillselion tracking)
  • Ranked #419 of 1,335 Generative Media skills by installs in the Skillselion catalog
  • Data as of Aug 4, 2026 (Skillselion catalog sync)
npx skills add https://github.com/pexoai/pexo-skills --skill videoagent-director

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs453
repo stars762
Last updatedJuly 21, 2026
Repositorypexoai/pexo-skills

How do agents produce multi-shot videos from a brief?

Direct multi-step video generation agents through shot planning, scene sequencing, prompts, and creative constraints to produce coherent automated video outputs.

Who is it for?

Developers building agent workflows that generate brand videos, social reels, or short films from natural-language creative briefs.

Skip if: Manual video editors who want frame-by-frame control or teams that need a specific proprietary render farm without agent orchestration.

When should I use this skill?

User wants to make a video, storyboard, scene breakdown, or short clip from a natural-language idea including brand videos and social reels.

What you get

Shot storyboard table, per-shot image and video URLs, audio assets, and a production report with scene breakdown.

  • Shot storyboard table
  • Per-shot media URLs
  • Production report

By the numbers

  • Skill version 1.1.0 with director.js CLI per shot
  • Shot tables scale from 3–4 shots (15–20s) to 7–9 shots (45–60s)

Files

SKILL.mdMarkdownGitHub ↗

🎬 VideoAgent Director

Use when: The user wants to produce a video from a natural-language idea — a brand video, short film, social reel, product ad, or any creative concept. Also use for "make a storyboard", "create a scene breakdown", or "produce a short clip about X".

You are the creative director. The user describes what they want. You handle everything — shot planning, prompt writing, asset generation — without asking the user to write any prompts.

---

Your Responsibilities

The user gives you an idea. You do the rest.

  • Break the idea into the right number of shots
  • Write all image, video, and audio prompts internally (never ask the user to write them)
  • Execute each shot via director.js
  • Return a clean, visual production report

Never surface prompt details, model names, or technical parameters to the user unless explicitly asked.

---

Workflow

Step 1 — Understand the brief (one pass)

From the user's message, infer:

  • Concept — What is the video about?
  • Format — Vertical (9:16) for social/mobile, landscape (16:9) for film/desktop, square (1:1) for feed. Default to 16:9 if unclear.
  • Tone — Cinematic, energetic, calm, playful, corporate, dramatic
  • Length — Short (15–20 s), standard (30 s), long (45–60 s). Default to 30 s.

If any of these is truly ambiguous, ask one clarifying question only. Otherwise, proceed.

Step 2 — Show a one-line storyboard for quick confirmation

Plan all shots internally, then show the user only a compact table — no prompts, no technical details:

🎬 **[Title]** · [N] shots · [format] · ~[duration]s

| # | Scene | Audio |
|---|-------|-------|
| 1 | Rainy street, wide establishing | music |
| 2 | Neon sign reflection in puddle | rain SFX |
| 3 | Person with umbrella, tracking | city ambience |
| 4 | Fade to black on neon glow | music |

Looks good? I'll start generating.

Wait for a single word of approval (e.g. "yes", "go", "ok", "好的", or any positive reply) before proceeding.

Step 3 — Execute shot by shot

Call director.js once per shot after user confirms.

node {baseDir}/tools/director.js \
  --shot-id <n> \
  --image-prompt "<your internally crafted image prompt>" \
  --video-prompt "<your internally crafted motion prompt>" \
  --audio-type <music|sfx|tts> \
  --audio-prompt "<your internally crafted audio prompt>" \
  --duration <seconds> \
  --aspect-ratio <ratio> \
  --style "<global style string you chose>"

For text-to-video shots (no reference frame needed):

node {baseDir}/tools/director.js \
  --shot-id <n> \
  --skip-image \
  --video-prompt "<full scene description + motion>" \
  --duration <seconds> \
  --aspect-ratio <ratio>

For shots where the user provided an image:

node {baseDir}/tools/director.js \
  --shot-id <n> \
  --image-url "<url from user>" \
  --video-prompt "<motion description>" \
  --audio-type <type> \
  --audio-prompt "<sound>" \
  --duration <seconds>

Step 4 — Present the results

After all shots are complete, show only the production output — no prompts, no model names:

## 🎬 [Title]

**[Shot count] shots · [format] · [total duration]**

---

**Shot 1 — [Scene Name]**
🖼 [image_url]
🎬 [video_url]
🔊 [audio description or "no audio"]

**Shot 2 — [Scene Name]**
...

---
Ready to adjust any shot or generate more?

---

Shot Planning Reference (internal use only)

Shots by format

LengthShots
15–20 s3–4 shots
30 s5–6 shots
45–60 s7–9 shots

Shot sequence patterns

Brand / product (30 s): Establishing → Product detail close-up → Action/usage → Sensory moment → Lifestyle → Brand outro

Social reel (15 s): Hook (bold visual) → Core message → Payoff/result → CTA

Short film teaser (45 s): World → Character → Inciting moment → Action/tension → Emotional peak → Cliffhanger

Audio rule

  • Assign music to the opening shot and closing shot
  • Assign SFX to action shots (pouring, movement, impact)
  • Use TTS only if user explicitly asks for narration or voiceover
  • Omit audio for transitional shots when in doubt

Style consistency

Pick ONE style lock before executing and use it in --style for every shot. Example: cinematic, warm amber tones, shallow depth of field.

---

Example

User: "Make a short video about a rainy Tokyo street at night."

You internally plan:

  • 4 shots · 16:9 · ~20 s
  • Style: cinematic, neon-wet streets, shallow depth of field, rain
  • Shot 1: wide establishing (music), Shot 2: close-up puddle reflection (SFX rain), Shot 3: person with umbrella tracking (SFX city ambience), Shot 4: neon sign fade-out (music outro)

Then execute all 4 shots silently and show only the results.

Related skills

How it compares

Pick videoagent-director for end-to-end multi-shot agent video pipelines; pick single-model image skills when only one still frame is needed.

FAQ

What does videoagent-director produce?

videoagent-director plans shots from a natural-language brief, runs director.js for each scene, and returns image URLs, video clip URLs, and audio assets in a production report without exposing internal prompts.

How many shots does videoagent-director plan?

videoagent-director targets 3–4 shots for 15–20 second videos, 5–6 for 30 seconds, and 7–9 for 45–60 seconds, with brand, social reel, and short-film sequence patterns.

Generative Mediaagentsautomation

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.