What is video-production-pipeline?

A plan for producing a short video from an initial brief through script, storyboard, shot list, rendering, and review. A storyboard is a scene-by-scene visual plan, while rendering turns the plan into a video file.

Use it for launch videos, feature announcements, explainers, social clips, and turning an existing script or article into planned shots.

Starting with tools before agreeing on the audience, message, and length often produces an unfocused video. This workflow helps settle the story and production choices before implementation.

video-production-pipeline — Skill for Claude Code by latestaiagents

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add latestaiagents/agent-skills --skill video-production-pipeline

Clone the repo

git clone --depth 1 https://github.com/latestaiagents/agent-skills

Made for: Claude Code.

Or install video-motion, the plugin that ships this one along with the rest of its 5 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/latestaiagents/agent-skills/video-production-pipeline/github.svg)](https://agentmods.dev/skills/latestaiagents/agent-skills/video-production-pipeline)

Your own site

<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/video-production-pipeline"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/video-production-pipeline/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/video-production-pipeline"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/video-production-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 151 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,230 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00151	$0.02230
Opus 5.5	$0.00060	$0.00892
Sonnet 5.5	$0.00030	$0.00446
Haiku 4.5	$0.00015	$0.00223

Measured 9d ago against content hash 4f68d5f54bb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

video-production-pipeline scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/video-motion/video-production-pipeline/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Video Production Pipeline

Plan the video before writing a single frame: brief → script → storyboard → renderer choice → render → review.

Most failed agent-made videos fail upstream: no clear audience, a script that is too long for the runtime, or a renderer chosen before anyone knew what the video needed. This skill is the production plan. Framework-specific code belongs to the official framework skills (see Step 4).

When to Use

A user asks for "a video" and the goal, length, or platform is unclear
Planning a launch video, feature announcement, explainer, or social clip
Deciding between Remotion, HyperFrames, or plain FFmpeg
Turning an existing script, blog post, or demo into a shot list
Reviewing a rendered video before it ships

When NOT to Use

Writing Remotion components or HyperFrames compositions: use the official skills (Step 4)
Editing existing footage only (trim, normalize, captions): use ffmpeg-post-production
Screen-recorded product walkthroughs: start with product-demo-video

Workflow

Step 1: Write a One-Page Brief

Do not start until these are answered. Ask the user for anything missing.

Field	Example
Goal	"Get existing users to try the new export feature"
Audience	"Current customers, technical, watching in-app"
Platform(s)	YouTube (16:9), Shorts/Reels (9:16)
Target length	30 s
Single message	"Exports now run in the background"
Call to action	"Open Settings → Export"
Assets available	Logo SVG, brand colours, screen recording, VO? music?
Sound-off viewing?	Assume yes for social: on-screen text and captions carry the message
Deadline / review owner	Who approves the cut

One video, one message. If the brief lists three messages, propose three videos.

Step 2: Script to the Clock

Write the script as a two-column table: what is heard, what is seen. Time it.

| # | Time | Audio (VO / music / SFX)              | Visual                                  |
|---|------|---------------------------------------|-----------------------------------------|
| 1 | 0–3s | Music in. VO: "Exports used to block…" | Product UI, spinner, title card fades in |
| 2 | 3–9s | VO: "Now they run in the background."  | Click Export → toast appears            |
| 3 | 9–…  | …                                     | …                                       |

Read the full file on GitHub · 156 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 156 lines · 151 tokens per session scan A 4f68d5f54bb4

Subscribe to this mod's changes

video-production-pipeline is a skill published in the GitHub repository latestaiagents/agent-skills (6 stars, last pushed 9d ago), licensed MIT. It adds 151 tokens to every session and 2,230 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-04.

Creative and media Planning agentic-ai agentic-rag agentic-workflow agentshub agentskills ai

video-production-pipeline next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
video-production-pipelinelatestaiagents/agent-skills	Skill	6	9d ago	MIT	A	151	Claude Code
nexent-daily-testModelEngine-Group/nexent	Skill	6.2k	today	MIT	A	78	Claude Code, Codex
ai-humanizer-zhskillsaiagent/aiskills	Skill	5	5mo ago	none	A	81	Codex
ai-paywall-croskillsaiagent/aiskills	Skill	5	5mo ago	none	A	73	Codex
ai-account-research-sales-cardskillsaiagent/aiskills	Skill	5	5mo ago	none	A	71	Codex
ai-account-researchskillsaiagent/aiskills	Skill	5	5mo ago	none	A	65	Codex
ai-amazon-brand-analyticsskillsaiagent/aiskills	Skill	5	5mo ago	none	A	72	Codex