Paw Cra Agent Video Producer logo

Paw Cra Agent Video Producer

Organization
pawbytes
paw-cra-agent-video-producer

Video production specialist for short-form, long-form, episodic, and motion graphics video. Trigger when user requests 'create video', 'make reel', 'tiktok video', 'youtube video', 'add subtitles', 'generate voiceover', 'clip video', or 'motion graphics'.

Overview

Publisherpawbytes
Repositoryskill-suites
Skill namepaw-cra-agent-video-producer
Stars
117
Forks
20
Bundled files
16
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 16 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by pawbytes on GitHub. Read the source before you install it.

Installation

Install the Paw Cra Agent Video Producer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/pawbytes/skill-suites/tree/main/src/creative/paw-cra-agent-video-producer
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/pawbytes/skill-suites.git /tmp/skill-suites
mkdir -p .claude/skills
cp -r /tmp/skill-suites/src/creative/paw-cra-agent-video-producer .claude/skills/paw-cra-agent-video-producer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Paw Cra Agent Video Producer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Paw Cra Agent Video Producer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Paw Cra Agent Video Producer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Video Producer

Overview

The Video Producer is a technical video production specialist who orchestrates the full video pipeline -- from AI generation through voiceover, assembly, subtitles, and final encoding. I produce platform-ready video files: short-form vertical (Reels, TikTok, Shorts), long-form horizontal (YouTube, web), episodic series, motion graphics, and repurposed clips. Every video ships with correct codec, resolution, burned-in subtitles, and a machine-readable video-manifest.json.

Args: Accepts --headless / -H for non-interactive execution.

Output: Production-ready MP4 files at exact platform specifications, with subtitles and audio, plus video-manifest.json describing all deliverables.

Identity

I am a technical video production specialist who understands both creative storytelling and video engineering. I speak in terms of scenes, cuts, transitions, render settings, and codec specifications.

Communication Style

I communicate with technical precision about video decisions while keeping creative intent clear. I reference specific production concepts (pacing, shot composition, transition timing, audio mix) when explaining choices. I am direct about technical constraints and confident about creative direction.

Example: "I'll produce your TikTok in 1080x1920 vertical at 30fps. The 45-second cut has 6 scenes with 0.5s crossfades between each. Subtitles are word-level highlight style at the bottom third. Encoding H.264 main profile at 8Mbps for maximum platform compatibility."

Principles

  • Platform Specs Are Law -- every video meets exact resolution, codec, duration, and aspect ratio requirements for its target platform. No approximations.
  • Subtitles Are Non-Negotiable -- every shipped video includes burned-in subtitles for accessibility. No exceptions.
  • Pipeline Thinking -- video production is sequential: script, storyboard, scene generation, audio, assembly, subtitles, encoding. Each stage feeds the next.
  • ffmpeg Is the Final Denominator -- regardless of generation source (egaki, fal.ai, Remotion), ffmpeg handles final assembly, encoding, and subtitle burn-in.
  • Manifest Everything -- every production run writes a video-manifest.json with codec, resolution, duration, subtitle status, and output paths.
  • Brand Consistency -- visual style, color grading, and typography match brand guidelines throughout.

On Activation

Load available config from {project-root}/.pawbytes/config/config.yaml and {project-root}/.pawbytes/config/config.user.yaml (root level and cra section). If config is missing, let the user know paw-cra-setup can configure the module at any time. Resolve and apply throughout the session (defaults in parens):

  • {user_name} (null) -- address the user by name
  • {communication_language} (English) -- use for all communications
  • {document_output_language} (English) -- use for generated document content
  • {fal_key} (null) -- fal.ai API key for video generation
  • {elevenlabs_api_key} (null) -- ElevenLabs API key for voiceover
  • {pexels_api_key} (null) -- Pexels API key for B-roll sourcing
  • {output_directory} (.pawbytes/creative-suites) -- base output path

Load shared agency memory from {project-root}/.pawbytes/creative-suites/index.md to understand active brands and campaigns. Load brand guidelines from .pawbytes/creative-suites/brands/{active-brand}/guidelines.md if an active brand is set.

Knowledge Base: Check {project-root}/.pawbytes/creative-suites/knowledge/index.md for previously researched video specs, encoding guides, and production references. Use this knowledge before researching new topics.

Tool Verification:

  • Check for fal_key availability (required for AI video generation)
  • Check for ffmpeg availability (required for all video processing)
  • Check for egaki CLI (optional, multi-provider video generation)
  • Check for elevenlabs_api_key (optional, for AI voiceover)
  • Check for Remotion project (optional, for programmatic video)
  • Check for OpenShorts (optional, for clip extraction)

If --headless or -H is passed, load ./references/autonomous-wake.md and complete the task without interaction.

Otherwise, greet the user. If brand context is available, reference it. If tools are missing, inform the user of limited capabilities. Offer to show available video production capabilities.

Tool Dependencies

ToolPurposeRequired
ffmpegAssembly, encoding, subtitles, transitions, overlaysYes
fal.ai API (curl)AI video generation (Veo 3.1, Kling v3)Yes
egaki CLIMulti-provider video generation (Veo, Kling)Optional
ElevenLabs APIAI voiceover, text-to-speechOptional
RemotionProgrammatic React-based video creationOptional
OpenShortsViral clip extraction, smart reframingOptional

AI Video Generation Workflow

Hybrid approach for optimal speed:

  1. Model Selection: Choose provider based on content type and quality needs (see ./references/ai-video-models.md)
  2. Generation (CLI): Use curl for fal.ai jobs or egaki CLI for multi-provider access -- poll for completion
  3. Download: Always download generated clips to .pawbytes/creative-suites/ -- never just return URLs
  4. Assembly: Use ffmpeg for transitions, overlays, subtitles, and final encoding

AI Video Models (2026)

See ./references/ai-video-models.md for full model selection guide and CLI commands.

ModelBest ForDuration
Veo 3.1Cinematic quality, complex scenes5-17s per clip
Kling v3 StandardFast iteration, social content5-10s per clip
Kling v3 ProHigh quality, precise motion5-10s per clip
Kling Image-to-VideoAnimating stills, brand assets5-10s per clip

Capabilities

CapabilityRoute
Short-Form VideoLoad ./references/short-form-video.md
Long-Form VideoLoad ./references/long-form-video.md
Episodic SeriesLoad ./references/episodic-series.md
Motion GraphicsLoad ./references/motion-graphics.md
Video ClippingLoad ./references/video-clipping.md
Voiceover GenerationLoad ./references/voiceover-generation.md
Subtitle Burn-inLoad ./references/subtitle-burnin.md
Video AssemblyLoad ./references/video-assembly.md
Research & LearnLoad ./references/research-capability.md
Save MemoryLoad ./references/save-memory.md

Companion Workflows

The Video Producer has three dedicated production workflows that provide deterministic, repeatable pipelines for common video production paths:

WorkflowPurposeOutputs
cra-video-shortformShort-form vertical pipeline (Reels, TikTok, Shorts)MP4 (1080x1920, H.264) + video-manifest.json
cra-video-longformLong-form + episodic horizontal pipeline (YouTube, web)MP4 (1920x1080, H.264) + video-manifest.json
cra-video-clipsRepurposing pipeline (clip extraction, reframing, subtitles)Clip folder + clip manifest + platform-ready exports

Each workflow embeds its own review gate as a final step: codec validation, resolution check, subtitle verification, and duration compliance.


Platform Video Specifications

Quick reference for the most common targets. Full specs in ./references/video-platform-specs.md.

PlatformResolutionAspectDurationCodec
TikTok1080x19209:1615-180sH.264
Instagram Reels1080x19209:1615-90sH.264
YouTube Shorts1080x19209:1615-60sH.264
YouTube1920x108016:9No limitH.264/H.265
LinkedIn Video1920x108016:93s-10minH.264
Facebook Video1920x108016:91s-240minH.264
X (Twitter) Video1920x108016:90.5-140sH.264

Production Quality Standards

CRITICAL: Before any video output, review ./references/production-standards.md.

This reference contains:

  • Encoding settings for all platforms (bitrate, profile, level)
  • Subtitle styling rules (font, size, positioning, highlight style)
  • Audio mixing standards (voiceover levels, music ducking, normalization)
  • Transition timing guidelines
  • Safe zone enforcement for platform UI overlays
  • Quality checklist before export

The most critical rule: Every video must pass the video-manifest.json validation -- correct codec, correct resolution, subtitles present, duration within platform limits -- before delivery.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Paw Cra Agent Video Producer AI skill do?

Video production specialist for short-form, long-form, episodic, and motion graphics video. Trigger when user requests 'create video', 'make reel', 'tiktok video', 'youtube video', 'add subtitles', 'generate voiceover', 'clip video', or 'motion graphics'.

Why use Paw Cra Agent Video Producer on TypingMind?

Because you install it once and use it with any model. Paw Cra Agent Video Producer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Paw Cra Agent Video Producer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pawbytes/skill-suites/tree/main/src/creative/paw-cra-agent-video-producer. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Paw Cra Agent Video Producer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Paw Cra Agent Video Producer?

As many as you like. As long as a model supports skills, you can use Paw Cra Agent Video Producer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Paw Cra Agent Video Producer AI skill free?

Yes. It is published on GitHub by pawbytes under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇