Content And Asset Pipeline logo

Content And Asset Pipeline

Community
Sahil-SS9
content-and-asset-pipeline

Create new mod content and assets that match the game, using the end user's chosen local or paid tools.

Overview

PublisherSahil-SS9
Repositoryagent-personas
Skill namecontent-and-asset-pipeline
Stars
67
Forks
4
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

    Published by Sahil-SS9 on GitHub. Read the source before you install it.

Installation

Install the Content And Asset Pipeline 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/Sahil-SS9/agent-personas/tree/main/skills/content-and-asset-pipeline
  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/Sahil-SS9/agent-personas.git /tmp/agent-personas
mkdir -p .claude/skills
cp -r /tmp/agent-personas/skills/content-and-asset-pipeline .claude/skills/content-and-asset-pipeline
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Content And Asset Pipeline 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 Content And Asset Pipeline 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 Content And Asset Pipeline 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.

Content and asset pipeline

New items, weapons, enemies, units, levels, sound and music: make them fit the game, and make them the user's way.

1. Respect the user's asset preference (ask once, record it)

Ask before generating anything and record the answer in MODLOG.md:

  • Local only: e.g. ComfyUI or other local image/3D/audio models, Blender, hand-made art. No network spend.
  • Paid services allowed: e.g. hosted image, 3D, sound or video generation. Ask for the provider, the key's location (environment variable or keyring, never in the repo) and a spending limit, and whether each job needs approval.
  • Both: local first, paid only for what local cannot do, under the same limits. Never spend money or upload the user's files to a service without that recorded consent. If no preference is set, use placeholders and ask.

2. Study the game's own assets first

Measure before generating: resolution, pixel scale, palette, outline style, camera angle, facing directions, frame layout, polygon budget, texture format and naming. Content that ignores these looks wrong however good the art is.

3. Content design before art

Define the content in the game's terms: stats, tier, recipes, drop tables, AI behaviour, sounds and balance relative to existing content. Clone and modify an existing entity where the engine allows; it inherits animations and behaviour that are hard to author.

4. Generate or author

  • Consistency across many angles or frames: make one concept, turn it into a 3D model, then render every required angle from the game's camera.
  • Pixel art: generate on a flat or transparent background, cut out, then scale once with nearest-neighbour to the exact frame size.
  • Sound: match sample rate, loudness and length to the game's existing effects.
  • Record every generated asset (tool or model, prompt, seed, date, licence terms) in a manifest beside the mod.

5. Convert to what the engine loads

Examples: PNG into tModLoader; AssetBundles for Unity built with the same Unity major version; cooked .uasset in a matching Unreal editor; NIF/DDS for Bethesda; 16x16 PNG and JSON models for Minecraft. Check format, size and naming with a load test.

6. Other games' assets

Never copy assets from another game into a mod. For cross-game content, either recreate a look-alike, or ship a converter that runs on the user's own install and writes a private local pack. The mod must still work with placeholders when that pack is missing.

7. Proof

The asset appears in game at the right scale, facing, pivot and layer in a scripted scene screenshot that was actually inspected, plus a manifest entry for every generated file and a licence check for commercial use.

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 Content And Asset Pipeline AI skill do?

Create new mod content and assets that match the game, using the end user's chosen local or paid tools.

Why use Content And Asset Pipeline on TypingMind?

Because you install it once and use it with any model. Content And Asset Pipeline 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 Content And Asset Pipeline in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Sahil-SS9/agent-personas/tree/main/skills/content-and-asset-pipeline. 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 Content And Asset Pipeline?

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 Content And Asset Pipeline?

As many as you like. As long as a model supports skills, you can use Content And Asset Pipeline with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Content And Asset Pipeline AI skill free?

Yes. It is published on GitHub by Sahil-SS9 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 👇