Asset Passport logo

Asset Passport

Community
machina-exm
asset-passport

Create film-asset passports before generation. Use for characters, locations, props, and state variants that need repeatable visual identity.

Overview

Publishermachina-exm
Repositoryfilm-studio-skills
Skill nameasset-passport
Stars
156
Forks
25
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by machina-exm on GitHub. Read the source before you install it.

Installation

Install the Asset Passport 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/machina-exm/film-studio-skills/tree/main/skills/asset-passport
  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/machina-exm/film-studio-skills.git /tmp/film-studio-skills
mkdir -p .claude/skills
cp -r /tmp/film-studio-skills/skills/asset-passport .claude/skills/asset-passport
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Asset Passport 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 Asset Passport 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 Asset Passport 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.

Asset Passport

Create one authoritative visual passport for one film asset at a time. Treat the passport as the asset's memory: its descriptor and approved references will be copied unchanged into later prompts.

Start

  1. Read the ## AI film studio section in the project's CLAUDE.md or AGENTS.md.
  2. Use the configured image model only as the destination for reference-sheet prompts; do not assume a particular model.
  3. If the section is missing, tell the user to run setup first.
  4. Continue if the user wants to proceed by asking which image model they use and how they submit prompts.
  5. Check for /assets/characters/, /assets/locations/, /assets/props/, /docs/registry.md, and /docs/breakdown.md in the studio root.
  6. If a required folder is missing, offer to create only the needed folder in the studio tree.
  7. Ask which single character, location, prop, or state variant to passport.

Ask one question at a time throughout.

Establish identity

Confirm the asset's:

  • tag, beginning with @;
  • type: character, location, or prop;
  • version;
  • scenes in which it appears;
  • seed or reference files already chosen.

Read /docs/breakdown.md when available and reconcile its scene IDs and asset tags with the user's answers. Do not silently merge two tags or change an existing tag.

Treat every state variant as a separate asset with its own passport and registry row. For example, keep @cal, @cal_wet, and @cal_blood separate. Ask what visibly changes in the variant and what must remain identical to the base asset.

Write the descriptor

Interview the user until the visual identity is exhaustive and unambiguous. Ask about one missing dimension at a time. Cover stable visual facts that another prompt writer must reproduce without guessing. Separate permanent identity from scene-specific action, framing, or camera choices.

For a character, resolve face, hair, age cues, build, skin, wardrobe, footwear, carried items, wear, and distinctive details. For a prop, resolve form, scale, material, colour, finish, wear, markings, moving parts, and distinctive details. For a location, resolve layout, surfaces, architecture, fixed objects, scale, weathering, and spatial landmarks.

For a location, also include the scene's:

  • dominant, secondary, and accent colours;
  • light character;
  • built-in grade.

Pull those colour decisions from /docs/bible.md when present. If they are undecided, ask the user rather than inventing them.

Write one canonical descriptor in complete prose. Never provide a short form or omit details for brevity. Mark the descriptor as draft until the asset passes stress-test.

Write the reference-sheet prompt

Write a prompt for the user's configured image model. Ask it to show the same asset on a neutral grey background in these views:

  1. front;
  2. three-quarter;
  3. profile;
  4. back;
  5. close portrait or close detail.

Paste the canonical descriptor verbatim into the prompt. Keep unrelated locations, set dressing, narrative action, and dramatic staging out of the sheet. For a state variant, include the full invariant identity and the variant's exact visible changes. Save each generated reference sheet beside its passport under the matching /assets/<type>/ folder. Give every sheet a versioned filename and record that exact path in the passport.

Create the passport file

Choose the matching folder:

  • characters: /assets/characters/;
  • locations: /assets/locations/;
  • props: /assets/props/.

Create a versioned Markdown file using the project's existing naming pattern. If no pattern exists, use <tag-without-@>-v<version>.md. Never rename a reference file; a new version gets a new file.

Use this structure:

markdown
# <tag> — version <version>
Status: draft
Type: <type>
Scenes: <scene IDs>
Seed files: <paths or pending>

## Canonical descriptor
<exhaustive descriptor>

## Reference-sheet prompt
<prompt containing the descriptor verbatim>

## Reference files
<versioned paths or pending>

Update the registry

Open /docs/registry.md and find the row by exact tag and version. Preserve the columns tag · type · version · seed file · scenes · status. Append a row when none exists; otherwise update that exact draft row. Set status to draft. Use the passport or reference-sheet path in seed file according to the project's existing convention. Do not mark the asset locked; only stress-test can do that.

Finish

Report the passport path, registry row, unresolved fields, and the next action. Tell the user to generate or attach the reference sheet in the asset folder, approve the references, and run stress-test before using the asset in film generation.

Frequently asked questions

What does the Asset Passport AI skill do?

Create film-asset passports before generation. Use for characters, locations, props, and state variants that need repeatable visual identity.

Why use Asset Passport on TypingMind?

Because you install it once and use it with any model. Asset Passport 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 Asset Passport in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/machina-exm/film-studio-skills/tree/main/skills/asset-passport. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Asset Passport?

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 Asset Passport?

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

Is the Asset Passport AI skill free?

It is published on GitHub by machina-exm. Check the repository for licensing terms. 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 👇