AI Film Production Team Agent Skill

Operate the AI-film production team and govern reusable assets from an approved director package.

Context cost
17.5k tokensestimated from the bundle, loaded when it triggers
Bundle
17 files · 75.9 kB1 script among them — read before you run
Licence
MITthe author’s own terms
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Prepare and preserve reusable AI-film identities, animal characters, locations, props and voices; review character references, voice auditions and scene continuity; track states, reference roles, generated sources, selects and dependencies. Use for production breakdown, asset reuse or continuity, including image-first workflows.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

productivity

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md11.0 kB · preview
--- name: production-asset-library ---
6# AI Film Production Assets
7
8Own asset identity/design, casting, production design, wardrobe, props, sound sources, storage and continuity records. Cinematography owns shot composition and editorial selection; this skill registers and preserves those files without turning every shot into a reusable asset. The writer-director owns story and exact words. The execution specialist owns model settings and generated-job records.
9
10## Scope And Existing Work
11
12Start from the active task/project policy and only the required asset subset. Follow the short work-packet procedure in [production-workflow.md](../ai-film-director/references/production-workflow.md) at stage changes; a source archive is not an instruction to load every file or to execute obsolete jobs.
13
14Use the current brief/script/shot list and existing assets at their actual level of maturity. A full episode contract is unnecessary for a small request. Inventory and organize existing material before making more. Preserve user-selected characters, style, tools, directories, IDs and approvals; do not equate an attractive filename or old prompt with approval.
15
16Separate reusable identity/design, scene state, shot composition references, raw generated sources, accepted ranges and edit exports. For image-first films, animals, storage or generated-source management, read [references/production-storage.md](references/production-storage.md). Reusable assets can be few while a sequence legitimately has many composition frames.
17
18## Breakdown And Reference Decisions
19
20For recurring cast and storyboard/contact-sheet inputs, read [references/reference-preparation.md](references/reference-preparation.md). Establish independent character assets before final character-bearing shot references. Multi-panel sheets may support planning; prepare and inspect individual shot images before ordinary video-reference conditioning, with explicit roles and crop lineage.
21
22Parse only relevant categories: cast/animals, wardrobe and condition, location/layout, props/ownership, extras, vehicles, weather/VFX, voice, pronunciation, ambience, foley, music and graphics. Record which shots need which IDs, versions and states. Prepare the next useful sequence or selected creative test rather than speculative variants for the entire film.
23
24Choose sufficient references for the intended quality and route:
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md1,274 words
Files17
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈100
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
17,375
on trigger
The instruction body and 16 supporting files, read only when the skill fires.
8.7%
of a 200k window
Ten skills this size would take about 87% of the window before you open a file.
050k100k150k200k context window

17.5k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

17 files, 75.9 kB on disk. Mostly text — the instructions the model reads — with 1 script in it that your client would run only if the instructions tell it to.

  • SKILL.md11.0 kB
  • agents/openai.yaml0.3 kB
  • examples/ancient-costume-four-view.md4.1 kB
  • examples/legacy-short-drama-prompt-examples.md7.7 kB
  • examples/realistic-guzhuang-character-refs.md4.3 kB
  • examples/short-drama-voice-assets.md3.1 kB
  • references/asset-schema.md3.9 kB
  • references/identity-consistency.md8.8 kB
  • references/research-notes.md1.5 kB
  • references/scene-breakdown-and-call-sheet.md4.5 kB
  • references/tool-workflows.md1.8 kB
  • scripts/init_character_library.py6.0 kB
  • references/character/character-card-template.md1.9 kB
  • references/character/consistency-workflow.md4.7 kB
  • references/character/industry-patterns.md1.8 kB
  • references/character/photoreal-portrait-prompting.md8.6 kB
  • references/character/project-library-template.md1.9 kB
What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 1 script beside the text, so the bundle is 17 files you can review in full before installing. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# AI Film Production Team · 17.5k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/ai-film-production-team/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/ai-film-production-team" ] && { [ ! -e .claude/skills/ai-film-production-team ] || { mv .claude/skills/ai-film-production-team "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/ai-film-production-team" .claude/skills/ && echo "Installed .claude/skills/ai-film-production-team"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add alianess/ai-film-production-team

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/ai-film-production-team/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/ai-film-production-team/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/ai-film-production-team" ] && { [ ! -e ~/.claude/skills/ai-film-production-team ] || { mv ~/.claude/skills/ai-film-production-team "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/ai-film-production-team" ~/.claude/skills/ && echo "Installed ~/.claude/skills/ai-film-production-team" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/ai-film-production-team/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. It appears as production-asset-library in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, ai-film-production-team.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referencealianess/ai-film-production-team

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers0
Claim this skill