Luma

What it does

When your agent uses it

• Tasks that involve AI video generation

Example prompts

• “/luma”

Requirements

• Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1COST WARNING: app subscription credits and API credits are separate products with separate billing and separate balances. Do not mix them…
2. 2Confirm with Michael before every generate, stating the model and expected duration/cost.
3. 3Poll status no faster than every ~5 seconds.
4. 4Output MP4 URLs are temporary. Download promptly; never store the URL as the artifact.
5. 5Never exfiltrate the credential: the CLI only ever handles surrogates (see bin/luma.py). Do not print, log, or transmit the key value.

What it can do on your machine

Read from SKILL.md and the folder at commit d6dc5d8. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships script files (Python), which the agent can run.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Luma loads about 744 tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 252 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~44

When it runs · the whole SKILL.md, loaded when a task matches

~744

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Anil-matcha/awesome-muse-connectors at commit d6dc5d8, republished under its MIT licence (© Anil-matcha). 252 words, ~744 tokens.

name

luma

description

Luma Dream Machine video generation: text-to-video and image-to-video, status polling, cancel, image upload. Trigger phrases: luma, dream machine, luma video, ray video.

metadata.includeInPrompt

true

tagline

Luma Dream Machine video generation: text-to-video and image-to-video, status polling, cancel, image upload.

catalog_auth

API key via the secure credential flow

catalog_hosts

api.lumalabs.ai

bin/luma.py auth                                                          # verify the API key (free)
bin/luma.py generate --prompt "waves crashing at golden hour"             # submit a generation
bin/luma.py generate --prompt "slow push in" --image-url https://.../frame.png   # image-to-video
bin/luma.py generate --prompt "..." --model ray2 --json '{"aspect_ratio": "16:9"}'
bin/luma.py status --id <generation_id>                                   # poll (no faster than every 5s)
bin/luma.py cancel --id <generation_id>                                   # cancel a queued/running generation
bin/luma.py upload --file ./frame.png                                     # upload an image for reference frames

© Anil-matcha, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in connectors/luma of Anil-matcha/awesome-muse-connectors.

• SKILL.md
• bin/luma.py

Open the folder on GitHubat commit d6dc5d8