Multimodal LLM

What it does

When your agent uses it

• Processing images
• Transcribing audio
• Generating speech
• Generating AI video (Kling v3

Example prompts

• “/multimodal-llm”

Requirements

• Python 3
• Compatibility (from SKILL.md): Claude Code 2.1.277+.
• Pre-approved tools (allowed-tools): Read, Glob, Grep, WebFetch, WebSearch

Workflow steps

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

1. 1Not setting max_tokens on vision requests (responses truncated)
2. 2Sending oversized images without resizing (>2048px)
3. 3Using high detail level for simple yes/no classification
4. 4Using STT+LLM+TTS pipeline instead of native speech-to-speech
5. 5Not leveraging barge-in support for natural voice conversations
6. 6Using deprecated models (GPT-4V, Whisper-1)
7. 7Ignoring rate limits on vision and audio endpoints
8. 8Calling video generation APIs synchronously (they're async — poll or use callbacks)
9. 9Generating separate clips without character elements (characters look different each time)
10. 10Using Sora for high-volume social content (expensive, slow — use Kling Standard instead)

What it can do on your machine

Read from SKILL.md and the folder at commit e4ff8d9. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Glob
  • Grep
  • WebFetch
  • WebSearch

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  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.

• Compatibility

  Claude Code 2.1.277+.

  From compatibility in the SKILL.md frontmatter.

Context cost

Multimodal LLM loads about 2.2k tokens when it runs. Until then it costs about 72 tokens; SKILL.md has 806 words of instructions outside code blocks.

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

~72

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

~2.2k

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 yonatangross/orchestkit at commit e4ff8d9, republished under its MIT licence (© yonatangross). 806 words, ~2,246 tokens.

name

multimodal-llm

description

Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI video (Kling v3, Sora 2, Veo 3.1 std/lite/fast, Runway Gen-4.5 via `gen4_turbo`), or building multimodal AI pipelines.

allowed-tools

Read, Glob, Grep, WebFetch, WebSearch

compatibility

Claude Code 2.1.277+.

license

MIT

user-invocable

false

disable-model-invocation

true

effort

high

metadata.owner-agent

multimodal-specialist

metadata.category

mcp-enhancement

metadata.version

2.1.1

metadata.author

OrchestKit

metadata.complexity

high

metadata.tags

vision, audio, video, multimodal, image, speech, transcription, tts, kling, sora, veo, video-generation

import anthropic, base64

client = anthropic.Anthropic()
with open("image.png", "rb") as f:
    b64 = base64.standard_b64encode(f.read()).decode("utf-8")

response = client.messages.create(
    model="claude-opus-5-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": [
        {"type": "image", "source": {"type": "base64", "media_type": "image/png", "data": b64}},
        {"type": "text", "text": "Describe this image"}
    ]}]
)

© yonatangross, 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 12 other files in src/skills/multimodal-llm of yonatangross/orchestkit.

• SKILL.md
• rules/_sections.md
• rules/_template.md
• rules/audio-models.md
• rules/audio-speech-to-text.md
• rules/audio-text-to-speech.md
• rules/video-generation-models.md
• rules/video-generation-patterns.md
• rules/video-multi-shot.md
• rules/vision-document.md
• rules/vision-image-analysis.md
• rules/vision-models.md
• test-cases.json

Open the folder on GitHubat commit e4ff8d9