AI Research Skills Library is a collection of reusable instructions that guide AI agents through research and machine-learning engineering tasks, from finding ideas and writing papers to training, evaluation, and deployment. It is for configuring agents such as Claude Code, Codex, and Gemini to perform research workflows.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/Orchestra-Research/AI-Research-SKILLsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/orchestra-research/ai-research-skills/multimodal)<a href="https://agentmods.dev/plugins/orchestra-research/ai-research-skills/multimodal"><img src="https://agentmods.dev/badge/plugins/orchestra-research/ai-research-skills/multimodal/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/orchestra-research/ai-research-skills/multimodal"><img src="https://agentmods.dev/badge/plugins/orchestra-research/ai-research-skills/multimodal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
multimodal scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "multimodal",
"description": "Vision, audio, and multimodal models including CLIP, Whisper, LLaVA, BLIP-2, Segment Anything, Stable Diffusion, AudioCraft, Cosmos Policy, OpenPI, and OpenVLA-OFT. Use when working with images, audio, multimodal tasks, or vision-language-action robot policies.",
"source": "./",
"strict": false,
"skills": [
"./18-multimodal/audiocraft",
"./18-multimodal/blip-2",
"./18-multimodal/clip",
"./18-multimodal/cosmos-policy",
"./18-multimodal/llava",
"./18-multimodal/openpi",
"./18-multimodal/openvla-oft",
"./18-multimodal/segment-anything",
"./18-multimodal/stable-diffusion",
"./18-multimodal/whisper"
]
}What it installs
The manifest is a name and a version. 10 skills travel with it, and installing the plugin installs all of them — 633 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill fine-tuning-openvla-oft A 103 tokens
- Skill evaluating-cosmos-policy A 51 tokens
- Skill fine-tuning-serving-openpi A 87 tokens
- Skill audiocraft-audio-generation A 54 tokens
- Skill segment-anything-model A 45 tokens
- Skill llava A 64 tokens
- Skill clip A 60 tokens
- Skill stable-diffusion-image-generation A 50 tokens
- Skill blip-2-vision-language A 52 tokens
- Skill whisper B 67 tokens
What ships with it
1 file beside marketplace.json#multimodal in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 18 lines scan A 87b630541cce
multimodal is a plugin published in the GitHub repository Orchestra-Research/AI-Research-SKILLs (12,412 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other plugins, from other repositories
ai-shortfilm-prompts
A collection of five-part methods and reusable templates for writing cinematic prompts for AI video generation. It covers 21 subject areas and lists compatibility with tools such as Seedance, Kling, Sora, Veo, Jimeng, and Runway.
qwen-mm-plugins-api
Qwen-MM-Plugins api — cloud APIs for understanding media, by model family: VL (vision chat, OCR, grounding), Omni A/V (timestamped captioning, ASR / multi-speaker diarization, temporal grounding, event counting), plus ASR and segmentation (SAM3), exposed as an MCP server; currently supports DashScope.
instagram-skills
9 Claude Code and Codex skills for Instagram marketing: caption writing with a first-125-char hook, slide-by-slide carousel planning, viral Reel and carousel hook extraction, 2026 hashtag sizing, an AI-tell humanizer with pre-publish audit, cross-platform repurposing, profile optimization, niche and profile audience…
visual-gen
Generate blog cover images, architecture diagrams, and process infographics as PNG files using HTML+CSS rendered via Chrome headless.
apple-creator-studio-skills
Apple Creator Studio workflows for production and delivery.
freeglm-api
FreeGLM API — cloud media understanding by model family: VL vision chat, OCR, and grounding on DashScope Qwen or Zhipu GLM-4.6V-Flash; Omni A/V, ASR, and segmentation on DashScope.