oh-my-mlip
Claude Code plugin for oh-my-mlip, five skills behind one registry: /oh-my-mlip:setup installs+verifies a model env on your GPU; /oh-my-mlip:run executes single-point predictions…
Plugin-Paket · von Jinuk Moon
Überblick
oh-my-mlip ist ein Plugin-Paket für KI-Coding-Tools von Jinuk Moon. Marktplätze, die wir lesen und die es listen: 1 (Community GitHub marketplaces). Wir haben es erstmals am 2026-10-23 gesehen und seither keine Änderung erfasst. Stand unseres Marktplatz-Durchlaufs vom 2026-10-28.
Claude Code plugin for oh-my-mlip, five skills behind one registry: /oh-my-mlip:setup installs+verifies a model env on your GPU; /oh-my-mlip:run executes single-point predictions; /oh-my-mlip:catbench runs adsorption benchmarks and builds the comparison report; /oh-my-mlip:finetune converts your dataset and drives the framework's own fine-tuning; /oh-my-mlip:distill orchestrates teacher-to-NN-MTP distillation down to a CPU LAMMPS student. Deterministic by design — every executed command exists on disk first.
Was es abfragt
- Wird als Plugin-Paket installiert
Keiner der Marktplätze, die wir lesen, veröffentlicht seine Tools oder die abgefragten Einstellungen.
Was es deklariert, abfragt und ausführt, vollständig
Installieren Sie nur Plugins von Entwicklern, denen Sie vertrauen. Wir zeigen, was die Marktplätze veröffentlichen, und testen keine Plugins.
Funktioniert mit
- Claude Code
Nach den Marktplätzen, die ihn listen, und dem angegebenen MCP-Transport, wie jeder Client sie dokumentiert. Wir testen keine Plugins.
Verbinden
Befehle und Konfigurationen nur aus den Angaben der Marktplätze. Wir führen sie nicht für Sie aus und testen keine Plugins.
Als Claude-Code-Plugin
Erstellt aus den Angaben von Community GitHub marketplaces.
/plugin marketplace add jinukmoon/oh-my-mlip
/plugin install oh-my-mlip@oh-my-mlipWo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Community-Marktplatz jinukmoon/oh-my-mlip (Quelle auf GitHub öffnen) | Gelistet | skills-2026.10.18.2 | Forks (GitHub): 1 Sterne (GitHub): 20 |
Nicht markiert |
Jede Zahl stammt vom jeweiligen Marktplatz und wird nie über Marktplätze hinweg addiert. Ein Marktplatz ohne veröffentlichte Zahl zeigt keine: keine Zahl ist nicht null.
In einem Community-Marktplatz gelistet
| Marktplatz | Repository | Sterne (GitHub) |
|---|---|---|
| oh-my-mlip | jinukmoon/oh-my-mlip | 20 |
Was das Paket enthält
So veröffentlicht auf Community GitHub marketplaces.
Skills: 5
catbenchdistillfinetunerunsetup
Was sich geändert hat
- Wird seitdem als Produkt geführt
- Community GitHub marketplaces: erschienen
Ähnliche Plugins
Produkte, deren eigene Namen, Beschreibungen, Werkzeuge und Skills diesem der Bedeutung nach am nächsten sind, auf allen Marktplätzen, die wir lesen. Die Nähe ist nur innerhalb dieser Liste geordnet.
-
Materials simulations for AI agents over MCP: binding token quote before every run, record after it.
-
Design experiments and make predictions for materials & chemicals properties in your local agent
-
Corollary — scientific AI models, tools and databases
Find open biology and chemistry AI models, bioinformatics tools and databases, and run them online.
-
Fine-tune LLMs with Unsloth using GRPO or SFT: rewards, datasets, FP8, vision, MLX, export, mobile.
-
Run real bioinformatics from your AI agent. Reliable, reproducible, on your own GPUs.
-
Plan small custom models and fine-tunes: check the Hub, research options, write the spec in a planning repo.
-
Claude model selection advisor — recommends optimal model for each task via shell hook. Zero attack surface.
-
Arquestra — Scientific Computing Orchestration
AI orchestration for computational chemistry and HPC workflows.
-
Predict structures, screen molecules and proteins, and design binders with Boltz from Claude Code.
-
Predict structures, screen molecules and proteins, and design binders.
Ähnliche Plugins nach Marktplatz
Dieselbe Frage an jeden Marktplatz einzeln: Gibt es dort ein Gegenstück zu diesem Plugin?
Gelistet auf Claude Code: claude-plugins-community (5)
-
Claude model selection advisor — recommends optimal model for each task via shell hook. Zero attack surface.
-
Arquestra — Scientific Computing Orchestration
AI orchestration for computational chemistry and HPC workflows.
-
Predict structures, screen molecules and proteins, and design binders with Boltz from Claude Code.
-
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered…
-
Autonomous experiment loop for Claude Code. Run an endless optimize-measure-keep/discard cycle on any optimization target: LLM training loss, test speed, bundle size, build time…
Gelistet auf Claude Code: claude-plugins-official (5)
-
Predict structures, screen molecules and proteins, and design binders with Boltz from Claude Code.
-
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered…
-
Build, train, evaluate, and use open source AI models, datasets, and spaces.
-
Build, train, and deploy AI models with deep AWS AI/ML expertise brought directly into your coding assistants, covering the surface area of Amazon SageMaker AI.
-
AMD's verified Agent Skills in one plugin: route image/audio through local AI on Ryzen AI, serve LLMs on AMD Instinct GPUs with vLLM, optimize inference throughput with Hyperloom…
Gelistet auf Claude: knowledge-work-plugins (5)
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Build multimodal AI applications with Pixeltable -- tables, computed columns, embedding search, UDFs, tool-calling agents, and 25+ AI provider integrations.
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
AI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp
-
Connect to preclinical research tools and databases (literature search, genomics analysis, target prioritization) to accelerate early-stage life sciences R&D
Gelistet auf Codex: openai-curated (openai/plugins) (5)
-
Predict structures, screen molecules and proteins, and design binders.
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
General life-sciences research workflows with query routing, evidence synthesis, and optional parallel subagent analysis across genetics, omics, biology, chemistry, structure…
Gelistet auf Community GitHub marketplaces (5)
-
Fine-tune LLMs with Unsloth using GRPO or SFT: rewards, datasets, FP8, vision, MLX, export, mobile.
-
Plan small custom models and fine-tunes: check the Hub, research options, write the spec in a planning repo.
-
Automated AI research toolkit: hypothesis generation, experiments, and paper writing
-
LLM serving benchmarks, SGLang model Day-0 support, profiling, code review, prod incident triage, PR-history dossiers, and SGLang explainer videos.
-
Skills for reproducing, verifying, and porting models in the Core AI model zoo.
Gelistet auf Copilot CLI: github/awesome-copilot (5)
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
Task Researcher and Task Planner for intermediate to expert users and large codebases - Brought to you by microsoft/edge-ai
-
Visualizes live session AI-credit usage as a Pac-Man board with pellets, ghosts, fruit milestones, and game-over limits.
-
Skills and interactive Copilot canvas for designing, configuring, testing and deploying agents to Microsoft Foundry.
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
Gelistet auf Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
-
Complete bundle: all Microsoft Skills for Fabric for developers and consumers.
-
code-apps-preview
Build and deploy Power Apps code apps using React, Vite, and Power Platform connectors.
Gelistet auf Cursor: cursor/plugins (5)
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
-
Build apps, scripts, and automations with the TypeScript SDK.
-
if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.
Gelistet auf Docker MCP Catalog (5)
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Tools for interacting with Hugging Face models, datasets, research papers, and more.
-
Discover and connect to a curated marketplace of MCP servers for extending AI agent capabilities.
-
Giving Claude ability to run code with E2B via MCP (Model Context Protocol).
Gelistet auf Official MCP Registry (5)
-
Materials simulations for AI agents over MCP: binding token quote before every run, record after it.
-
Design experiments and make predictions for materials & chemicals properties in your local agent
-
Corollary — scientific AI models, tools and databases
Find open biology and chemistry AI models, bioinformatics tools and databases, and run them online.
-
Run real bioinformatics from your AI agent. Reliable, reproducible, on your own GPUs.
-
Arquestra — Scientific Computing Orchestration
AI orchestration for computational chemistry and HPC workflows.
Gelistet auf PyPI (MCP servers) (5)
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
replicate com.mcparmory/replicate
Run AI models, create deployments, and manage predictions via cloud API
-
offline-mcp io.github.gabrielmahia/offline-mcp
Local AI over Ollama for low connectivity: status, local inference, model and deployment guides.
-
Read, measure and explain LLM eval runs of a digline suite. Cannot promote a baseline.
-
MCP server for AlphaFold and 8 other biomedical data sources with a local SQLite knowledge graph
Gelistet auf npm registry (MCP servers) (5)
-
rubber-duck io.github.nesquikm/rubber-duck
Bridge to multiple LLMs and CLI agents: councils, debates, voting, and more
-
sub-agents-mcp io.github.shinpr/sub-agents-mcp
MCP server for delegating tasks to specialized AI sub-agents across coding tools
-
open-mcp-apps io.github.2nd1st/open-mcp-apps
Persistent, interactive MCP Apps — the AI builds an app once, you both reuse it
-
SigRank SignalAF — AI Operator Cascade & Leaderboard
SigRank SignalAF on-device scanner — four-token cascade, leaderboard, 25 local tools.
-
Local MCP server for AI coding safety: risk checks, sessions, checkpoints, and fix prompts.
Nach Bedeutung gefunden, nicht über gemeinsamen Code oder ein gemeinsames Repository: Ähnliche Plugins bleiben getrennte Produkte, und dies ist weder eine Bewertung noch eine Empfehlung.
Möchten Sie dieses Zeichen für Ihr Plugin in unserem Katalog?
Belegen Sie mit einer Datei im Repository, einer Datei auf Ihrer Domain oder einem DNS-Eintrag, dass Sie es pflegen, und Sie können dieses Zeichen auf der Karte zeigen, dazu Live-Banner für Ihre Website und Ihr README. So funktioniert die Verifizierung
Außerdem erhalten Sie Hinweise, wenn ein Marktplatz es aufnimmt, entfernt, sein Verified-Zeichen oder seine Anforderungen ändert, und sein Remote-Endpunkt wird wie ein Webdienst überwacht.
Daten von Community GitHub marketplaces. Die Zahlen stammen aus unseren eigenen regelmäßigen Durchläufen über die Marktplätze, zuletzt abgerufen am . Kontaktdaten von Plugin-Herausgebern veröffentlichen wir nicht.