unsloth-training vs Skills Anywhere
unsloth-training is no longer listed on any marketplace we read: these are its last known data, as of 2026‑10‑29.
unsloth-training is a plugin bundle for AI coding tools published by duyet. No marketplace we read lists it any more. Skills Anywhere is an MCP server published by noteflowai. Marketplaces we read that list it: 2 (Official MCP Registry, npm registry (MCP servers)). As of our marketplace pass on 2026-10-29. A plugin in this pair is no longer listed on any marketplace we read, so search engines are asked not to index the page.
Where each is published
| Marketplace |  Skills Anywhere | |
|---|---|---|
| Community marketplace duyet/codex-claude-plugins | Removed on 2026-10-29 Version: 1.1.0 Forks (GitHub): 1 Stars (GitHub): 15 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 0.19.0 Downloads/month (npm): 4 567 Downloads/week (npm): 652 Forks (GitHub): 0 Stars (GitHub): 6 Not marked · First seen |
| npm registry (MCP servers) | Not listed | Listed Version: 0.19.0 Downloads/month (npm): 4 567 Downloads/week (npm): 652 Forks (GitHub): 0 Stars (GitHub): 6 Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | unsloth-trainingno longer listed · | Skills Anywhere |
|---|---|---|
| Marketplaces that list it (differs) | 0 | 2 |
| Stars (GitHub) (differs) | 15 | 6 |
| Forks (GitHub) (differs) | 1 | 0 |
| Last release | Not published | Not published |
| Where it runs (differs) | Installs as a plugin bundle | On your machine (dsh-skills-anywhere) |
| Transport (differs) | Not stated | stdio |
| Tools it declares | Not published | Not published |
| Environment variables it asks for | Not published | Not published |
| Parts of the bundle (differs) | 1 | Not a bundle |
| Licence | MIT | MIT |
| Repository (differs) | github.com/duyet/codex-claude-plugins | github.com/noteflowai/dsh-skills-anywhere |
| Changes in the last 7 days (differs) | 2 | 0 |
| First seen (differs) | 2026-10-16 | 2026-10-11 |
Lines where the two differ have a tinted background and bold values. No value is marked better or worse: a plugin no marketplace lists any more is shown with its last known data, which we do not rank against current figures.
What to use instead of unsloth-training
Plugins still listed whose own names, descriptions, tools and skills are closest in meaning to it. Comparable, not endorsed.
-
Collection of LLM engineering skills for PyTorch, Transformers, LoRA, and MLX
-
Connect to Hugging Face Hub and thousands of Gradio AI Applications
-
Build, train, evaluate, and use open source AI models, datasets, and spaces.
-
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.
-
LLM application development, prompt engineering, and AI assistant optimization
What each says it does
unsloth-training
Fine-tune LLMs with Unsloth using GRPO or SFT: rewards, datasets, FP8, vision, MLX, export, mobile.
Skills Anywhere
Discover and load Agent Skills from configured local directories and Git sources over stdio MCP.
How to run each
unsloth-training
No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.
Skills Anywhere As a local MCP server: npm package
claude mcp add --transport stdio dsh-skills-anywhere -- npx -y dsh-skills-anywhere mcpCommands built only from what the marketplaces declare; the full set for every client is on each card.
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
Neither one's marketplaces publish the settings it asks for.
What it can do: unsloth-training · What it can do: Skills Anywhere · Compare two other plugins
Data comes from public marketplace files in GitHub repositories of their authors. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Package data comes from the public npm registry (registry.npmjs.org). Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.