overthinkos/unsloth
ov-jupyter/skills/unsloth/SKILL.md
Unsloth LLM fine-tuning library with vLLM integration. Tier 1 post-install layer — no pixi.toml, requires pixi env from a parent layer (python-ml, jupyter-ml, unsloth-studio). Use when working with Unsloth, LLM fine-tuning, or vLLM wheel installation.
development
Updated May 10, 2026
$ install --global
skillsauthnpx skillsauth add overthinkos/overthink-plugins unslothInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 10, 2026, 5:38 AM164.6s1 file scanned
SKILL.md
- name:
- unsloth
- description:
- |
unsloth -- LLM fine-tuning (Tier 1 post-install layer)
Layer Properties
| Property | Value |
|----------|-------|
| Dependencies | None (requires pixi env from parent) |
| Volumes | models -> ~/.cache/huggingface |
| Aliases | unsloth -> unsloth |
| Install files | layer.yml, tasks: |
Architecture: Tier 1 Post-Install Layer
This layer has no pixi.toml and no depends. It installs pip packages into the pixi environment established by a Tier 2 "environment-owner" parent layer. The user-phase tasks run AFTER the parent's pixi COPY in the final image build.
Cannot be used standalone — must be composed into an environment-owner layer via the layers: field.
Environment Variables
| Variable | Value |
|----------|-------|
| UNSLOTH_SKIP_LLAMA_CPP_INSTALL | 1 |
| HF_HOME | ~/.cache/huggingface |
Post-pixi Installs (tasks:)
- vLLM cu130 nightly wheel (
pip install --no-deps) — installed here because vLLM wheel must run after pixi env exists - unsloth + unsloth-zoo (
pip install --no-deps) — incompatible with transformers 5.x in pixi solve - opentelemetry runtime deps (
pip install) — pixi resolver conflict prevents solving these via conda-forge - vLLM torch.compile patch (
patch_vllm_size_nodes.py) — fixes_decompose_size_nodesbug wheregetitemusers andx.size(dim)patterns crash during model compilation (upstream: vllm-project/vllm#38360)
Used In Layers (via layers: field)
/ov-jupyter:jupyter-ml—layers: [llama-cpp, unsloth, jupyter-mcp]/ov-jupyter:unsloth-studio—layers: [llama-cpp, unsloth]
Related Layers
/ov-jupyter:llama-cpp— llama.cpp binaries (often paired as sibling Tier 1 layer)/ov-jupyter:unsloth-studio— Studio web UI (Tier 2 parent, owns pixi.toml)/ov-jupyter:jupyter-ml— ML Jupyter with MCP (Tier 2 parent, owns pixi.toml)/ov-foundation:python-ml— Core ML environment (Tier 2, uses vllm pip install in its own tasks: instead)
Used In Images
/ov-jupyter:jupyter-ml(viajupyter-mlmetalayer)/ov-jupyter:jupyter-ml-notebook(viajupyter-mlmetalayer)/ov-jupyter:unsloth-studio(viaunsloth-studiometalayer)
When to Use This Skill
Use when the user asks about:
- Unsloth fine-tuning setup or configuration
- LLM fine-tuning environments
- The unsloth Python library or unsloth-zoo
- vLLM wheel installation inside pixi environments
- HuggingFace model cache volume
- The
unslothhost alias - The two-tier layer architecture for ML layers
Related
/ov-build:layer— layer authoring reference (layer.ymlschema, task verbs, service declarations)/ov-build:eval— declarative testing (eval:block,ov eval image,ov eval live)
Related Skills
overthinkos/agents
development
VerifiedTrustedCommunity
Claude Code multi-agent support in Overthink — sub-agents, dynamic workflows, and agent teams, and how each drives the existing `ov eval` disposable beds to test and verify. MUST be invoked before authoring or invoking an ov sub-agent / dynamic workflow / agent team, wiring agent-lifecycle hooks, or asking "which primitive should drive the R10 beds?".
SKILL.mdUpdated May 31, 2026
overthinkos/workspace-mount
tools
VerifiedTrustedCommunity
Mounts a virtiofs share tagged `workspace` at /workspace inside a VM guest via a systemd .mount unit. Use when a kind:vm entity shares a host directory into the guest and you need it auto-mounted (and re-mounted at every boot).
SKILL.mdUpdated May 30, 2026
overthinkos/android
development
VerifiedTrustedCommunity
MUST be invoked before any work involving: the `kind: android` schema kind, a `target: android` deploy, the `apk:` layer package format (installing Android apps declaratively), AndroidDeployTarget, an in-pod emulator OR a remote/physical adb-endpoint device, or nested `pod → android` deployment. The first-class Android device + app surface that sits above `ov eval adb`/`appium`.
SKILL.mdUpdated May 26, 2026
overthinkos/git-workflow
tools
VerifiedTrustedCommunity
Use when committing, branching, pushing, merging, tagging, creating PRs, or approving/merging PRs with gh — the feat/-branch, R10-gated, never-force-push landing workflow across the main repo + the plugins submodule + image/<distro> submodules. Covers sync-to-upstream, branch/worktree pruning, the fork+PR path for contributors without write access, and cross-repo @github landing order.
SKILL.mdUpdated May 25, 2026