FreeSkills
Commits, branches and sync with the but CLI
- 361361 downloads
- 198198 likes
- 103103 saves
- Claude Code
- Codex
- Cursor
- and 3 more
Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans
Use this resource to run LLMs locally with Ollama
New
Free
In a terminal, from the folder you want:
npx --yes palatekit@latest install ollama-local-llm-stackWith no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.
First time: connect the CLI with
npx --yes palatekit@latest loginThe agent installs Ollama, downloads a model with the chosen quantization, then sets up a Docker Compose stack with Open WebUI. You get the commands, a model selection guide by available memory and a docker-compose.yml file.
Mostly picked by
Updated November 2, 2026
You say
“Install Ollama on my machine with a 7B model and an Open WebUI interface in Docker.”

Skill published by bagelhole under the MIT license, delivered in its original version.
Listed unmodified
« ollama-stack » (bagelhole, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.
–
No ratings yet
Loading reviews…