Stats
Actions
Tags
From ollama
Pull an Ollama model by name. Streams download progress. Run /ollama-models first to see what's already installed.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ollama:ollama-pullThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
`$ARGUMENTS` — model name (e.g. `llama3.2`, `mistral`, `codellama:13b`). Required.
$ARGUMENTS — model name (e.g. llama3.2, mistral, codellama:13b). Required.
MODEL="$ARGUMENTS"
if [ -z "$MODEL" ]; then
echo "Usage: /ollama-pull <model-name>"
echo "Examples: llama3.2 mistral codellama:13b nomic-embed-text"
exit 1
fi
if [ ! -f "$HOME/.claude/ollama.json" ]; then
echo "ERROR: Ollama not configured. Run /ollama-setup first."
exit 1
fi
HOST=$(python3 -c "import json,os; d=json.load(open(os.path.expanduser('~/.claude/ollama.json'))); print(d.get('host','http://localhost:11434'))")
echo "Pulling $MODEL from $HOST..."
curl -sf -X POST "$HOST/api/pull" \
-H "Content-Type: application/json" \
-d "{\"name\":\"$MODEL\",\"stream\":false}" \
| python3 -c "import json,sys; print(json.loads(sys.stdin.read()).get('status','done'))"
echo "Done. Run /ollama-models to verify."
Browse available models: https://ollama.com/library
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub danielstewart77/ollama-claude-plugin --plugin ollama