Loading...
Loading...
Install and initialize task-master for AI-powered task management and specification-driven development. Use this skill when users ask you to parse a new PRD, when starting a new project that needs structured task management, when users mention wanting task breakdown or project planning, or when implementing specification-driven development workflows.
npx skill4agent add sfc-gh-dflippo/snowflake-dbt-demo task-master-installtask-master --version.taskmaster/npm install -g task-master-ainpx task-master-ai init.taskmaster/task-master init--name <name>--description <text>--version <version>--rules <profiles>cursor,windsurf-y, --yestask-master init --name "My Project" --description "AI-powered web app" --version "0.1.0" --rules cursor,windsurf --yes.taskmaster/.cursor/rules/# Using npx (no global install required)
cortex mcp add --args '-y, task-master-ai, mcp' taskmaster npx
snova mcp add --args "run, -i, --rm, -e, DOCUMENT_URL, -e, DOCUMENT_TOKEN, -e, DOCUMENT_ID, -e, RUNTIME_URL, -e, RUNTIME_TOKEN, -e, ALLOW_IMG_OUTPUT, datalayer/jupyter-mcp-server:latest" --env "DOCUMENT_URL=http://host.docker.internal:8888, DOCUMENT_TOKEN=jupyter_mcp_token, DOCUMENT_ID=notebooks/model_training.ipynb, RUNTIME_URL=http://host.docker.internal:8888, RUNTIME_TOKEN=jupyter_mcp_token, ALLOW_IMG_OUTPUT=true" jupyter-mcp-server docker
# Or if task-master is installed globally
cortex mcp add taskmaster task-master --args "mcp".cursor/mcp.jsonclaude_desktop_config.json{
"mcpServers": {
"taskmaster": {
"command": "npx",
"args": ["-y", "task-master-ai", "mcp"]
}
}
}{
"mcpServers": {
"taskmaster": {
"command": "task-master",
"args": ["mcp"]
}
}
}winget install OpenJS.NodeJSbrew install nodesudo apt install nodejs npmsudo yum install nodejsnpm uninstall -g task-master-ai
npm install -g task-master-aitask-master --versioncurl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.3/install.sh | bashnvm install 24