Review how you use Superset and identify unused features that fit your workflow. Get a short list of suggestions, learn about each option, and set up selected features such as scheduled agents, parallel workspaces, or shared tasks.
Personalized audit that teaches the advanced Superset features the user isn't using yet (automations, parallel agents, tasks, multi-host, terminal remote control, custom commands, MCP, pages) and sets them up live. Use when the user wants to get more out of Superset, asks "what else can Superset do", "how do I 10x my workflow", "what am I missing", or wants to learn a specific Superset feature.
Review the instructions the agent will receive before you install.
Teach the user the advanced Superset features they aren't using yet, grounded in their real usage rather than a lecture. If they named a topic after the command, skip the audit and go straight to that topic.
Run bash scripts/audit.sh from this skill's directory (bash ${CLAUDE_SKILL_DIR}/scripts/audit.sh in Claude Code). It runs superset auth whoami, automations list, workspaces list, agents list --local, hosts list, tasks list, and pages list with --json, tolerating individual failures, and prints one JSON object.
If the CLI is missing, offer to install it: curl -fsSL https://superset.sh/cli/install.sh | sh. If unauthenticated, superset auth login. If the audit is impossible, ask the user what their current workflow looks like and proceed from their answer.
Compare their usage against the catalog below and present a short scorecard: the 3-5 highest-impact features they aren't using, one line each on the payoff. No walls of text.
For each recommendation in order: a two-sentence pitch, then ask (use the ask_user tool if available) with options Set it up now / Tell me more / Skip. "Set it up now" means actually doing it, creating the real automation or spawning the real workspace, after confirming the specifics (name, schedule, prompt) with the user. Never print instructions as a substitute for doing it.
| Feature | Why it 10x's you | Live setup |
|---|---|---|
| Automations | Scheduled agents: triage, changelogs, standups run while you sleep | superset automations create, then superset automations logs to review runs |
| Parallel workspaces | Every task gets an isolated worktree; run several agents at once instead of queueing | superset workspaces create --local --project <id> then superset agents create --workspace <id> --agent claude --prompt "..." |
| PR review workspaces | Check out any PR into its own workspace in one command | superset workspaces create --local --pr <number> |
| Tasks | A shared queue agents can pick up; track work across sessions | superset tasks create --title "...", superset tasks update |
| Multi-host | Run agents on your desktop from your laptop; wake offline machines | superset hosts list, superset hosts set-wake, superset hosts wake <id> |
| Terminal remote-control | Read and drive any agent's terminal from anywhere | superset terminals list / read / send |
| Custom slash commands | Your repo's own workflows as commands every agent can run | create .agents/commands/<name>.md in their repo |
| MCP servers | Give every workspace agent the same extra tools | add servers to .mcp.json at their repo root |
| Pages | Turn a report, dashboard, or digest into a link the org can read and pin comments to, versioned on every republish | the page skill, or superset pages publish report.html --workspace <id> --title "...", then superset pages comments list |
| Feedback loop | Report bugs or ideas without leaving the agent | the feedback skill |
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Set up recurring tasks in Superset with an agent prompt, a schedule or event trigger, and a chosen execution workspace. After explicit confirmation, create the automation, check its saved settings, and review a real first run.
Browse pages, click controls, fill fields, and inspect screenshots or console messages through Superset's browser pane. Use it to preview a running web app, check interface behavior, and work through browser tasks in a visible session.
Build Stripe payments, subscriptions, and invoicing using verified documentation and API parameter definitions. The skill guides product selection, sandbox testing, and webhook handling, where server notifications determine payment and subscription state.
Verify desktop UI changes through the Chrome DevTools Protocol, a connection for controlling the running app. Reproduce the user’s actual steps and compare screenshots, measured state, and console errors to establish evidence before and after a fix.
Diagnose failed GitHub Actions runs by finding the first meaningful error, separating code problems from infrastructure issues and intermittent failures, and comparing the base branch. Get a focused report explaining the PR’s involvement and recommended next steps.
Operate real desktop apps and browser windows by inspecting controls, clicking, typing, and checking the result after each action. Use it for settings changes, window arrangement, or verifying a complete workflow through the interface.