Automation

Exa Search searches the web via Exa's API and extracts content like highlights, full text, or summaries alongside results. Use it when you need broad web results beyond academic databases, find similar pages, or fetch content from known URLs.

Experiment Bridge turns an experiment plan into running GPU experiments by implementing code, reviewing it, deploying it, and collecting initial results. Use it after idea refinement and before the auto review loop.

Experiment Queue orchestrates large batches of ML experiments on SSH remote GPU servers with state tracking, OOM retry, stale-screen cleanup, and wave transitions. Use it for multi-seed sweeps, grid searches, teacher-student chains, or any 10+ job batch that needs orchestration beyond a single run.

Feishu Notification sends status updates and checkpoint alerts to Feishu/Lark via webhook or interactive bridge. Use it when a user asks to notify Feishu or when other skills need to report experiment results, review scores, or pipeline steps.

Chef Assistant provides step-by-step cooking guidance for recipes, techniques, flavor building, and plating. Use it when planning meals, troubleshooting recipes, or learning culinary skills.

File Indexer scans a local directory, builds a searchable index of file metadata, and uploads the index to a configured remote search service over HTTP. Use it when you need to make local files searchable in a remote system.

File Organizer sorts files in a project directory by type and cleans up clutter. Use it when a project directory becomes disorganized and you need to restore structure.

General Assistant helps with any task when you ask for help or need assistance. Use it for general requests, task completion, or guidance.

Paseo Handoff transfers the current task to another agent with full context, including decisions, failed attempts, and constraints. Use it when the user asks to hand off work to another agent.

Superset 10x audits your Superset usage and teaches advanced features you aren't using yet, including automations, parallel workspaces, tasks, multi-host, terminals, custom commands, and MCP servers. Use it when you want to learn advanced Superset features or set up new automations and workspaces.

Superset Automate turns a recurring chore into a scheduled Superset automation. It drafts the agent prompt, confirms schedule and target, creates the automation via CLI, and reviews the first run to refine the prompt.

Superset Settings reads and updates the Superset desktop app's user settings via the superset CLI, including creating, importing, and switching custom themes from JSON. Use it to change app behavior, terminal appearance, git preferences, and notifications without opening the settings UI.