Original workflows for websites, images, presentations, and everything in motion.
Design guidance for AI coding agents: generate a project design system, search styles, colors and typography, and apply framework-specific UI/UX recommendations to web and app interfaces.
Distill a conversation or completed task into reusable lessons for later agent work.
Save the decisions, facts, dead ends and architecture this conversation established to Atlas's shared memory, so other agents and future sessions can build on them.
Run Happy workspaces and use session, browser, terminal, diagram and observability workflows.
Turn owner, colleague, relationship or public-figure source material into reusable person profiles for personal agents.
Coordinate agents, workspaces, handoffs, advisors, committees and user plugins.
Design a project-specific harness with specialist agents, task Skills and a working orchestration structure.
Give coding agents a routed toolkit for web search, page reading, social content and video transcripts.
Collect execution feedback and improve an existing harness, its agents, Skills and orchestration rules.
Use two reasoning agents to reassess a difficult problem, investigate root causes and produce a plan.
Recall relevant context, summarize sessions and preserve durable memories through a configured Memori MCP connection.
Audit project rules, identify their source of truth, standardize naming, and build bridges for consistent use across agent hosts.
Compare perspectives from configured thinker personas to examine complex decisions and record a reasoned outcome.
Persistent memory for coding agents, with 21 curated workflows for recall, code exploration, planning, reviews, reports, and integrations. Install the upstream plugin; hosted memory and model usage may cost extra.
Inspect and control Herdr workspaces, tabs, panes, commands and coding agents from a Herdr-managed terminal.
Ask one coding agent for a second opinion on a task while retaining ownership of the work.
Build and debug Python agents and multi-agent workflows with Swarms tools, memory and orchestration architectures.
Implement NPC decision systems with blackboards, reusable behavior-tree nodes, utility scores, response curves, and hybrid agents.
Bake navigation surfaces, move NavMeshAgents, check reachable paths, carve obstacles, and connect navigation regions.
Code comment hygiene for AI coding agents: remove generic AI-slop comments, keep the valuable ones, never touch the code.
The official shadcn/ui skill for AI agents. Find, add, compose, customize, and debug UI components using your project configuration, current component docs, and the shadcn CLI.
Install, synchronize, inspect, deduplicate, or uninstall individual skills and collections across compatible agent hosts.
Design agents around capabilities, domain knowledge, context and progressively added complexity.
Transfer a task to another agent with the working context and progress needed to continue.