Design and review agent systems using published patterns, worked examples, glossary definitions, and decision records. Three skills help review an existing agent artifact, design a new agent system, and apply a named pattern. Five read-only MCP tools find relevant patterns, retrieve cards and exact sections, trace relationships, and provide a curated learning path. Recommendations cite their sources and distinguish published guidance from roadmap entries. Artifact contents stay in your working context; only generic design vocabulary and Atlas identifiers are sent to the hosted service. Applying a pattern can produce local edits when you authorize them. No account is required.
How to use
- 1Add it in ChatGPT
Open Agentic Atlas in ChatGPT's Plugin directory (button above), select + to add it and sign in if asked.
- 2Use it in a chat
Type @ in the composer and pick Agentic Atlas, or start your message with its name. ChatGPT may also suggest it when it fits what you ask.
Skills 3
- applying-a-pattern
Apply one named Agentic Atlas pattern to one existing skill, agent, plugin, or workflow as concrete, cited edits. Use when the user points at a specific pattern (by id, title, or agentic-atlas.dev link) and wants their artifact changed to follow it: "apply this pattern to my skill", "retrofit my plugin with progressive disclosure". A review against every pattern goes to reviewing-agent-designs; nothing built yet goes to designing-agent-systems. Changes that do not trace to a named pattern stay with the normal development workflow.
- designing-agent-systems
Design a new agent system (skill, subagent, plugin, hook set, or multi-agent workflow) from the Agentic Atlas patterns, with a citation behind each structural choice. Use when the user is starting one or rethinking its shape: "help me design an agent for X", "should this be one agent or several", "what context should each dispatch carry", or where verification belongs in the decomposition. Also answers quick atlas questions like "what does the atlas say about X". An artifact that already exists goes to reviewing-agent-designs; one named pattern to retrofit goes to applying-a-pattern. Not for ordinary software design (schemas, APIs, app code).
- reviewing-agent-designs
Audit an existing agent artifact (skill, subagent, plugin, hooks, or multi-agent workflow) against the Agentic Atlas patterns and return cited, checkable findings. Use when the user wants something they already wrote reviewed, critiqued, or graded: "review my skill", "is this agent definition right", "why does my skill never trigger", even if they never mention the atlas. Nothing written yet goes to designing-agent-systems; one named pattern to retrofit goes to applying-a-pattern. Not for ordinary application code that merely sits near agents.
Things to ask
- “Help me design a research agent with clear verification boundaries.”
- “Review my agent skill against Agentic Atlas patterns.”
- “Show me where to start with Agentic Atlas.”