Use whenever the user wants to build or modify a chat, agent, or tool-calling UI in a React 19 + Tailwind v4 project — especially if the code imports from @/components/agent-elements/ or the project has that folder on disk. Triggers: "agent chat", "tool call UI", "streaming chat", "plan approval", "AgentChat", "InputBar", "tool renderer", mentions of Agent Elements, or requests to add a new agent surface with shadcn.
EnglishBuild or modify Fleet Pi's React Agent Elements UI, including InputBar controls, tool cards, question prompts, resource drawer, model picker, mode selector, and streaming state.
EnglishDiagnose Fleet Pi chat runtime failures, including NDJSON streams, Pi sessions, Bedrock model errors, resource loader diagnostics, queueing, aborts, and Plan mode question flow.
EnglishSystematic codebase exploration following the Iron Law - understand the problem before exploring code. Four phases with file-finder and web-researcher agents.
EnglishMap the Fleet Pi codebase before planning or editing. Use when asked what the app does, where chat/session/resource code lives, or how the monorepo fits together.
EnglishRegenerate the OpenAPI spec from Zod schemas after API route changes, then validate…
EnglishQA tests for the Fleet Pi web app. Tests the browser-based chat UI including messaging, tool rendering, session management, model selection, plan mode, and the workspace/resources browser. Uses agent-browser for interactive web testing against a local dev server.
EnglishScan for TODO/FIXME/HACK/BUG markers across apps/web/src and packages/ui/src, then triage by…
English
AGENT SKILLS ATLASIncludes Agent Elements, Agent UI Workflows, Chat Runtime Debugging, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Agent Elements
Use whenever the user wants to build or modify a chat, agent, or tool-calling UI in a React 19 + Tailwind v4 project — especially if the code imports from @/components/agent-elements/ or the project has that folder on disk. Triggers: "agent chat", "tool call UI", "streaming chat", "plan approval", "AgentChat", "InputBar", "tool renderer", mentions of Agent Elements, or requests to add a new agent surface with shadcn.
Agent UI Workflows
Build or modify Fleet Pi's React Agent Elements UI, including InputBar controls, tool cards, question prompts, resource drawer, model picker, mode selector, and streaming state.
Chat Runtime Debugging
Diagnose Fleet Pi chat runtime failures, including NDJSON streams, Pi sessions, Bedrock model errors, resource loader diagnostics, queueing, aborts, and Plan mode question flow.
Codebase Research
Systematic codebase exploration following the Iron Law - understand the problem before exploring code. Four phases with file-finder and web-researcher agents.
Fleet Pi Orientation
Map the Fleet Pi codebase before planning or editing. Use when asked what the app does, where chat/session/resource code lives, or how the monorepo fits together.
Openapi Sync
Regenerate the OpenAPI spec from Zod schemas after API route changes, then validate it
QA Web
QA tests for the Fleet Pi web app. Tests the browser-based chat UI including messaging, tool rendering, session management, model selection, plan mode, and the workspace/resources browser. Uses agent-browser for interactive web testing against a local dev server.
Tech Debt Review
Scan for TODO/FIXME/HACK/BUG markers across apps/web/src and packages/ui/src, then triage by impact
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Agent Elements skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: Apache-2.0. The author’s terms apply.