BuilderIO

How screen and camera recording works in Clips — MediaRecorder lifecycle, chunked upload, permission handling, pause/resume, camera bubble overlay, error recovery, and screenshots (still-image recordings). Use when adding or modifying the recorder UI, the…

How to create and run agent actions. Actions are the single source of truth for app operations — the agent calls them as tools and frontend code calls them through client hooks. Use when creating a new action, adding an API integration, or wiring up frontend…

How to look up version-matched Agent-Native framework docs and source in node_modules. Use before coding against @agent-native/core APIs or advanced features.

General guidance on querying data sources, using existing scripts vs ad-hoc queries, filtering patterns, and generating charts for the analytics app.

Own pull requests from outside contributors to BuilderIO/agent-native: see who is waiting, take one, reply warmly, and land it with their credit intact. Use when triaging community PRs, handling one, or auditing how replies went.

Review recent BuilderIO/agent-native human pull requests, approve eligible internal PRs, and merge changes that are ready by Steve's bar. Use for scheduled or manual PR sweeps; flag external work needing a major product call or new framework API, and…

All AI features in Clips — titles, summaries, chapters, tags, filler-word removal — delegate to the agent chat via sendToAgentChat except the narrow media pipeline path: transcription. Use when adding any AI-powered feature.

How auth works in agent-native apps. Use when wiring login/signup, configuring auth modes, setting up organizations, protecting routes, or debugging session issues.

Use in the BuilderIO/skills repo whenever adding, updating, publishing, documenting, validating, or wiring a public skill. Covers the repo-local skill files, root catalog docs, plugin metadata, @agent-native/skills dynamic install path, optional managed…

Alias for /efficient-orchestrator. Run only when the user explicitly invokes /efficient-fable; never self-activate.

Alias for /efficient-orchestrator. Run only when the user explicitly invokes /efficient-frontier; never self-activate.

Run only when the user explicitly invokes /efficient-orchestrator (or the /efficient-frontier and /efficient-fable aliases). Keeps an expensive model (Fable, Opus, Astra, Sol) on planning, judgment and review while cheaper subagents do bounded research,…

Turns a thread, skill, spreadsheet, or Claude/ChatGPT project into a polished, visual Agent-Native app: populated domain screens with the in-app agent working behind contextual controls. Use when a user invokes `/turn-into-app`, or asks to turn a workflow,…

Open and collaboratively edit a running local app in Design, with shared fallback previews and source handoff. Use when the user asks to inspect, share, or edit a real local app in Design.

Experimental workflow for babysitting one explicitly authorized pull or merge request. Use to monitor its live review state and checks, fix actionable in-scope findings, and apply separate reply, approval, merge, and soak gates.

Experimental workflow for collecting and triaging product feedback, product telemetry, runtime errors, and issue reports. Use when scanning configured signal sources and applying separate fix, reply, or close rules.

Performs a thorough code review covering correctness, security, performance, and style

Run fallow's project-wide scans (health, dead-code, dupes), report the top 10 issues across the whole codebase, and walk the user through fixing them one at a time. Use when the user wants a full-codebase quality pass, not a diff-scoped audit. Use when the…

Run the fallow diff-scoped code-quality audit (changes vs the merge-base), report the top 10 issues, and walk the user through fixing them one at a time. Stops immediately when the diff has no findings. Use when the user asks to audit or improve recent…

Set up, verify, build, and run the iOS app on a simulator or device. Use when the user invokes /ios-native install, asks to install or configure Xcode, or asks to build, compile, run, launch, or deploy the iOS app; also use when they mention xcodebuild,…

Translate a source application into a faithful web prototype through discovery, design and logic capture, gap planning, iterative implementation, and evidence-based review.

Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.

Relentlessly interviews the user to sharpen a plan, design, decision, or idea while building the project's domain glossary and recording durable architectural decisions. Use when the user asks to be grilled, challenged, interviewed, stress-tested, or wants to…

Adds safe command allowlist entries to an existing builder.config.json. Use when a user asks to allow commands, permit a CLI tool, configure allowedCommands, enable mobile development tooling, or allow unzip commands, even if they do not mention this skill.

How to create and run agent actions. Actions are the single source of truth for app operations — the agent calls them as tools and frontend code calls them through client hooks. Use when creating a new action, adding an API integration, or wiring up frontend…

How the agent knows what the user is looking at. Use when exposing UI state to the agent, implementing view-screen or navigate actions, wiring navigation state, or debugging agent context issues.

How to store application data in agent-native apps. All data lives in SQL. Use when adding data models, deciding where to store data, or reading/writing application data.

The four-area checklist every new feature must complete. Use when adding any feature, integration, or capability to ensure the agent and UI stay in parity.

Fast end-to-end workflow for turning this starter into a working domain app from a short or vague request. Use when asked to build, make, create, or prototype an app, tool, tracker, dashboard, booking, inventory, or CRM system with Agent-Native. Read before…

Product-specific interface design for an Agent-Native app. Use when creating or changing any user-facing UI, including screenshot feedback, copy or density cleanup, settings, controls, or a visual redesign.

Cross-platform pattern for handling messaging integration webhooks (Slack, Telegram, WhatsApp, email, etc.) on serverless hosts. Use when adding a new integration adapter, debugging dropped messages, or wiring long-running agent work into a webhook handler.

How to register user-facing setup steps (API keys, OAuth, connecting third-party services) for the sidebar setup checklist. Use when adding a feature that needs initial user configuration.

Search, read, create, and update Jira issues, check sprint status, and see who's working on what. Use this skill whenever the user mentions Jira, asks about tickets, issues, sprints, or story points, references issue keys like PROJ-123, wants to know what…

Interact with Slack workspaces — search messages, read channel history, browse threads, list channels, and find users. Use this skill whenever the user mentions Slack, asks about messages in a channel, wants to check what people said about a topic, look up…

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for…

Expert help with GitHub CLI (gh) for managing pull requests, issues, repositories, workflows, and releases. Use this when working with GitHub operations from the command line.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or…

How agent-native apps discover, authenticate with, and call each other over A2A. Use when connecting one app to another, debugging a remote agent that won't authenticate, exposing skills to peers, or calling agents from scripts.

Manual, event-triggered, webhook-triggered, and schedule-triggered automations with optional event conditions. Use when creating automations, wiring events or webhooks, running one on demand, or understanding triggers.

Connect external agents and MCP hosts (Claude, Claude Desktop, Claude Code, ChatGPT custom MCP apps, Codex, Cursor, Claude Cowork, VS Code GitHub Copilot, Goose, Postman, MCPJam) to an agent-native app over MCP, and round-trip artifacts back into the UI with…

Turns a thread, skill, spreadsheet, or Claude/ChatGPT project into a polished, visual Agent-Native app: populated domain screens with the in-app agent working behind contextual controls. Use when a user invokes `/turn-into-app`, or asks to turn a workflow,…

Make a product screenshot (still, product image, hero image, "picture of the app") of any agent-native app (Clips, Slides, Analytics, Design, Plan, Content, Chat, Mail, Calendar, Forms, CRM, Tasks…) in light and dark mode, built in code from the real app's…

Make a short product video (launch video, feature video, demo clip, animated product visual, social video) of any agent-native app built in code with Remotion from the real app's source, with motion held to Emil Kowalski's animation standards. Use when…

Set up Product Visuals on this computer, or check that it's ready. Clones the repo if the user only pasted its link, installs packages, downloads the agent-native code and the render browser. Use when the user pastes the repo link and says "set this up", "set…

Search and read Jira issues, check sprint status, and see who's working on what. Use this skill whenever the user mentions Jira, asks about tickets, issues, sprints, or story points, references issue keys like PROJ-123, wants to know what someone is working…

Interact with Slack workspaces — search messages, read channel history, browse threads, list channels, and find users. Use this skill whenever the user mentions Slack, asks about messages in a channel, wants to check what people said about a topic, look up…