agent-native

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

Use Content for repo-backed Markdown/MDX docs, blogs, resources, rich document editing, local components, shareable copies, and Content local-file workspaces. Prefer Content actions over raw filesystem writes when available.

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 Clips shares recordings — composes with the framework sharing skill and adds password, expiry, embed URLs, and view-counting. Use when wiring the share dialog, building embed links, adding a password, or debugging who can see a recording.

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.

Turn ordinary text plans into rich interactive visual plans with diagrams, file maps, annotated code, open questions, and UI/prototype review when useful.

Turn a PR, branch, commit, or git diff into an interactive visual recap with diagrams, file maps, API/schema summaries, annotated diffs, and focused review notes.

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

Add or use full agent harness runtimes like Claude Code, Codex, Pi, Cursor, Mastra, or ACP agents inside Agent Native.

Best practices for Remotion - Video creation in React

How screen and camera recording works in Clips — MediaRecorder lifecycle, chunked upload, permission handling, pause/resume, camera bubble overlay, and error recovery. Use when adding or modifying the recorder UI, the upload endpoint, or permission prompts.

How to delegate all AI work to the agent chat. Use when delegating AI work from UI or scripts to the agent, when a user asks for agent behavior or LLM-powered features, when tempted to add inline LLM calls, or when sending messages to the agent from application code.

How to keep the UI in sync with agent changes via SSE plus polling fallback. Use when wiring query invalidation for new data models, debugging UI not updating, or understanding jitter prevention.

Build many focused workspace apps that compose through agent discovery and A2A. Use when designing headless mini-apps or cross-app workflows.

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 data fetching.

How to find version-matched Agent Native framework docs bundled in node_modules. Use before implementing or answering questions about @agent-native/core APIs, generated apps, workspaces, or advanced features.

Declaratively register API keys and service credentials a template needs so they appear in the agent sidebar settings UI and the onboarding checklist. Use for any third-party API key (OpenAI, Stripe, Twilio, etc.) and for surfacing OAuth connections in the unified settings UI.

How to add routes without remounting the app shell. Use when adding a new route, fixing agent sidebar reloads on navigation, or choosing between `root.tsx` layout and pathless `_app.tsx` layout patterns.

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.

Answer code/product questions as visual Plan artifacts using repo, bridge, or GitHub context; use for API specs, UI look, schema models, and architecture.

Search Gong call metadata and transcript excerpts for sales-call analysis, customer conversations, objections, risks, and next steps.

Make arbitrary authenticated HTTP calls to configured Analytics providers when first-class actions are too narrow; inspect provider docs/specs first.

Search sales call recordings, transcripts, and participants via Gong. Use this skill when the user asks about sales calls, customer conversations, or call transcripts.

Make arbitrary authenticated HTTP calls to configured Analytics provider APIs when first-class actions are too narrow.

How to view, export, and analyze form responses. Use when the user asks about submitted data, wants to export responses, or needs response analytics.

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 MCP Apps and deep links. Use when adding an action's `link` builder or `mcpApp`, wiring the `/_agent-native/open` route, exposing an "ingest" action to MCP/A2A, or scaffolding apps from an external agent.

Agent observability, evals, feedback, and experiments. Use when adding observability dashboards, configuring trace capture, setting up evals, creating A/B experiments, or collecting user feedback on agent responses.

Secure coding practices for agent-native apps: input validation, SQL injection, XSS, secrets, data scoping, and auth. Use when writing any action, route, or component that touches user data or external input.

Commit and push all local current-branch work, open a ready PR, babysit it, merge when clean, then create a fresh branch

How to use Resources-backed workspace files for large-scale multi-source analyses: scratch/ temporary staging, chunked batch processing with per-item memos, run-code aggregation, saveToFile for big API pulls, and synthesizing across files that exceed one context window.

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

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.

Query the configured BigQuery warehouse for analytics data. Use when the user asks for warehouse SQL, BigQuery tables, Amplitude-in-BigQuery events, or a metric/table that the data dictionary says lives in BigQuery.

Query HubSpot CRM for deals, companies, contacts, tickets, owners, and account/deal context.

How the booking system works: checking availability, managing booking links, configuring availability settings, and the public booking URL pattern.

Monitor a PR, fix feedback and CI failures until fully green for 30 min. Run with /babysit-pr <number>

Creating, editing, and managing extensions — sandboxed Alpine.js mini-apps that run inside iframes. Use when a user asks for a dashboard, widget, calculator, or any interactive mini-app that calls external APIs. Distinct from LLM "tools" (function calls) — see note below.

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.

Use Agent Native Assets for image and video generation requests, brand-safe asset search/export, and human-in-the-loop asset selection through the hosted Assets MCP app. Prefer this over generic image tools when installed.

Use Agent Native Design for UI exploration, side-by-side design directions, interactive prototype previews, human selection, iteration, and coding handoff through the hosted Design MCP app.