BuilderIO/agent-native - 第 3 页

library-management

Schema, CRUD, sharing, URL style imports, and cascade-delete patterns for asset libraries, collections, and assets. Use when managing a library or importing visual brand evidence from a URL.

原文语言：英语

analysis-workspace

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…

原文语言：英语

agent-native-docs

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

原文语言：英语

actions

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…

原文语言：英语

adding-a-feature

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.

原文语言：英语

agent-native-docs

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

原文语言：英语

agent-native-toolkit

Inventory and ownership rules for shared Agent Native workspace UI. Use before building app chrome, settings, navigation, sharing, collaboration, setup, history, comments, chat rails, agent UX, or repeated workspace behavior.

原文语言：英语

delegate-to-agent

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…

原文语言：英语

frontend-design

Sets the visual direction for a new or redesigned surface, with production quality that avoids generic AI aesthetics. Use when building a new page, app, or marketing surface, defining visual identity, or doing a design pass ("make this look good"). Do not…

原文语言：英语

self-modifying-code

Tiers, checkpoints, and off-limits paths for an agent editing the app's own source. Use when designing UI for agent editability, deciding whether a file is safe for the agent to change, or when tempted to patch config, `.env`, or an `@agent-native/*` package.…

原文语言：英语

shadcn-ui

The shadcn CLI, component composition, theming, and registry workflow. Use when adding, replacing, upgrading, or debugging a shadcn/ui primitive itself, or when changing a theme or registry. Do not load it for ordinary edits to a file that happens to import a…

原文语言：英语

sharing

Framework-level sharing and privacy for user-authored resources (dashboards, documents, forms, decks, etc.). Use when making a resource table ownable, wiring list/read/update access checks, or dropping the standard share dialog into a template.

原文语言：英语

upgrade-agent-native

Bring an older Agent Native app or workspace current. Use when updating @agent-native/core, fixing a broken upgrade, or when tempted to patch or override core/dispatch packages to make an old branch run.

原文语言：英语

visual-plan

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

原文语言：英语

visual-recap

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.

原文语言：英语

recording

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.

原文语言：英语

new-branch

Only when explicitly asked for /new-branch or a fresh git branch: stash local changes, update main, and create it. Do not auto-run for normal coding, PR, Builder.io, or Fusion branch workflows.

原文语言：英语

video-sharing

How Clips shares recordings — composes with the framework sharing skill and adds password, expiry, embed URLs, view-counting, and per-viewer "Viewed by" records. Use when wiring the share dialog, building embed links, adding a password, showing who viewed a…

原文语言：英语

customizing-agent-native

How to configure, compose, or eject Agent Native features into app-owned code. Use when overriding shared components or integrations, customizing a template, adding UI to chat or headless apps, or inspecting package source.

原文语言：英语

video-editing

Non-destructive video editing in Clips — the editsJson model, trim / split / cut / speed / blur, transcript-based editing, and ffmpeg.wasm export. Use when building the editor UI, adding a new edit operation, or wiring the export pipeline.

原文语言：英语

fix-at-the-boundary

How to find every sibling instance of a reported bug before fixing it. Use whenever a bug report names one file but the defect is a call pattern, hook, duplicated literal, or copy-pasted helper that plausibly exists in other files, apps, or templates.

原文语言：英语

factory-graphs

Design, inspect, and safely edit Factory graph versions. Use when a user asks to create a factory, change a node or route, explain an item path, or comment on the visual map.

原文语言：英语

secrets

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…

原文语言：英语

composable-mini-apps

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

原文语言：英语

dashboard-ops

Deployment and runtime internals for dashboard email reports and analytics alert rules: server-side SVG/PNG report rendering, serverless timing budgets, cron wiring, and notification delivery env vars. Use when configuring, deploying, or debugging…

原文语言：英语

analytics-data-for-decks

Route customer, account, CRM, HubSpot, pipeline, renewal, usage, product activity, Gong, and other analytics-backed deck requests through the Analytics agent. Use when generating or updating Slides content that needs external or first-party data.

原文语言：英语

content-product-development

Product contracts and proof boundaries for Agent Native Content. Use when planning, implementing, reviewing, testing, or documenting Content behavior or shared framework behavior that changes Content.

原文语言：英语

browser-sessions

Architecture for attaching Chrome page context and control to Agent Native conversations. Use when building browser capture, extension chat, browser control, or cross-app webpage workflows.

原文语言：英语

extension-points

How extensions render as widgets inside other apps via named UI slots — the framework's optional extension system. Use when an extension-enabled app needs to wire an ExtensionSlot or make an existing one-off custom block installable into a slot.

原文语言：英语

hubspot

Query HubSpot CRM for deals, companies, contacts, tickets, owners, and account/deal context. Use when the user asks for HubSpot data or connection status.

原文语言：英语

external-agents

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…

原文语言：英语

security

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.

原文语言：英语

responsive-breakpoints

Framer-style responsive breakpoint editing in Design: one DOM tree per screen with cascading width-scoped overrides. Use when adding/removing breakpoints, editing a design at a specific device width, resolving which value renders at a width, or persisting…

原文语言：英语

crm

How to run typed CRM work — attributes and options, lists and pipelines, saved and board views, provider proposals, duplicates and merge, gated enrichment, and evidence-grounded call signals. Use for any CRM read, write, setup, or provider question.

原文语言：英语

qa

Autonomous multi-app QA sweep that drives template apps with Playwright MCP. Use only when the user explicitly runs /qa or asks for an end-to-end QA sweep. Do not load it for ordinary feature work, single-page checks, or one-off bug fixes.

原文语言：英语

charts

Generate inline chart images (PNG) for embedding in chat responses. Use this skill when you need to create bar, line, or area charts for data visualization in chat.

原文语言：英语

a2a-assets

Use Assets from other apps or MCP hosts to generate, refine, export, and insert brand images or videos.

原文语言：英语

assets-navigation

Assets routes, tabs, chat surfaces, and `navigate` targets. Use when sending a user to a screen, interpreting navigation state, deciding which surface owns a workflow, or wiring chat into the Create tab or agent sidebar.

原文语言：英语

logo-composite

How the generate-then-composite pipeline puts a pixel-perfect canonical logo onto a generated image without letting the LLM regenerate the logo.

原文语言：英语

ai-video-tools

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.

原文语言：英语