Loading pattern preview
BlocksReal-world Examples
Marketing agent with skills + readFile
Marketing agent with skills + readFile
Chat UI wired to a ToolLoopAgent that loads filesystem skills and exposes readFile on the skill sandbox—demo includes ad-creative, copywriting, and paid-ads skill packs for campaign workflows.
Loading pattern preview
Problems solved
Technical challenges this implementation handles out of the box.
- Load filesystem skill packs into a ToolLoopAgent
- Read skill reference docs through a sandboxed readFile tool
- Run marketing workflows with ad-creative, copywriting, and paid-ads skills
- Stream the skill-driven agent through an AI Elements chat UI
Use cases
Products and workflows this pattern is designed to support.
- Marketing ops copilots
- Skill-pack-driven campaign agents
- Sandbox reference lookup from chat
- Teaching skill + readFile agent wiring
Compare with
Similar patterns, and when each one is the better fit.
Just Bash Skills AgentUse this when an ops or on-call assistant should load markdown runbooks and checklists from disk as skills, using only a skill tool and readFile.
Tool ExecutionUse this when your chat app calls tools and you want each call's input, output, and status rendered inline as it streams.
Marketing Plan & Implement AgentUse this when your agent must capture brand details from a URL or form, get a todo plan approved, then carry it out with scraping and research tools.
Spreadsheet AgentUse this when users need a multi-sheet .xlsx with cleaned data, a chart, a summary, and a log of every transform the agent applied.
Setup
Requirements, wiring steps, and what this pattern adds to your project.
Getting started
Pick how you want to pull this pattern in. Then wire env vars and routes the same way.
- 1
Download → Next.js app
Use Download → Next.js app in the preview toolbar. You get a zip scaffold (Pro downloads rewrite preview `/view/.../api/*` paths to `/api/*` automatically).
- 2
Extract the zip and install dependencies
Unzip the archive, then run `pnpm install` (or npm / yarn) in the project folder.
- 3
Fill .env.local
The download includes .env.local placeholders when needed. Add real values for: AI_GATEWAY_API_KEY.
- 4
Customize the agent and tool files
Adapt prompts, tools, and stop conditions in the generated project for your product.
- 5
Run the app and open the pattern route
Run `pnpm dev`, open the setup/checklist page if present, then navigate to the generated pattern route and verify responses.
Environment variables
AI_GATEWAY_API_KEYGet key
Capabilities
AI SDK APIs
ToolLoopAgentcreateAgentUIStreamResponsegatewaystepCountIsProviders
Claude
Files added
18 files
app/page.tsxapp/layout.tsxapp/api/chat/route.tsapp/api/chat/skills-directory.tscomponents/chat-form.tsxapp/skills/ad-creative/SKILL.mdapp/skills/ad-creative/references/google-ads.mdapp/skills/ad-creative/references/linkedin-ads.mdapp/skills/ad-creative/references/meta-ads.mdapp/skills/ad-creative/references/platform-specs.mdapp/skills/ad-creative/references/tiktok-ads.mdapp/skills/copywriting/SKILL.mdapp/skills/copywriting/references/copy-frameworks.mdapp/skills/copywriting/references/natural-transitions.mdapp/skills/paid-ads/SKILL.mdapp/skills/paid-ads/references/ad-copy-templates.mdapp/skills/paid-ads/references/audience-targeting.mdapp/skills/paid-ads/references/platform-setup-checklists.md
Dependencies
8 total
npm packages
5AISDKbash-toollucide-reactNext.jsReact
Registry components
emptyscroll-areatooltip
Critical files
1 file
chat/route.tsCreates ToolLoopAgent with gateway model, createSkillTool from app/skills, createBashTool for sandbox file upload — exposes skill + readFile tools only (no bash); streams via createAgentUIStreamResponse.
Requirements
- Complexity
- Intermediate
- Setup time
- ~15 minutes
- Node
- 24+
- Memory
- 512MB
bash-tool runtime
