agent

作者 talivia-group已验证

Revenue-first website analytics installed and verified by AI agents through MCP

58
Stars
0
Forks
JavaScript
语言
2026/8/24
添加时间

⚠️ 第三方软件声明

本 Skill 为第三方开源软件,独立托管于 GitHub。SkillTip 仅为信息目录,不控制或维护底层仓库。所显示的安全检查为自动化且范围有限,安装前请自行审查源码。

阅读服务条款

安装

添加到你的 Claude Code skills 目录:

# Add to your Claude Code skills
git clone https://github.com/talivia-group/agent

快速入门

使用 agent 等 Skills 的指南。

安全报告

已验证

上次扫描:—

{
  "status": "PASSED",
  "issues": []
}

README.md

Talivia revenue-first analytics dashboard showing visitors, revenue, conversion rate, traffic sources, and customer geography

Talivia Agent Kit

Revenue-first website analytics that your AI agent can install, connect, and verify for you.

Talivia shows founders which referrers, campaigns, pages, search keywords, and customer journeys turn visits into revenue. @talivia/agent connects Codex, Claude Code, ChatGPT, OpenClaw, Hermes, and other MCP clients to Talivia so an agent can finish the analytics setup inside your project - not just paste a tracking snippet and hope it works.

Ask your agent to set up Talivia. It can find or create the right website, generate a framework-specific installation plan, add the tracker with its native coding tools, verify that real events are arriving, open a secure payment-provider handoff, and check that revenue attribution is ready.

Start free | Agent Kit | Documentation | npm | GitHub

See which traffic becomes revenue

Most analytics products count visits. Payment dashboards count transactions. Talivia connects the two, so you can answer the questions that matter to a growing product:

  • Which referrers, campaigns, and search keywords bring paying customers?
  • Which landing pages and customer journeys lead to a purchase?
  • How do visitors, conversion rate, revenue per visitor, and revenue change together?
  • Which tracked session produced an individual payment?
  • Is analytics and checkout attribution actually working in production?

Talivia puts traffic, visitor journeys, events, payment revenue, and attribution in one workspace. Connect a supported payment provider or use the Manual Payment API for a custom checkout.

From one prompt to verified analytics

Give this to a coding agent after connecting Talivia:

Set up Talivia revenue analytics for this project.

1. Connect to my Talivia account and find the correct website.
2. If it does not exist, ask before creating it.
3. Install the Talivia tracker using the right plan for this framework.
4. Build and test the project.
5. Verify that Talivia is receiving real events.
6. Help me connect revenue attribution through Talivia's secure browser flow.
7. Tell me what is working and what still needs attention.

The agent works in your repository. Talivia supplies the exact tracking configuration, secure account workflows, and live verification. Setup is not considered complete merely because code was generated - it is complete when Talivia receives real data.

Why founders and developers use it

  • Revenue-first analytics: follow traffic all the way from source and session to payment.
  • Less integration work: let an agent navigate the tracker, framework, and checkout setup instead of jumping between documentation pages.
  • Real verification: check live ingestion and revenue readiness before declaring the task complete.
  • Framework-aware setup: get an installation plan for Next.js, React/Vite, Astro, or plain HTML.
  • One account connection: use the same Talivia MCP connection across every website in your account.
  • Secure handoffs: approve access and connect payment providers in Talivia's browser UI, not in chat.

Use it for a SaaS launch, indie product, marketing site, developer tool, or any web product where knowing which traffic creates revenue matters more than collecting another pageview count.

Connect Talivia to an AI agent

MCP endpoint

Use the hosted website analytics MCP server when your client supports HTTP MCP and OAuth:

https://talivia.com/mcp

Codex:

codex mcp add talivia --url https://talivia.com/mcp
codex mcp login talivia

Claude Code:

claude mcp add --transport http talivia https://talivia.com/mcp

Talivia opens in your browser for sign-in and permission approval. After that, ask the agent to install or verify Talivia in your project.

npm package

Use the package when an agent expects a local stdio MCP server:

npx -y @talivia/agent setup --agent codex
npx -y @talivia/agent checkin --agent codex
codex mcp add talivia -- npx -y @talivia/agent mcp

Check the connection at any time:

npx -y @talivia/agent status

The package also includes a Codex plugin manifest and SKILL.md, so compatible agents can discover both the Talivia MCP server and the safe setup workflow.

What the agent can do

AreaOutcome
AccountCheck the connected Talivia account and available capabilities
WebsitesList existing websites or create one after user approval
TrackingGet the exact tracker and a framework-specific installation plan
VerificationConfirm that real analytics events are reaching Talivia
RevenueStart a secure payment connection and check attribution readiness
CheckoutGet provider-specific guidance for preserving visitor and session attribution

Talivia keeps the product logic on the hosted MCP server, so agents receive the current setup rules without bundling a second analytics implementation into your codebase.

Safe by design

  • Talivia authentication and consent happen in your browser.
  • MCP access is scoped to the permissions you approve.
  • Website permissions are checked on every website-specific action.
  • Payment-provider secrets are never requested through chat or MCP tool arguments.
  • Connections can be reviewed and revoked in Talivia Settings.

Prefer to self-host? Talivia also has an open-source version for running revenue analytics on your own infrastructure. Talivia Cloud provides the managed service and agent connection described here.

Start with your own traffic

Create a Talivia account, connect an agent, and follow the next visit all the way to the payment.

常见问题

What is agent?

agent is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by talivia-group. Revenue-first website analytics installed and verified by AI agents through MCP. It has 58 GitHub stars.

Is agent safe to use?

Yes. agent passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install agent?

Clone the repository with "git clone https://github.com/talivia-group/agent" and add it to your Claude Code skills directory (see the Installation section above). agent ships a SKILL.md manifest, so compatible agents can discover and load it automatically.

What programming language is agent written in?

agent is primarily written in JavaScript. It is open-source under talivia-group on GitHub, so you can review or fork the full source.

Are there alternatives to agent?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh agent against similar tools.

评论 (0)

暂无评论,成为第一个分享想法的人!

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情

claude-code

by anthropics

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

120,03119,897Shell
AI 智能体
查看详情

开发者还喜欢

基于喜欢此 Skill 的开发者投票和收藏

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

n8n

by n8n-io

12

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

201,88160,308TypeScript
MCP 服务器apisai-tools
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情