Token导航 LogoToken导航

Agent Skill · 研究检索

billing-setup(计费设置)

billing-setup 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

billing-setup 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为调用外部服务;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 24,581。

总安装 3,975周安装 164GitHub Stars 1下载 1,299核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:billing-setup(计费设置)
来源仓库:https://github.com/credyt/ai-skills
仓库路径:skills/billing-setup
安装命令:
npx skills add https://github.com/credyt/ai-skills --skill billing-setup
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/credyt/ai-skills --skill billing-setup

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

billing-setup 引导用户配置 Credyt 计费模型,包括产品、定价与资产设置。支持多次运行以增改产品,自动验证完整计费周期。通过 npx skills add 安装,先调用 list_assets 和 list_products 查看现状。需用户提供业务语义与价格结构,避免凭空假设字段含义。

生产变更前建议在沙箱环境测试,确认扣费与通知链路正常。

来源仓库内路径:skills/billing-setup

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/credyt/ai-skills --skill billing-setup;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要调用外部服务,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

billing-setup 怎么安装?

在终端执行 npx skills add https://github.com/credyt/ai-skills --skill billing-setup。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

billing-setup 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

billing-setup 需要什么权限?

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

billing-setup 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

billing-setup 用的人多吗?

公开数据是累计安装 3,975 次,近一周安装 164 次,下载 1,299 次,GitHub 1 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

billing-setup 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
billing-setup

计费设置 · 本页

3,9751调用外部服务未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Credyt Setup

Guide the user through understanding their billing model, then configure everything in Credyt via MCP tools, then automatically verify the full billing cycle end-to-end. This skill can be run multiple times — to add new products, change pricing, or set up additional assets.

First: Check what already exists

Before jumping into discovery, check the current state by calling credyt:list_assets and credyt:list_products.

If they already have products configured, acknowledge what's there:

"I can see you already have [X] set up. Are you looking to add something new, change existing pricing, or start fresh?"

If they want to start fresh, do not archive or delete existing products. Leave them as-is. The user can manage existing products conversationally at any time (e.g. "archive the Pro product", "delete this product") — never do this automatically.

If this is their first time, proceed with full discovery.

Discovery: Understand their business

Ask questions one at a time. Listen to each answer before asking the next. Adapt follow-ups based on what they tell you. This is a conversation, not a form.

What does your app do?

"Tell me about your app — what does it do, and what are the main things your users do in it?"

Ground every follow-up question in their specific app and activities.

What costs you money?

"Which of those activities cost you money to provide? For example, if you're calling an AI model, each call has a cost. What are the expensive parts?"

This identifies the billable events — the activities they'll track and eventually charge for.

How do you want to charge?

Help them pick between three approaches. Explain each using examples from *their* app, not abstract concepts:

  • Pay-as-you-go (prepaid wallet): Users add funds. Each activity deducts from their balance. When it runs out, they top up or service pauses. This is how OpenAI and Replicate work.
  • Monthly subscription: Flat monthly fee regardless of usage. Classic SaaS model, like Netflix. Good if they're still figuring out pricing or want predictable revenue.
  • Hybrid (subscription + credits): Monthly fee that includes a credit allowance. Extra usage costs more. This is how Cursor and Clay work.

It's OK not to know yet

If they're unsure about pricing, guide them to track first and price later:

"No problem — you don't need to decide on pricing now. We can start tracking all the meaningful activities in your app and what they cost you. Credyt will show you your unit economics, and you can set pricing based on real data."

For this path: set up products with zero or placeholder prices, and emphasize attaching costs to events.

Dollars or credits?

"Do you want your users to see prices in dollars (like '$2.50 per video') or in your own currency like credits or tokens (like '10 credits per video')?"

Credits make sense when: costs vary behind the scenes, users aren't technical, you want users to earn credits, or you might adjust pricing later.

Dollars make sense when: costs are fixed per activity, users are developers, you want full transparency.

If unsure, suggest credits — more flexibility to adjust later.

Does pricing vary?

"Does the cost change depending on anything? Like a higher-quality output costing more, or a different AI model being pricier?"

If yes, get the specifics. These become pricing dimensions in Credyt.

Discovery checkpoint

Before configuring, confirm you understand:

  • What the app does and what activities matter
  • Which activities cost them money
  • Billing approach (pay-as-you-go, subscription, hybrid, or tracking first)
  • Dollars or custom currency
  • Whether pricing varies by any dimensions

If anything is unclear, ask. Don't proceed until discovery is complete.

Configure via MCP

Walk the user through each step. Before executing any MCP call that creates or modifies data, show the user a table of the intended parameters and get explicit confirmation:

"I'm going to create [X] with these settings — does everything look right?" | Field | Value | | --- | --- | | ... | ... | "Let me know if you'd like to change anything before I proceed."

This applies to every mutation: creating assets, products, vendors, versions, and adjustments. Never assume values the user hasn't confirmed — especially precision, pricing, and event types.

Create a custom currency (if using credits/tokens/coins)

Only if they chose a custom currency. This must be created before any products that use it.

Use credyt:create_asset. Verify precision explicitly — credits are typically whole numbers (precision 0) but this must be confirmed. For example:

| Field | Value | | --- | --- | | Name | Credits | | Code | credits | | Precision | 0 (whole credits, no fractions) | | Exchange rate | 1 credit = $0.05 → $1 buys 20 credits |

Explain the conversion in concrete terms so the user can verify it makes sense:

After creating, use credyt:quote_asset to verify the conversion. Quote how many units $1, $10, and $50 would buy:

"Let me verify that... ✓ $1 buys 20 credits, $10 buys 200, $50 buys 1,000. Does that look right?"

If the conversion is wrong, use credyt:add_asset_rate to correct it and re-quote.

Create products with pricing

Use credyt:create_product for each billable activity. For example:

| Field | Value | | --- | --- | | Name | Image Generation | | Code | image_gen | | Event type | image_generated | | Usage type | unit | | Price | 10 credits per event |

Key fields to confirm with the user:

  • Product name and code: What this billing item is called and its identifier
  • Event type: The activity name that triggers billing (e.g., "image_generated") — must match exactly what the app will send
  • Usage type: Per occurrence ("unit") or based on a quantity like tokens ("volume")
  • Pricing: How much each event costs

For "tracking first", set price to zero and make that explicit in the table.

A product can have both a fixed recurring price and a usage-based real-time price. For example, a $20/month subscription that also charges 1 credit per AI job is a single product with two prices — a recurring USD price and a per-event credit price. By default, use a single product with multiple prices; only create separate products if the user specifically wants them.

To update pricing on an existing product, always create a new version using credyt:create_product_version — never create a new product. This preserves billing history and keeps customers on their existing subscription. Show the same confirmation table before creating a version.

After creating or updating every product, use credyt:simulate_usage to validate. Always specify the product version explicitly in the simulation (e.g., version: 1) rather than relying on the default — this ensures you're testing what you just configured:

"Let me test this — one image generation should cost 10 credits... ✓ Confirmed: 10 credits deducted, that's $0.50. Does that match what you expected?"

If the simulation doesn't match, create a new product version with credyt:create_product_version using the corrected pricing and re-simulate until it's right. Confirm the new version parameters in a table before creating it.

Note on version changes: After creating a new product version, any existing test customers will still be subscribed to the old version. Either create a new test customer subscribed to the new version, or update the existing customer's subscription before running verification.

Included credits (entitlements)

If the billing model includes credits bundled into a subscription (e.g., "$20/month includes 1,000 credits"), those are configured as entitlements at the product level — not as a negative price or a separate product.

Include an entitlements array in the create_product (or create_product_version) call. For example, a product that grants 1,000 credits per day:

"entitlements": [
  {
    "name": "Daily Credit Allowance",
    "asset": "{assetCode}",
    "amount": 1000,
    "purpose": "bundled",
    "refresh": {
      "interval": "day",
      "strategy": "expire_and_replace"
    },
    "accounting": {
      "revenue_basis": 0.00,
      "cost_basis": "auto"
    }
  }
]

Confirm the entitlement fields (name, asset, amount, refresh interval) with the user before creating, using the standard parameter table.

Do not attempt to model included credits as a negative fixed price — this fails validation and isn't the correct approach.

Set up cost tracking (prompt for this)

Before verification, ask if they want to track what activities cost them:

"Do you want to track what each activity actually costs you? For example, if generating an image costs you $0.03 in API fees, Credyt can record that alongside the revenue so you can see your margins in real time."

If yes, create vendors with credyt:create_vendor for each service provider (OpenAI, Anthropic, AWS, etc.):

"You mentioned you're using OpenAI for image generation — I'll register them as a cost provider so we can track those costs."

Explain that when they send usage events from their app, they'll include a costs array with the vendor and amount. Credyt then calculates profit automatically.

If no, that's fine — they can add cost tracking later.

Verify the configuration

After all products are configured, automatically run a full billing cycle test. Don't ask — just do it.

"Now let me verify everything works end-to-end by running a test billing cycle..."

Run the verification against each product that was created or modified in this session. For each product, follow the six-step procedure in skills/billing-verification/references/procedure.md.

If any step fails, explain what went wrong and help fix it, then re-run the verification for that product.

"The test customer will stay in your account — since you're in test mode, this won't affect anything."

Wrap up

Summarize what was created and verified, then suggest next steps:

"Here's what's set up and verified in Credyt: - [List assets created] - [List products with pricing summary and verification status] - [List vendors if created] Run /credyt:billing-integration when you're ready to wire this into your app, or /credyt:billing-setup again to add more products."

平台分布

Codex

37.78%
按下载量换算491

Claude

31.86%
按下载量换算414

Cursor

18.87%
按下载量换算245

Gemini CLI

9.06%
按下载量换算118

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills