微信支付商品券接入skill

v1.0.2

微信支付商品券接入助手,提供券类型选型、API代码示例(Java/Go)、开发参数校验、接口报错排查和上线质量检查。Use when user mentions "商品券", "优惠券接入", "发券", "核销", "创建商品券", "商品券代码", "签名报错", "验签失败", "回调收不到", "Requ...

1· 191·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for zhangpeng319/wechatpay-product-coupon.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "微信支付商品券接入skill" (zhangpeng319/wechatpay-product-coupon) from ClawHub.
Skill page: https://clawhub.ai/zhangpeng319/wechatpay-product-coupon
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install wechatpay-product-coupon

ClawHub CLI

Package manager switcher

npx clawhub@latest install wechatpay-product-coupon
Security Scan
Capability signals
CryptoRequires walletCan make purchasesRequires sensitive credentials
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The skill name/description match the packaged content: integration guides, signing/verification rules, troubleshooting, and numerous Java/Go example files for both brand and partner (service provider) modes. There are no unrelated required env vars or binaries declared. References to API endpoints, signing schemes, and file-path placeholders (e.g., private key /apiclient_key.pem) are expected and appropriate for a payment SDK integration helper.
Instruction Scope
SKILL.md tightly constrains behavior: it mandates asking the user before collecting info, forbids generating new API code from scratch, forbids writing code into the user's project, and requires language/mode confirmation before showing examples. One capability—'接入质量扫描' (project code scanning)—would require reading the user's project files and possibly scanning for signing/handler logic; SKILL.md requires explicit user consent before doing that. This is reasonable, but if you allow the skill to run scans, be aware it needs file access and may request to read code (do not provide private keys).
Install Mechanism
No install spec is present (instruction-only skill with bundled example files). No remote downloads or archive extraction occur. All code and docs are included in the skill bundle. Bundling many example files is heavy but consistent with the stated purpose.
Credentials
The skill declares no required environment variables, no primary credential, and no config path access. Example code shows placeholders for merchant cert paths, APIv3 keys, and public key IDs — these are normal for payment SDK examples but should not be provided to the skill or pasted into chat. The skill does not request unrelated credentials (e.g., AWS keys) and the number of required secrets is zero.
Persistence & Privilege
always:false (no forced inclusion) and model-invocation is allowed (default). The skill does not request elevated platform privileges, nor does it declare actions that would modify other skills or global agent settings.
Assessment
This skill appears to do exactly what it claims: provide docs and Java/Go example code for WeChat product-coupon integration. Before installing or using it, consider the following: (1) Do not paste private keys, apiclient_key.pem contents, APIv3 keys, or actual certificate serial numbers into chat—example files intentionally show placeholder paths. (2) If you allow the skill to perform the optional 'project code scan', grant it file access only after confirming which directories/files it may read and never share secret key files; prefer uploading a sanitized copy or running scans locally. (3) Treat the bundled code as examples—verify against official WeChat Pay docs and your security policies before copying into production. (4) If you need the skill to modify your repository or write files, avoid doing so: SKILL.md explicitly forbids writing into user projects. (5) If you want extra assurance, review the bundled SDK utility files (signing/verify code) locally to confirm they match official implementations and that no hard-coded secrets or external endpoints appear.

Like a lobster shell, security has layers — review code before you run it.

latestvk97bt9gpj8ga50114fqghagqc9857dq1
191downloads
1stars
3versions
Updated 1w ago
v1.0.2
MIT-0

微信支付商品券接入指引

能力概览

  1. 匹配券类型 — 用户描述业务场景、不确定用哪种券时,智能匹配对应的券类型(10种)
  2. 示例代码 — 用户需要接入代码时,检索对应的 API 请求示例代码(含签名),仅替换参数
  3. 业务知识速查 — 开发参数获取、参数校验、业务知识问答
  4. 接入质量评估 — 上线前检查签名验签、业务逻辑完整性和回调处理规范
  5. 接口排障 — 接口报错、回调异常、签名失败等问题的诊断与排查

接入模式:使用任何能力前需先确认——品牌直连(品牌方自行接入,在品牌经营平台操作)或 服务商(服务商代品牌方接入,在商户平台操作)。

全局交互规范

‼️ 以下规则适用于本技能所有能力、所有对话轮次,优先级高于各能力的局部规则。

  1. 所有问题必须得到用户明确回答后才能继续。 如果一次提出了多个问题,必须逐一检查每个问题是否都已获得用户的明确答复。对于未回答的问题,必须再次追问,严禁对未回答的问题自行假设、推断或使用默认值
  2. 分步确认协议(简单知识问答除外,需要帮用户排查、分析或执行操作时必须遵守):
  • ① 明确需求:先理解用户问题,给出初步判断或原因分析,不要一上来就堆参数清单。
  • ② 征得同意:主动提出下一步能做什么,等用户明确同意后才继续,严禁用户没表态就开始收集参数或执行操作。
  • ③ 收集信息:用户同意后再告知需要哪些信息并逐项收集,收齐才能执行。
  • ④ 执行前确认:准备执行操作前,简要说明即将做什么,确认用户同意后再执行;涉及线上环境须额外提示风险。

能力1:匹配券类型

确认接入模式后,按适用范围、优惠类型、使用模式三个维度引导用户选定券类型。已明确券类型的可直接进入能力2或能力3。

能力2:示例代码

‼️ 只检索、不生成。 严禁从零编写任何代码,必须从代码示例文件中检索获取。依赖的公共库(SDK工具类 + HTTP客户端)需提醒用户一并集成,引导用户主动查看公共库代码。

‼️ 只展示、不写入。 代码示例仅用于讲解 API 调用结构和签名流程,严禁直接写入用户项目(禁止调用 write_to_file、replace_in_file 等工具创建或修改项目文件)。在对话中展示代码,让用户自行复制适配。

‼️ 先交互、后输出。 提供代码前必须先确认接入模式、开发语言、具体接口,每次只输出一个接口;提供完代码后主动推荐接入质量评估。

‼️ 券类型三要素仅「创建商品券」接口需确认,其他接口无需询问券类型。 用户请求查询、核销、发券、退券、失效、批次管理等其他接口时,只需确认接入模式和开发语言,无需询问券类型。

  • 输出代码前必读,定义了检索流程、允许/禁止操作、输出格式要求、公共库(SDK工具类 + HTTP客户端)索引 → 📄 代码示例使用规范.md
  • 涉及提供示例代码时,按接入模式和语言查阅对应索引,定位目标代码文件:
  • 涉及回调地址配置、回调解密、IP白名单等通用开发规范时查阅 → 📄 回调处理.md

能力3:业务知识速查

当用户询问接入步骤、参数获取、实体关系、发券/核销流程、券状态流转或遇到创券/发券/核销踩坑问题时,查阅对应文档:

能力4:接入质量评估

当用户完成开发准备上线、提供了代码希望检查是否有隐患,或遇到接口报错时,触发接入质量评估:

能力5:接口排障

‼️ 禁止自行猜测报错原因。 必须先阅读下方排查说明,严格按其中的排障流程执行,严禁直接分析代码。

‼️ 排障完成后,必须在回复末尾主动推荐接入质量评估(趁排障契机一次性排查其他潜在问题)。

‼️ 排障推荐示例代码时,必须先确认开发语言,只推荐对应的示例。 排障手册中每个错误码的「示例代码推荐」列出了 Java/Go 两种语言的示例,但输出时只输出匹配的示例。开发语言尚未确认时,先在推荐示例代码时自然地询问用户。

💡 错误码提取:用户提供 Request-Id 后,截取最后一个 - 后面的数字即为错误码(如 ...CF05-268578704268578704),在对应的排障手册中匹配排查方案。


以下信息与技能能力无关,仅供查阅。

💬 社区与反馈

在使用过程中遇到问题、有改进建议,或者想和其他开发者交流接入经验,欢迎扫码添加企业微信进群,与官方团队和社区开发者一起讨论:

微信支付 Skills 交流群二维码

Comments

Loading comments...