Skills ai-model-wechat

📦

ai-model-wechat

Name: ai-model-wechat
Author: tencentcloudbase

v2.23.8 Content revision r1 Safe ⚙️ External commands🌐 Network access

建置微信小程式 AI 呼叫

微信小程式 AI 設定在 provider、計費與串流方面有差異，容易設定錯誤。此技能會引導 Claude、Codex 或 Claude Code 完成 CloudBase 前置檢查與 wx.cloud.extend.AI 使用方式。

Supports: Claude Codex Code(CC)

🥈 80 Silver

Maintain this Skill? Claim it 🥈 80 Silver

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "ai-model-wechat" from https://skillstore.io/skills/tencentcloudbase-ai-model-wechat.md and its manifest at https://skillstore.io/api/skills/tencentcloudbase-ai-model-wechat/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/tencentcloudbase-ai-model-wechat.md Signed manifest GET /api/skills/tencentcloudbase-ai-model-wechat/manifest Signed lockfile GET /api/skills/tencentcloudbase-ai-model-wechat/lockfile

Test it

Using "ai-model-wechat". 我想在微信小程式中使用預設 AI 文字生成。

Expected outcome:

此技能會返回設定順序：確認環境存取、檢查 Growth Plan 或 Token Credits 資格、驗證模型就緒狀態，然後加入 generateText 呼叫。

Using "ai-model-wechat". 我的 streamText 呼叫返回參數錯誤。

Expected outcome:

此技能會識別小程式參數包裝差異，並檢查回呼處理、完成事件與模型群組就緒狀態。

Using "ai-model-wechat". 我需要使用私有模型端點。

Expected outcome:

此技能會概述控制台或 Cloud API 導入流程，建議自訂群組名稱，並避免將 API keys 放入小程式程式碼中。

Security Audit

Safe

v2 • 7/9/2026 Open versioned report

Static analysis reported shell execution, hardcoded URLs, and system reconnaissance patterns. Manual review found documentation text, markdown code examples, CloudBase setup links, and model identifiers only; no prompt injection, credential exfiltration, or hidden execution evidence was found.

Files scanned

449

Lines analyzed

Review items

False positives ignored

Risk Factors

⚙️ External commands (50)

🌐 Network access (8)

SKILL.md:12 SKILL.md:13 SKILL.md:99 SKILL.md:118 SKILL.md:137 SKILL.md:218 SKILL.md:234 SKILL.md:439

No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/tencentcloudbase-ai-model-wechat/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/tencentcloudbase-ai-model-wechat/security.svg)](https://skillstore.io/skills/tencentcloudbase-ai-model-wechat?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/tencentcloudbase-ai-model-wechat?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/tencentcloudbase-ai-model-wechat/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/tencentcloudbase-ai-model-wechat.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

tencentcloudbase. (2026). ai-model-wechat security audit report (audit version 2) [Author version 2.23.8]. Skillstore. https://skillstore.io/skills/tencentcloudbase-ai-model-wechat/audits/2

BibTeX citation

@techreport{tencentcloudbase-tencentcloudbase-ai-model-wechat-2026,
  author = {tencentcloudbase},
  title = {ai-model-wechat security audit report (audit version 2)},
  institution = {Skillstore},
  year = {2026},
  number = {2},
  url = {https://skillstore.io/skills/tencentcloudbase-ai-model-wechat/audits/2},
  note = {Author version 2.23.8}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "ai-model-wechat security audit report (audit version 2)"
version: "2.23.8"
type: report
authors:
  - name: "tencentcloudbase"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/tencentcloudbase-ai-model-wechat/audits/2"
identifiers:
  - type: other
    value: "skillstore:tencentcloudbase-ai-model-wechat:audit:2"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

100

Maintainability

Content

Community

Spec Compliance

What You Can Build

為小程式加入 AI 聊天

使用此技能規劃 CloudBase AI 設定，並以正確的微信小程式 API 形式加入文字生成。

發布前準備模型存取

使用前置檢查指引，在發布前確認計費資格、模型群組就緒狀態與已啟用的模型選項。

連接自訂模型群組

當受管理的 CloudBase 目錄模型無法滿足專案需求時，使用自訂導入流程。

Try These Prompts

確認基本設定

我正在為微信小程式加入 AI 文字生成。在撰寫程式碼之前，請檢查必要的 CloudBase 設定步驟。

實作串流聊天

協助我在微信小程式中使用 wx.cloud.extend.AI 與回呼加入串流聊天回應。

啟用受管理模型

引導我檢查 CloudBase 受管理模型是否已啟用，包括定價與就緒狀態考量。

導入自訂端點

我需要使用第三方或自託管模型端點。請規劃自訂 CloudBase 模型群組設定與小程式整合。

Best Practices

在檢查模型群組就緒狀態之前，先執行計費資格檢查。
使用 cloudbase 或 hunyuan-exp 作為 provider，然後將具體模型 ID 放入 model 欄位。
在啟用或變更 CloudBase AI 模型之前，先驗證模型可用性與定價。

Avoid

將供應商名稱用作 createModel providers。
在撰寫業務程式碼之前跳過計費與模型就緒狀態檢查。
在小程式程式碼中硬編碼第三方 API keys。

Frequently Asked Questions

此技能可以用於 Web App 嗎？

不可以。它是為使用 wx.cloud.extend.AI 的微信小程式撰寫的。

它會自動選擇模型 provider 嗎？

它會說明決策路徑。在選擇 cloudbase、hunyuan-exp 或自訂群組之前，你仍需要進行環境檢查。

streamText 的運作方式和 Node SDK 一樣嗎？

不會。小程式 streamText 需要 data 包裝器，並支援 onText、onEvent 與 onFinish 等回呼。

它可以協助自訂模型端點嗎？

可以。它會描述 CloudBase 自訂模型群組，並將端點密鑰保留在 CloudBase 端。

它會處理圖片生成嗎？

不會。此技能說明圖片生成無法透過這個小程式流程使用。

需要哪些權限？

你需要目標 CloudBase 環境的存取權限，以及查詢或更新 AI 模型設定的權限。

Developer Details

Author

tencentcloudbase

License

MIT

Author version

v2.23.8

Skillstore revision

Repository

https://github.com/tencentcloudbase/skills/tree/main/skills/ai-model-wechat

Ref

24b2fe42a456262f3fd0fb3df72e12d9ed2c32ec

Maintenance freshness

7/18/2026

Usage

2 downloads · 0 views

File structure

📄 SKILL.md