cloudbase skill
✓ 検証済みデータベース、クラウド関数、ストレージ、組み込みAIモデルを含むTencent CloudBaseプロジェクトの開発、デプロイ、トラブルシューティングをエージェントで実行可能にします。
- GitHubスター
- 1,164
- ファイル
- 180
- 最終コミット
- 2026年11月11日
- ライセンス
- MIT
- 許可されたツール
- —
cloudbase skillは何をしますか
データベース、クラウド関数、ストレージ、組み込みAIモデルを含むTencent CloudBaseプロジェクトの開発、デプロイ、トラブルシューティングをエージェントで実行可能にします。
skillのSKILL.mdから生成された要約。
cloudbase skill について
WeChat Mini Program、Web/H5アプリケーション、またはFlutterやReact Nativeを使用したモバイルアプリを構築する開発者は、このSKILLを使用してTencent CloudBaseバックエンド全体を管理できます。NoSQLドキュメントデータベース、PostgreSQL、クラウド関数、クラウドストレージを含む、サーバーレス環境の設計、デプロイ、トラブルシューティングに必要なツールを提供します。このSKILLは、国内版または国際版のいずれかを使用しているCloudBaseエコシステム内で作業するユーザー向けに特別に設計されています。
エージェントがこのSKILLをロードすると、フロントエンドのコードを記述する前に、認証プロバイダー、セキュリティルール、データベーステーブルなどのバックエンドリソースを準備できます。環境IDを解決するためのqueryEnvや、アプリケーションをデプロイするためのmanageAppsなど、環境管理のための特定のツールに依存しています。また、統合されたAI機能もサポートしており、HunyuanやDeepSeekなどの組み込みプロバイダーを通じて、モデルの作成やストリーミングテキスト、画像生成を利用できます。これは、バックエンドを自前サーバーではなくCloudBaseにホストするフルスタック開発ワークフローを対象としています。
エージェントができること
- 1Webアプリケーションのデプロイエージェントは、特定のデプロイアクションを使用して、CloudBaseサービスにフロントエンドアプリケーションをデプロイできます。
- 2データベースリソースのセットアップ開発者は、フロントエンドのロジックを記述する前に、NoSQLコレクションやPostgreSQLデータベースを準備するようAIに指示できます。
- 3組み込みAIモデルの統合テキストまたは画像タスクに対して、特定のプロバイダーグループ名を使用してAIモデルを作成するようエージェントにタスクを割り当てることができます。
- 4クラウド運用のトラブルシューティングエージェントは、CloudBase環境内の問題を解決するために、検査や診断を実行できます。
skill の SKILL.md から作成されています。すべてのユースケースは、その引用と照合されています。
cloudbase skillのインストール方法
各コマンドはskillフォルダをクライアントのskillsディレクトリにコピーします。読み込むには、クライアントを再起動するか新しいセッションを開始してください。Claude Codeにcloudbase skillをインストールする
~/.claude/skills/cloudbase/SKILL.md
$ npx degit TencentCloudBase/CloudBase-AI-Toolkit/connectors/cloudbase-intl/skills ~/.claude/skills/cloudbaseClaude Code (project)にcloudbase skillをインストールする
.claude/skills/cloudbase/SKILL.md
$ npx degit TencentCloudBase/CloudBase-AI-Toolkit/connectors/cloudbase-intl/skills .claude/skills/cloudbaseCodexにcloudbase skillをインストールする
~/.agents/skills/cloudbase/SKILL.md
$ npx degit TencentCloudBase/CloudBase-AI-Toolkit/connectors/cloudbase-intl/skills ~/.agents/skills/cloudbaseGemini CLIにcloudbase skillをインストールする
~/.gemini/skills/cloudbase/SKILL.md
$ npx degit TencentCloudBase/CloudBase-AI-Toolkit/connectors/cloudbase-intl/skills ~/.gemini/skills/cloudbaseClaude.aiにcloudbase skillをインストールする
npx degit TencentCloudBase/CloudBase-AI-Toolkit/connectors/cloudbase-intl/skills cloudbase && zip -r cloudbase.zip cloudbase # claude.ai → Customize → Skills → + → Create skill → Upload a skill → cloudbase.zip
自動チェック
実行日 2026年11月15日完全なレポート →自動チェックに合格しました。これはセキュリティ監査ではありません。エージェントに実行させる前にスクリプトを読んでください。 チェックの仕組み · 点数を上げるための改善点
- ソースリポジトリがリンクされており、アクセス可能tencentcloudbase/cloudbase-ai-toolkit/connectors/cloudbase-intl/skills is public and reachablegithub.com/tencentcloudbase/cloudbase-ai-toolkit/tree/HEAD/c ↗合格
- オープンソースライセンス (OSI)MITspdx.org/licenses/MIT.html ↗合格
- 過去1年以内にコミットまたはリリースありLast commit 2026-11-11github.com/tencentcloudbase/cloudbase-ai-toolkit/commits ↗合格
- スクリプトにダウンロード実行や認証情報の窃取がないNo scripts in the skill folder合格
- SKILL.md に隠れた指示がないNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/tencentcloudbase/cloudbase-ai-toolkit/blob/HEAD/c ↗合格
- 事前許可ツールが限定されているNo pre-approved tools; the agent asks before using onegithub.com/tencentcloudbase/cloudbase-ai-toolkit/blob/HEAD/c ↗合格
- SKILL.md が Agent Skills の形式に従っているname "cloudbase" differs from the folder "skills"github.com/tencentcloudbase/cloudbase-ai-toolkit/blob/HEAD/c ↗検出事項
SKILL.md
GitHubで表示CloudBase Development Guidelines
📁 Reference Files Location
All reference documentation files are located in the references/ directory relative to this file.
File Structure:
cloudbase/
├── SKILL.md # This file (main entry)
└── references/ # All reference documentation
├── auth-web-cloudbase/SKILL.md # Web authentication guide
├── auth-wechat-miniprogram/SKILL.md # WeChat authentication guide
├── cloudbase-document-database-web-sdk/SKILL.md # NoSQL database for Web
├── ui-design/ # UI design guidelines
└── ... # Other reference docs
How to use: When this document mentions reading a reference file like references/auth-web-cloudbase/SKILL.md, simply read that file from the references/ subdirectory.
Step 0 — Confirm the site (domestic vs international)
CloudBase has two independent account systems: 国内站 (domestic, cloud.tencent.com) and 国际站 (international, tencentcloud.com). Environments, consoles, API keys, and login state do not cross over. A wrong-site login usually looks like "logged in, but no environments visible" rather than a clear error — so settle the site before installing MCP, logging in, or binding an env.
Infer it when you can (console domain, envId, an existing error); otherwise ask the user once. Do not guess.
| 国内站 domestic | 国际站 international | |
|---|---|---|
| Remote MCP (preferred) | https://tcb-api.cloud.tencent.com/mcp/v1 |
https://tcb-api.tencentcloud.com/mcp/v1 |
| Local stdio MCP | nothing to set (TCB_SITE is domestic by default) |
TCB_SITE=intl + TCB_REGION=ap-singapore |
tcb CLI |
default | TCB_IS_INTL=true (or tcb config set isIntl true) |
Project record .cloudbase/project.json |
site omitted, or "domestic" |
"site": "intl", "region": "ap-singapore" |
| Console | tcb.tencentcloud.com |
tcb.tencentcloud.com |
| Default region | ap-shanghai |
ap-singapore |
| NoSQL / document DB tools | available | not available |
- Connect remote by default. Both hosts are first-class endpoints: OAuth covers the login and the hostname decides the site, so there is no
siteparameter to pass. International:https://tcb-api.tencentcloud.com/mcp/v1; domestic:https://tcb-api.cloud.tencent.com/mcp/v1. - Use local stdio only when something requires it — an account signing in with a CloudBase API key, one session that must cover both sites (a remote URL is bound to one), or a task that needs a tool the hosted endpoint does not register. Deploying functions or apps is not a reason: that works remotely through the two-step upload. Comparison:
references/mcp-setup.md. TCB_IS_INTL(CLI) andTCB_SITE(MCP) are different variable names for different tools. Set the one matching the tool in use; setting the wrong one silently does nothing.- On a first run, settle the site once and persist it — the CLI switch is machine-global, the MCP switch is per-client, and only
.cloudbase/project.jsonis project-scoped and readable by MCP after a restart. Followreferences/site-onboarding.md; do not re-ask on later sessions.
Details and copy-paste configs: references/mcp-setup.md. CLI specifics: references/tooling-fallback.md. First-run orchestration (trigger/skip, conflict arbitration, MCP-down fallback): references/site-onboarding.md.
Step 0.1 — Decide the project type before installing anything
Read the project root, or the user's own words (e.g. "我主要做微信小程序开发"). A WeChat mini program has project.config.json plus app.json / miniprogram/app.json. For a mini program project, generic CloudBase setup only connects the backend — it does not let the agent open the simulator or preview the mini program. Route to miniprogram-development first, recommend configuring the 微信开发者工具 Skill (WeChat DevTools Skill), and verify the simulator preview before taking business requests. The mini program tutorial is not a fallback-only step.
International site (intl) — read first
This connector is bound to the CloudBase international site, whose accounts, environments,
and billing are separate from the China site. Before acting, read
references/international-site.md for the international console and gateway hosts, the
region to use, OAuth sign-in behaviour, and the capabilities that this site does not have.
Workflow
1. Exploration → Read the matching skill completely before writing any code.
Search with searchKnowledgeBase(mode="skill"), then Read full SKILL.md.
2. Implementation
├── 2a. Resource preparation → Prefer MCP; if MCP tools are missing in THIS session,
│ configure MCP for next session and use `tcb` CLI now (see tooling-fallback.md)
└── 2b. Frontend implementation → Write code, install deps, start server, test
3. Close-out → Run cloudbase-code-review, fix errors, declare done
(after a verified deploy: optionally offer Deployment Share once — see references/deployment-workflow.md §5)
Key constraints: Stage 2a must precede frontend code. Stage 3 is mandatory.
Activation Contract
Routing uses stable skill ids (auth-tool-cloudbase, auth-web-cloudbase, http-api-cloudbase, …) across source, generated artifacts, and installs.
Standalone skill fallback
If only one published skill is exposed:
- Prefer local relative paths (
references/<skill-id>/SKILL.mdor sibling skill directories) when those files exist in the workspace. - Do not fetch sibling skill markdown from remote raw URLs into the agent context.
- If a required sibling skill is missing locally, ask the user to install the full CloudBase skills pack or IDE plugin (
npx skills add tencentcloudbase/cloudbase-skills). When that fails becausegitis missing, use the tarball path inreferences/mcp-setup.md, then continue using local files only.
Follow relative references/... paths from the current skill. If MCP is unavailable in this session, follow references/tooling-fallback.md: configure MCP via references/mcp-setup.md for the next session, and use tcb CLI via the references/cloudbase-cli/SKILL.md skill (read core.md + the matching domain reference — not tcb deploy) to finish login/manage now. If npm/npx are missing, follow the “No npm/npx” section in tooling-fallback.md.
Global rules before action
- Identify the scenario, then read the matching skill before writing code or calling CloudBase APIs.
- Prefer semantic sources for toolkit maintenance; express runtime routing in stable skill ids.
- Prefer MCP or mcporter for management tasks when those tools are available in this session; inspect tool schemas before execution. If they are not available yet, do not stall — use the CLI fallback in
references/tooling-fallback.md. - Connecting MCP at all (local stdio versus remote), calling tools from the shell with mcporter, the site / region / plugin switches, or a fix to this open-source repo: read
cloudbase-mcp. - UI tasks: read
ui-designfirst and output the design spec before interface code. - Auth tasks: read
auth-tool-cloudbasefirst and enable providers before frontend implementation. - Keep auth domains separate: management login uses
auth(ortcb loginwhen MCP auth is unavailable); app-side auth usesqueryAppAuth/manageAppAuth.
Universal guardrails
- After 2–3 failed attempts on the same path, stop and reroute (platform skill, runtime, auth domain, permission model, SDK boundary).
- Always specify
EnvIdexplicitly; do not rely on CLI-selected or implicit env state. - When the environment identifier is an alias, nickname, or other short form, do not pass it directly to
auth.set_env, SDK init, console URLs, or generated config. First resolve it to the canonical fullEnvIdwithqueryEnv(action=list, alias=..., aliasExact=true). If multiple environments match or no exact alias exists, stop and clarify with the user. - When writing MCP/tool results to a file, pass serialized text (
JSON.stringify(result, null, 2)), not raw objects. If a write tool sayscontentexpected a string but received an object, do not retry with the same raw object. Serialize the object first, then retry once with the serialized text, and make sure the retried call actually passes the serialized string rather than the original object. - Keep scenario-specific pitfalls in child skills — do not expand this entry file.
- First frontend deploy must use
manageApps(action="deployApp", ...). There is nocreateApp/updateAppaction — first deploy and re-deploy both usedeployApp, and a re-deploy reuses the sameserviceName.manageHostingis only for incremental updates of projects originally deployed via hosting.
Engineering constitution (applies to every scenario)
These rules override convenience. Full rationale lives in web-development.
- Prepare backend resources before writing frontend code. Prefer MCP for auth providers, tables, storage domains, and security rules; if MCP tools are missing in this session, use
tcbCLI after configuring MCP for the next session (references/tooling-fallback.md). - Do NOT use
anyto bypass type errors. Preferunknown+ type guards / precise interfaces. - Self-verify before claiming done. Static (
tsc/ lint / build / tests) and runtime (agent-browserfor user-visible flows). Name gaps explicitly if a layer cannot run. - Do not paper over failures. No empty
try/catch, no deleting failing tests to go green. ai.createModel(...)/wx.cloud.extend.AI.createModel(provider)takes a GroupName, not a vendor/model id. Legal:"cloudbase","hunyuan-v3"(legacy plan group, onlyhy3, being retired),"hunyuan-exp"(older legacy builtin), or"custom-<name>". Model ids go ingenerateText/streamTextmodelfield. Seeai-model-web/ai-model-nodejs/ai-model-wechat.- Low-capability STOP card: For PostgreSQL / CloudBase PG /
app.rdb()/queryPgDatabase/managePgDatabase, route topostgresql-development-cloudbase— do not use NoSQL collection APIs or MySQL tools for that path. For Web auth guards, useauth.getSession()and requiredata.session; do not use deprecatedgetLoginState()/auth.getUser()as login proof.
High-priority routing
| Scenario | Read first | Then read | Do NOT route to first | Must check before action |
|---|---|---|---|---|
| Web login / registration / auth UI | auth-tool-cloudbase |
auth-web-cloudbase, web-development |
cloud-functions, http-api-cloudbase |
Provider status and publishable key |
| First-time mini program CloudBase onboarding | miniprogram-development |
cloudbase-platform |
auth-web-cloudbase, web-development |
Project type, DevTools Skill configured, simulator preview works |
| WeChat mini program + CloudBase | miniprogram-development |
auth-wechat-miniprogram, cloudbase-document-database-in-wechat-miniprogram |
auth-web-cloudbase, web-development |
Whether the project really uses CloudBase / wx.cloud |
| Native App / Flutter / React Native | http-api-cloudbase |
auth-tool-cloudbase, postgresql-development-cloudbase |
auth-web-cloudbase, cloudbase-document-database-web-sdk, web-development |
SDK boundary, OpenAPI, auth method |
| Web projects + NoSQL Database | web-development |
cloudbase-document-database-web-sdk, auth-web-cloudbase |
relational-database-mcp-cloudbase, http-api-cloudbase |
Login state and database access permission model |
| CloudBase PostgreSQL Best Practices | postgresql-best-practices-cloudbase |
postgresql-development-cloudbase |
cloudbase-document-database-web-sdk |
Access paths, index decisions, row authorization, and launch capacity |
| CloudBase PostgreSQL / PG | postgresql-development-cloudbase |
auth-tool-cloudbase, auth-web-cloudbase, web-development, miniprogram-development, cloud-storage-web, http-api-cloudbase |
relational-database-mcp-cloudbase, cloudbase-document-database-web-sdk |
PG schema, usernamePassword login, backend/RLS permission model |
| Existing MySQL (do not recommend) | relational-database-mcp-cloudbase |
relational-database-web-cloudbase |
cloudbase-document-database-web-sdk, web-development |
Environment already has MySQL; new relational work uses PostgreSQL |
| Cloud Functions | cloud-functions |
auth-tool-cloudbase, ai-model-nodejs |
cloudrun-development, auth-web-cloudbase |
Event vs HTTP function, runtime, scf_bootstrap |
| CloudRun backend | cloudrun-development |
auth-tool-cloudbase, postgresql-development-cloudbase |
cloud-functions |
Container boundary, Dockerfile, CORS |
| AI Agent (智能体开发) | cloudbase-agent |
cloud-functions, cloudrun-development |
cloud-functions, cloudrun-development |
AG-UI protocol, scf_bootstrap, SSE streaming |
| Minimal Web BaaS demo (fast path) | minimal-web-baas-demo |
web-development, cloudbase-document-database-web-sdk, postgresql-development-cloudbase |
cloud-functions, cloudrun-development, spec-workflow, ui-design |
BaaS-first Web SDK CRUD, MCP schema only, zero cloud functions unless secrets/cron/rules-cannot-express |
| UI generation | ui-design |
web-development, miniprogram-development |
cloud-functions |
Design specification first |
| AI Model (Web) | web-development |
ai-model-web, ui-design |
ai-model-wechat, http-api-cloudbase |
Platform and streaming interaction mode |
| AI model call (大模型调用 / 文本生成 / 图片生成 / 流式对话) | ai-model-web |
ai-model-nodejs, ai-model-wechat |
cloudbase-agent, cloud-functions, cloudrun-development |
先跑「调用前必须的资格检查」:DescribeActivityInfo(小程序成长计划) + DescribeEnvPostpayPackage(Token Credits 资源包) |
| Resource health inspection / troubleshooting | ops-inspector |
cloud-functions, cloudrun-development |
ui-design, spec-workflow |
CLS enabled, time range for logs |
| Spec workflow / architecture design | spec-workflow |
cloudbase |
web-development, cloud-functions |
Requirements, design, tasks confirmed |
Activation triggers (derived from references/activation-map.yaml)
- Web login / registration / auth UI — CloudBase Web 登录, Web 注册, auth login page, publishable key, 短信登录, 邮箱登录
- First-time mini program CloudBase onboarding — 我主要做微信小程序开发, 小程序接入云开发, 小程序首次接入, 帮我接入云开发,我主要做微信小程序开发, 配置微信开发者工具 Skill, 配置开发者工具 Skill, connect this mini program project to CloudBase, first-time mini program CloudBase onboarding
- WeChat mini program + CloudBase — 小程序 云开发, wx.cloud, mini program cloudbase, OPENID, 小程序数据库
- Native App / Flutter / React Native — Android CloudBase, iOS CloudBase, Flutter CloudBase, React Native CloudBase, 原生 App 接入
- Web projects + NoSQL Database — Web 文档数据库, CloudBase collection, 前端查库, NoSQL Web SDK
- CloudBase PostgreSQL Best Practices — PG access pattern, 数据库访问路径, N+1 查询, 批量查询, 慢查询, EXPLAIN ANALYZE, 缺索引, 活动数据库容量
- CloudBase PostgreSQL / PG — CloudBase PG, PostgreSQL, Postgres, PG 模式, JS SDK v3 PostgreSQL, app.rdb(), queryPgDatabase, managePgDatabase, mysqldb OpenAPI, PostgREST, RLS, service_role, auth schema, storage schema, pgvector, 关系型数据库, 建表
- Existing MySQL (do not recommend) — 已有 MySQL, 现有 MySQL 实例, queryMysqlDatabase, manageMysqlDatabase
- Cloud Functions — 创建云函数, HTTP 云函数, getFunctionLogs, scf_bootstrap, runtime
- CloudRun backend — CloudRun 部署, 云托管, container backend, Dockerfile
- AI Agent (智能体开发) — AI Agent, 智能体, 智能体开发, AG-UI protocol, LangGraph, LangChain, CrewAI, streaming agent, agent UI
- Minimal Web BaaS demo (fast path) — 最小前后端, 最小可用 demo, 最小 fullstack, 搭一套 demo, 带云数据库的 demo, 带云函数+云数据库, 留言板, Todo 应用, todo app, Notes app, Kanban, Lovable, BaaS demo, minimal web baas, 快速 demo
- UI generation — 设计页面, 登录页 UI, frontend interface, 组件样式, prototype
- AI Model (Web) — Web AI 对话, CloudBase AI 流式输出, Web 集成模型
- AI model call (大模型调用 / 文本生成 / 图片生成 / 流式对话) — 大模型调用, AI 模型调用, generateText, streamText, generateImage, 文本生成, 图片生成, 流式对话, hunyuan-exp, deepseek-v4-flash, Token Credits 资源包, 小程序成长计划, ai_miniprogram_inspire_plan, callCloudApi AI 模型, CreateAIModel
- Resource health inspection / troubleshooting — 巡检, 诊断, health check, 资源健康, 异常日志, error inspection, troubleshooting, 错误排查
- Spec workflow / architecture design — 需求文档, 技术方案, tasks.md, Spec 工作流
Routing reminders
- Web auth failures: usually skipped provider config, not missing frontend snippets.
- Native App failures: usually Web SDK paths, not missing HTTP API knowledge.
- Mini program failures: treating
wx.cloudlike Web auth/SDK. - New relational databases use PostgreSQL. MySQL skills apply only when the environment already has a MySQL instance.
- CloudBase PG failures: falling back to NoSQL or MySQL, skipping username-password readiness, or guessing raw HTTP instead of
app.rdb()/ documented OpenAPI. - AI model failures: usually missing Token Credits / Growth Plan — run
DescribeEnvPostpayPackage/DescribeActivityInfobefore changing code.
MCP + CLI prerequisite
Prefer CloudBase MCP for management/deploy when tools are loaded in the current session. Setup: references/mcp-setup.md. First-session / unavailable path: references/tooling-fallback.md.
- Preferred install:
npx plugins add TencentCloudBase/cloudbase-plugin -y --scope user. Supported--targetIDs:claude-code,cursor,codex,grok,kimi,github-copilot,vscode. Seereferences/mcp-setup.md. Whenplugins addfails withprogram not found, use the no-git tarball path in that file. - Verify with
npx mcporter list | grep cloudbaseor the IDE MCP panel. Ifnpm/npxare missing, seereferences/tooling-fallback.md(install Node LTS or use IDE marketplace MCP). If MCP is missing or not yet visible after config, still proceed: finish install/config, tell the user a restart unlocks MCP next time, and usetcbCLI now viacloudbase-clidomain skills — do not recommendtcb deploy. - Prefer device-code login via MCP
authwhen available; otherwisetcb login. Do not hard-code secrets.
On-demand references
Load only when needed (do not expand this entry):
references/tooling-fallback.md— MCP vstcbCLI decision tree for first session / missing toolsreferences/site-onboarding.md— first-run site onboarding: trigger/skip, persistence, conflict arbitration, MCP-down fallbackreferences/deployment-workflow.md— deploy backend/frontend,manageAppsvs hosting, URL/docs updates, optional post-deployment Deployment Share offer (§5)references/console-links.md— console hash paths after creating resourcesreferences/scenarios.md— user-need → CloudBase capability mappingreferences/mcp-setup.md— Plugin install (global default + targets), IDE MCP / mcporter config and auth examplesreferences/activation-map.yaml— canonical routing contract source
Reference index
All packaged reference files (required for skill lint reachability):
このスキルのファイル
180cloudbase skillに関する質問
Claude Codeにcloudbase skillをインストールするには
npx degit TencentCloudBase/CloudBase-AI-Toolkit/connectors/cloudbase-intl/skills ~/.claude/skills/cloudbaseを実行してください。Claude Codeは~/.claude/skills(すべてのプロジェクト)または.claude/skills(単一プロジェクト)からskillsを読み込み、説明がタスクに一致する場合にskillを使用します。
cloudbase skillはどのクライアントで使用できますか
Agent Skills形式を読み込むすべてのクライアントで使用できます: Claude Code、Codex、Gemini CLI、claude.ai(ZIPとしてアップロード)。skill内のスクリプトは、クライアントがコード実行を許可した場合にのみ実行されます。
CloudBaseのPostgreSQLデータベースにNoSQLツールを使用できますか?
いいえ、PostgreSQLやCloudBase PGに対してNoSQLコレクションAPIやMySQLツールを使用しないでください。代わりに、特定のpostgresql-development-cloudbaseパスへルーティングしてください。
完全なEnvIdではない環境識別子をどのように扱うべきですか?
エイリアスやニックネームを直接SDKやAPIに渡さないでください。まずqueryEnvツールを使用して、それらを正規の完全なEnvIdに解決する必要があります。