CtrlK
BlogDocsLog inGet started
Tessl Logo

cloudbase

Use this skill when you develop, design, build, deploy, debug, migrate, or troubleshoot CloudBase (腾讯云开发, 云开发, TCB, 微信云开发) projects. Covers Web, 微信小程序, 小程序, uni-app, mobile (iOS, Android, Flutter, React Native). UI (页面, 界面, 表单, form, dashboard, prototype, 原型); auth (登录, 注册, OAuth, 微信登录, publishable key); databases (NoSQL 文档数据库, MySQL 关系型数据库, PostgreSQL/CloudBase PG, app.rdb(), queryPgDatabase/managePgDatabase, CRUD, 查询, security rules); 云函数/cloud functions (serverless, scf_bootstrap); CloudRun (云托管, Dockerfile); 云存储. Built-in AI (内置大模型, AI 对话, streaming, 流式输出, 图片生成, generateText, streamText, createModel, generateImage, TokenHub, Hunyuan, hunyuan-exp, DeepSeek, deepseek, GLM, Kimi, Token Credits 资源包, 小程序成长计划). 第三方大模型, 大模型接入, 大模型调用, LLM API, AI agent, 智能体, AI Agent, AG-UI, LangGraph. Ops (巡检, 诊断, health check, 日志, troubleshooting). Spec (需求文档, 技术方案, requirements, tasks.md). Do NOT use for non-CloudBase projects, pure frontend without CloudBase, or self-hosted backends without CloudBase.

72

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is cloudbase in TencentCloudBase/CloudBase-AI-Toolkit

SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured router skill with a clear staged workflow, concrete commands and routing table, and exemplary progressive disclosure pointing to real one-level-deep reference files. The main improvement opportunity is reducing repetition of the MCP-unavailable / tooling-fallback caveat across sections.

Suggestions

Consolidate the repeated 'MCP unavailable → use tooling-fallback.md / tcb CLI' guidance into a single canonical section and reference it by name elsewhere to trim tokens.

Add one short copy-paste example for the most common action (e.g. a minimal envQuery alias-resolution call) to lift actionability from concrete-identifier guidance to fully executable.

State the close-out validation steps inline (which static/runtime checks to run) rather than only delegating to the cloudbase-code-review skill, so the mandatory Stage 3 checkpoint is self-contained.

DimensionReasoningScore

Conciseness

Mostly lean routing guidance that assumes Claude's competence and avoids explaining known concepts, but the tooling-fallback.md path and MCP-unavailable caveat are repeated across several sections, adding some avoidable tokens.

4 / 5

Actionability

Provides concrete commands and identifiers (npx plugins add TencentCloudBase/cloudbase-plugin, npx mcporter list, envQuery(action=list, alias=...), manageApps(action="createApp"), JSON.stringify(result, null, 2)) plus a precise routing table, with only minor gaps in full copy-paste examples.

4 / 5

Workflow Clarity

Clear three-stage sequence (Exploration → Implementation → Close-out) with explicit constraints ('Stage 2a must precede frontend code', 'Stage 3 is mandatory') and validation checkpoints (self-verify, cloudbase-code-review, 2-3 failed-attempt reroute), though some child-skill validation detail is delegated rather than stated.

4 / 5

Progressive Disclosure

Acts as a clean overview entry: an 'On-demand references' section with one-line descriptions and a 'Reference index' point to one-level-deep files, and every referenced path (activation-map.yaml, console-links.md, deployment-workflow.md, mcp-setup.md, scenarios.md, tooling-fallback.md) exists in references/.

5 / 5

Total

17

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exceptionally thorough description that explicitly states what the skill covers, when to use it, and when not to, with dense bilingual trigger terms and concrete API references. Its only mild weakness is length bordering on keyword density, though every term is relevant rather than padded.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (develop, design, build, deploy, debug, migrate, troubleshoot) and enumerates specific capabilities with real API names (app.rdb(), queryPgDatabase, generateText, manageApps), giving comprehensive coverage rather than vague language.

5 / 5

Completeness

Explicitly answers both 'what' (covers Web, 小程序, databases, functions, CloudRun, storage, AI, ops, spec) and 'when' ('Use this skill when you develop...'), plus a concrete negative-boundary clause ('Do NOT use for non-CloudBase projects...').

5 / 5

Trigger Term Quality

Comprehensive natural keyword coverage in both English and Chinese with synonyms and product names (CloudBase, 腾讯云开发, 云开发, TCB, 微信云开发, 登录, 注册, 云函数, 流式输出), matching how users actually phrase these requests.

5 / 5

Distinctiveness Conflict Risk

Clear CloudBase niche with distinct product-specific triggers and an explicit exclusion clause for non-CloudBase / pure-frontend / self-hosted backends, minimizing wrong-skill activation.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
TencentCloudBase/CloudBase-AI-Toolkit
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.