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.

74

Quality

92%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 orchestration/routing entry skill with explicit workflow sequencing, validation, and clean one-level-deep progressive disclosure. Its main weakness is mild repetition of the MCP/CLI fallback guidance across several sections.

Suggestions

Consolidate the MCP/CLI fallback guidance into a single section (e.g., MCP + CLI prerequisite) and have other sections reference it once, removing the restated 'configure MCP for next session' phrasing.

For the most common cases (e.g., first deploy, alias resolution), include one short copy-paste command sequence inline so Claude can act without first reading a child skill.

The repeated 'see references/tooling-fallback.md' citations could be reduced to a single canonical pointer to avoid the same instruction appearing four times.

DimensionReasoningScore

Conciseness

Lean and directive with no padding or basic-concept explanations, but the MCP/CLI fallback logic ("configure MCP for next session and use tcb CLI via tooling-fallback.md") is restated across the Standalone fallback, Global rules, Engineering constitution, and MCP+CLI sections; minor redundancy prevents a 5 but is not verbose enough to drop to 3.

4 / 5

Actionability

Provides concrete commands and API calls (npx plugins add TencentCloudBase/cloudbase-plugin, npx mcporter list | grep cloudbase, queryEnv(action=list, aliasExact=true), manageApps(action="createApp"), JSON.stringify(result, null, 2)), but most guidance routes to child skills rather than giving copy-paste runnable blocks for common cases.

4 / 5

Workflow Clarity

Clear three-stage sequence (Exploration → 2a resource prep → 2b frontend → Close-out) with mandatory constraints, explicit validation (self-verify via tsc/lint/build/tests + agent-browser), and feedback loops ("After 2–3 failed attempts... stop and reroute"; alias conflict → clarify with user).

5 / 5

Progressive Disclosure

Entry skill stays an overview and splits detail into one-level-deep references; all six bundled reference files exist and are listed with one-line descriptions plus a reference index, and it explicitly instructs not to expand the entry file.

5 / 5

Total

18

/

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, bilingual trigger description that explicitly states both capability and activation conditions with concrete API symbols and a clear exclusion boundary. It is dense rather than padded, so verbosity does not undercut its strength.

DimensionReasoningScore

Specificity

Lists seven concrete actions (develop, design, build, deploy, debug, migrate, troubleshoot) plus a comprehensive set of specific API symbols (app.rdb(), queryPgDatabase, generateText, streamText, createModel, generateImage, scf_bootstrap) across every CloudBase domain.

5 / 5

Completeness

Explicitly answers 'what' (CloudBase projects across all listed capabilities) and 'when' ("Use this skill when you develop..."), and adds an explicit exclusion clause, satisfying both halves with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage in both English and Chinese with synonyms (CloudBase/腾讯云开发/云开发/TCB/微信云开发, 登录/微信登录/OAuth) and a file extension (tasks.md), matching users' real phrasing.

5 / 5

Distinctiveness Conflict Risk

Scoped tightly to the CloudBase niche with distinct bilingual triggers and an explicit "Do NOT use for non-CloudBase projects..." boundary, minimizing overlap with other skills.

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.