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.

68

Quality

83%

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

71%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 entry skill with concrete commands, a clear staged workflow with validation, and exemplary one-level-deep progressive disclosure. Its main weakness is repetition of the MCP/CLI fallback guidance across multiple sections, which inflates token cost without adding new information.

Suggestions

Consolidate the MCP/CLI fallback guidance into a single authoritative section (e.g., 'MCP + CLI prerequisite') and have other sections reference it once instead of restating the 'references/tooling-fallback.md' path seven times.

Tighten the 'Global rules before action' and 'Universal guardrails' lists, which overlap with the 'Engineering constitution' rules (e.g., MCP-preference and fallback appear in both), to reduce redundancy.

Add one inline validation checkpoint example for a destructive path (e.g., the 'First frontend deploy must use manageApps' rule) showing the verify-before-proceed step, to lift workflow_clarity to 5.

DimensionReasoningScore

Conciseness

Mostly efficient and free of basic-concept padding, but the MCP/CLI fallback path ('references/tooling-fallback.md', 'tcb' CLI) is restated at lines 18, 37, 43, 61, 100, 103, and 110 — repetition that could be consolidated. Not a 4 because the redundancy is noticeable rather than minor.

3 / 5

Actionability

Provides concrete, executable guidance — real commands and API actions like `npx plugins add TencentCloudBase/cloudbase-plugin -y --scope user`, `envQuery(action=list, alias=..., aliasExact=true)`, `manageApps(action="createApp", ...)`, and `JSON.stringify(result, null, 2)` — with only minor gaps since full code lives in child skills.

4 / 5

Workflow Clarity

Clear three-stage sequence (Exploration → Implementation 2a/2b → Close-out) with explicit checkpoints ('Stage 2a must precede frontend code', 'Stage 3 is mandatory') and a feedback loop ('After 2–3 failed attempts... stop and reroute'). Not a 5 because per-task validation detail is delegated to child skills rather than checked inline.

4 / 5

Progressive Disclosure

Clean overview with well-signaled one-level-deep references; the 'On-demand references' and 'Reference index' sections list six real bundle files (all verified present in references/), each described and linked, with no nested-reference chains.

5 / 5

Total

16

/

20

Passed

Description

95%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.

A highly specific, trigger-rich description that clearly states what the skill covers and when to use it, with an explicit negative-boundary clause. The only ding is the second-person 'you' phrasing, which costs one specificity point per the voice guideline.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (develop, design, build, deploy, debug, migrate, troubleshoot) across UI, auth, databases, cloud functions, CloudRun, storage, AI, ops, and spec with comprehensive coverage; reduced from 5 because the second-person 'Use this skill when you develop' triggers the voice penalty.

4 / 5

Completeness

Explicitly answers both 'what' (the full CloudBase capability surface) and 'when' ('Use this skill when you develop, design, build, deploy, debug, migrate, or troubleshoot CloudBase... projects') plus negative triggers ('Do NOT use for non-CloudBase projects...').

5 / 5

Trigger Term Quality

Comprehensive coverage of natural terms in both English and Chinese with abundant synonyms and aliases (CloudBase, 腾讯云开发, 云开发, TCB, 微信云开发, 登录, 注册, generateText, streamText, etc.).

5 / 5

Distinctiveness Conflict Risk

Clear CloudBase niche with distinct bilingual triggers and an explicit exclusion boundary ('Do NOT use for non-CloudBase projects, pure frontend without CloudBase, or self-hosted backends without CloudBase'), minimizing conflict risk.

5 / 5

Total

19

/

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.