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 — Web, 微信小程序, 小程序, uni-app, mobile (iOS, Android, Flutter, React Native). Covers UI (页面, 界面, 表单, dashboard, prototype, 原型); auth (登录, 注册, OAuth, publishable key); databases (NoSQL 文档数据库, MySQL 关系型数据库, PostgreSQL/CloudBase PG, app.rdb(), queryPgDatabase/managePgDatabase, CRUD, 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, DeepSeek, GLM, Kimi, Token Credits 资源包, 小程序成长计划); third-party/custom model onboarding (第三方大模型接入, 大模型调用, LLM API); AI agent (智能体, AG-UI, LangGraph); ops troubleshooting (巡检, 诊断, 日志); spec workflow (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.

70

Quality

86%

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

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 entry skill: lean, actionable routing tables and guardrails with a clearly sequenced, checkpointed workflow, and clean one-level-deep reference disclosure backed by real files. Slight gains available in conciseness and end-to-end actionability.

Suggestions

Consolidate the recurring MCP-vs-CLI fallback guidance (currently restated in Step 0, Activation Contract, and MCP+CLI prerequisite) into a single canonical pointer to tooling-fallback.md to trim tokens.

Add one fully copy-pasteable minimal example (e.g., a tiny BaaS CRUD snippet or an MCP call) in the body to lift actionability from 4 to 5.

Make the close-out validation step concrete with an explicit command or checklist (e.g., the exact cloudbase-code-review invocation) to push workflow_clarity to 5.

DimensionReasoningScore

Conciseness

Dense but lean — almost entirely actionable routing, guardrails, and contracts rather than concepts Claude already knows; a few sections (e.g., repeated MCP/CLI fallback notes) could be tightened slightly.

4 / 5

Actionability

Gives concrete commands, exact variable names, and executable code patterns (e.g., JSON.stringify(result, null, 2), queryEnv(action=list, alias=..., aliasExact=true), manageApps(action="createApp", ...)) with only minor gaps in full copy-paste examples.

4 / 5

Workflow Clarity

Clear staged workflow (Step 0 site check → Exploration → Implementation 2a/2b → mandatory Close-out) with explicit checkpoints ('Stage 2a must precede frontend code', 'Stage 3 is mandatory', 'Self-verify before claiming done'); minor validation gaps keep it just below a 5.

4 / 5

Progressive Disclosure

Clear overview with well-signaled one-level-deep references — an 'On-demand references' list and a 'Reference index' — and every referenced file (activation-map.yaml, console-links.md, deployment-workflow.md, mcp-setup.md, scenarios.md, tooling-fallback.md) exists as a real bundle file.

5 / 5

Total

17

/

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 strong, comprehensive description with explicit what/when/exclusion structure and rich bilingual trigger coverage. Only the second-person phrasing costs it a point on specificity per the rubric voice rule.

Suggestions

Rephrase in third person ('Use when developing, designing, building... CloudBase projects') to avoid the second-person voice penalty and reclaim the specificity point.

DimensionReasoningScore

Specificity

Lists many concrete actions (develop, design, build, deploy, debug, migrate, troubleshoot) across concrete domains (UI, auth, databases, cloud functions, CloudRun, AI), but the second-person voice 'Use this skill when you develop' triggers the rubric's -1 specificity penalty.

4 / 5

Completeness

Explicitly answers 'what' (Covers UI, auth, databases, AI...) and 'when' ('Use this skill when you develop...'), and adds an explicit exclusion clause ('Do NOT use for non-CloudBase projects...').

5 / 5

Trigger Term Quality

Comprehensive bilingual natural terms and synonyms (腾讯云开发, 云开发, TCB, 微信云开发, 小程序, 登录, 云函数, 流式输出) plus product/model names and file extensions, covering what users would actually say.

5 / 5

Distinctiveness Conflict Risk

Clear CloudBase niche with distinct triggers and an explicit 'Do NOT use for...' boundary, minimizing overlap with adjacent skills.

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.