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.

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

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

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, actionable routing entry file with strong progressive disclosure and clear workflow validation. The main weakness is conciseness: the MCP/CLI fallback guidance is repeated across multiple sections and could be consolidated to the single dedicated prerequisite section.

Suggestions

Consolidate the MCP/CLI fallback guidance: state the full procedure once in the 'MCP + CLI prerequisite' section and use brief one-line cross-references elsewhere instead of restating the configure-next-session-and-use-CLI recipe ~5 times.

Tighten the repeated 'if MCP unavailable, use tcb CLI via tooling-fallback.md' reminders in the Workflow, Activation Contract, Global rules, and Engineering constitution to single inline pointers.

DimensionReasoningScore

Conciseness

The body is dense and commendably avoids explaining concepts Claude already knows, but the MCP/CLI fallback procedure ('if MCP tools are missing, configure MCP for next session and use tcb CLI now, see tooling-fallback.md') is restated roughly five times (lines 38–39, 59, 65, 83, 122–125), which is noticeable verbosity that could be tightened — a 3 rather than 4.

3 / 5

Actionability

Provides concrete commands and API signatures throughout (npx plugins add TencentCloudBase/cloudbase-plugin, npx mcporter list | grep cloudbase, TCB_SITE=intl, queryEnv(action=list, alias=…, aliasExact=true), manageApps(action="createApp", …), JSON.stringify(result, null, 2)), but these are intermixed with routing directives ('read X skill first') that defer executable detail to child skills — solidly 4, not quite 5.

4 / 5

Workflow Clarity

A clear three-stage workflow (Exploration → Implementation 2a/2b → Close-out) with explicit validation (self-verify via tsc/lint/build/tests + agent-browser, mandatory cloudbase-code-review) and feedback loops (stop after 2–3 failed attempts; serialize-then-retry on write-tool type errors); detailed workflows live in child skills, leaving minor gaps versus the 5 anchor.

4 / 5

Progressive Disclosure

A clear overview entry file with well-signaled, one-level-deep references — all six referenced files (activation-map.yaml, console-links.md, deployment-workflow.md, mcp-setup.md, scenarios.md, tooling-fallback.md) exist under references/ and are indexed in both 'On-demand references' and 'Reference index' sections, matching the 5 anchor.

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 rich, highly specific description with comprehensive bilingual trigger terms, explicit use-when guidance, and clear conflict-avoidance boundaries. The only dock is the second-person voice ('you develop') which the rubric penalizes on specificity.

Suggestions

Rephrase the opening in third person to avoid the specificity penalty — e.g., 'Use this skill when developing, designing, building, deploying, debugging, migrating, or troubleshooting CloudBase…' instead of 'when you develop…'.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (develop, design, build, deploy, debug, migrate, troubleshoot) across UI/auth/DB/functions/CloudRun/AI/agents/ops/spec with comprehensive coverage, matching the 5 anchor; reduced to 4 because the second-person phrasing 'Use this skill when you develop…' incurs the rubric's -1 specificity penalty.

4 / 5

Completeness

Explicitly answers both 'what' ('Covers UI… auth… databases…') and 'when' ('Use this skill when you develop…') with concrete trigger phrases, plus an explicit 'Do NOT use for…' exclusion — a clear 5.

5 / 5

Trigger Term Quality

Comprehensive natural trigger terms with extensive synonyms in both English and Chinese (CloudBase, 腾讯云开发, 云开发, TCB, 微信云开发, 登录, 注册, 智能体, 流式输出, 图片生成), matching the 5 anchor's synonym coverage.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear CloudBase-specific niche with distinct product triggers and an explicit exclusion boundary ('Do NOT use for non-CloudBase projects, pure frontend without CloudBase, or self-hosted backends'), yielding minimal 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.