CtrlK
BlogDocsLog inGet started
Tessl Logo

miniprogram-development

WeChat Mini Program development skill for building, debugging, previewing, testing, publishing, optimizing, and promoting mini program projects. This skill should be used when users ask to create, develop, modify, debug, preview, test, deploy, publish, launch, review, optimize, or promote WeChat Mini Programs, mini program pages, components, `tabBar`, routing, navigation, icon assets, project structure, project configuration, `project.config.json`, `appid` setup, device preview, real-device validation, WeChat Developer Tools Nightly workflows, `wechatide` CLI, WeChat IDE Skills/MCP, console/network debugging, `miniprogram-ci` preview/upload flows, or mini program release processes. It should also be used when users ask about mini program SEO / search optimization / search promotion (小程序 SEO、搜索优化、微信搜索收录、搜索推广、页面收录、关键词排名、被搜索到) or page indexing by the WeChat search crawler (`mpcrawler`). when users explicitly mention CloudBase, `wx.cloud`, Tencent CloudBase, 腾讯云开发, 微信云开发, or 云开发 in a mini program project.

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 miniprogram-development 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.

The body is well-structured with strong progressive disclosure and concrete, actionable artifacts, backed by a complete set of real reference files. Its main weakness is redundant framing across the Activation Contract and When-to-use sections that adds tokens without adding guidance.

Suggestions

Collapse the overlapping "Activation Contract" (Use this first / Read before writing code / Do NOT use for) and "When to use this skill" sections into a single routing block to remove duplicated framing.

Reduce repetition of the Change Safety Protocol and Deployment Gate pointers—they appear in the Sibling skills, Common mistakes, How to use, and Debugging sections; cite them once at the activation point.

Inline one or two complete `wechatide` command examples (e.g., preview and upload invocations with required flags) so the most common operations are copy-paste ready without opening the reference.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes Claude's competence (defers Chinese-term detail to references), but the "Activation Contract" and "When to use this skill" sections overlap, and the Change Safety / Deployment Gate pointers are restated multiple times. Not a 5 due to this duplicated framing.

4 / 5

Actionability

Provides executable artifacts—a complete project skeleton (`app.js`, `app.json`, `project.config.json`), concrete `wechatide` context flags (`-c`, `--project`, `appid`, `env`), and specific API names (`cloud.openapi.customerServiceMessage.send`). Falls short of 5 because full `wechatide` command examples are deferred to references rather than shown inline.

4 / 5

Workflow Clarity

Routing is sequenced (general workflow → conventions → scenario routing) with explicit validation gates (Change Safety Protocol before code changes, Deployment Gate before publish). Not a 5 because routing guidance is split across overlapping sections ("Activation Contract", "How to use", "Debugging/Preview/Publishing"), creating mild ambiguity about which path applies.

4 / 5

Progressive Disclosure

Clear overview in SKILL.md with well-signaled, one-level-deep references; every cited reference file (cloudbase-integration, devtools-debug-preview, wxide-vs-cloudbase-mcp, message-push-customer-service, seo-search-optimization, pitfalls) exists in ./references/, and the inline content is appropriately kept high-level with detail pushed to those files.

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.

The description is specific, trigger-rich, and complete, with explicit what/when guidance and clear boundaries against sibling skills. It is somewhat long but every clause carries trigger value.

DimensionReasoningScore

Specificity

Lists multiple concrete actions—"building, debugging, previewing, testing, publishing, optimizing, and promoting"—plus specific config/files like `project.config.json`, `tabBar`, `appid`, `wechatide` CLI, and `miniprogram-ci` flows, giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both "what" (mini program build/debug/publish/optimize toolchain) and "when" via the "This skill should be used when users ask to…" clause with concrete trigger phrases, including CloudBase-specific triggers.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases ("create, develop, modify, debug, preview, test, deploy, publish, launch, review, optimize, or promote") with synonyms, file extensions/config names, and Chinese equivalents (小程序 SEO、搜索优化、客服消息/自动回复), matching what users actually say.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (WeChat Mini Programs) with distinct, domain-specific triggers and an explicit "Do NOT use for" boundary (web frontend, pure backend, UI-design-only), minimizing conflict with sibling 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.