CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

miniprogram-development

WeChat Mini Program development skill for building, debugging, previewing, testing, publishing, and optimizing mini program projects (小程序开发、调试、预览、发布). Covers project structure and config (`project.config.json`, `appid`, `miniprogramRoot`, `tabBar`, routing/navigation, icon assets), WeChat Developer Tools Nightly workflows (`wechatide` CLI, WeChat IDE Skills/MCP), `miniprogram-ci` preview/upload, console/network debugging, message push (消息推送) and customer-service auto-reply (客服消息), mini program SEO / search indexing (小程序搜索优化、页面收录、搜索推广、mpcrawler), and CloudBase integration (`wx.cloud`, 腾讯云开发, 云开发) when explicitly used. Use when users create, develop, modify, debug, preview, deploy, publish, or promote WeChat Mini Programs. NOT for Web frontend (use web-development), pure backend services (use cloudrun-development / cloud-functions), or UI-design-only tasks (use ui-design).

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

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

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 a well-routed, actionable overview with real bundle files and validation gates, but it pays a conciseness tax through triple-stated policies and a duplicated exclusion list. Consolidating the repeated rules into single canonical locations would move both conciseness and organization toward the top anchors.

Suggestions

Merge the two 'Do NOT use for' lists (Activation Contract and 'When to use this skill') into one canonical exclusion list with the sibling-skill redirects.

State the missing-`wechatide` policy once (e.g., in the Debugging section) and reference it from the gotchas and routing steps instead of repeating the full three-sentence version three times.

Consolidate the tabBar text-only preference (currently in Common mistakes, Route by scenario, and Resource Handling) into the Resource Handling section and link to it elsewhere.

DimensionReasoningScore

Conciseness

The content is dense with genuinely useful guidance, but the same rules are stated repeatedly: the "Do NOT use for" list appears twice (lines 43-47 and 75-78), the missing-`wechatide` policy is repeated three times (gotchas, routing step 5, and the Debugging section), and the text-only tabBar preference appears in three places. This matches 'mostly efficient but could be tightened'; it does not reach the verbose padding of the 2 anchor since nothing explains concepts Claude already knows.

3 / 5

Actionability

Guidance is mostly executable: complete `app.json` tabBar config, a full minimal project skeleton (`app.js`, page files, `project.config.json`), concrete CLI context flags (`-c <clientName>`, absolute `--project`, valid `appid`), and specific API names (`cloud.openapi.customerServiceMessage.send`). Minor gaps — e.g., no inline example `wechatide` invocation — keep it below the fully copy-paste-ready 5 anchor.

4 / 5

Workflow Clarity

"How to use this skill" gives a clear 5-step sequence with scenario-based routing, and validation is enforced via the Change Safety Protocol and Deployment Gate before code changes/publishing, plus an explicit wait-for-user-answer loop for the missing-`wechatide` case. It sits below the 5 anchor only because detailed validation checkpoints live in referenced protocol files rather than being shown inline.

4 / 5

Progressive Disclosure

Six reference files, all verified to exist, are one level deep and well signaled with when-to-read annotations in both the routing section and the References section. The inline duplication of routing rules and gotchas is a minor organization gap that keeps it below the 'content appropriately split' 5 anchor.

4 / 5

Total

15

/

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.

This is a strong description: concrete capability coverage, bilingual natural trigger terms, an explicit use-when clause, and explicit NOT-for redirects to sibling skills. The only criticism is verbosity — reference-level detail (e.g., `mpcrawler`, specific config keys) is inlined — but this does not reduce any dimension's score since coverage, triggers, and disambiguation are all comprehensive.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions ("building, debugging, previewing, testing, publishing, and optimizing mini program projects") plus specific artifacts and tools (`project.config.json`, `appid`, `tabBar`, `wechatide`, `miniprogram-ci`, `wx.cloud`), giving comprehensive coverage of the skill's capabilities. It clearly matches the 'multiple specific concrete actions; comprehensive coverage' anchor, not the 4 anchor which requires minor gaps in coverage.

5 / 5

Completeness

It explicitly answers both questions: what ("development skill for building, debugging, previewing, testing, publishing, and optimizing") and when ("Use when users create, develop, modify, debug, preview, deploy, publish, or promote WeChat Mini Programs"), with concrete trigger phrases. It cannot be the 4 anchor since the 'when' clause is fully explicit, not merely improvable.

5 / 5

Trigger Term Quality

Trigger terms are comprehensive and bilingual: "WeChat Mini Program", "mini program", 小程序开发/调试/预览/发布, 消息推送, 客服消息, 云开发, plus tool and API names (`wechatide`, `miniprogram-ci`, `mpcrawler`) users would naturally mention. This matches the 'comprehensive coverage of natural terms including synonyms' anchor.

5 / 5

Distinctiveness Conflict Risk

The niche is clear (WeChat Mini Programs specifically) and disambiguation is explicit: "NOT for Web frontend (use web-development), pure backend services (use cloudrun-development / cloud-functions), or UI-design-only tasks (use ui-design)". Distinct triggers and named sibling-skill redirects give minimal conflict risk, matching the top anchor.

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.

Validation — 15 / 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

Path

plugin/cloudbase/skills/miniprogram-development/SKILL.md

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.