CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cloudbase-document-database-in-wechat-miniprogram

Use CloudBase document database WeChat MiniProgram SDK to query, create, update, and delete data. Supports complex queries, pagination, aggregation, and geolocation queries.

Quality

69%

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

Fix and improve this skill with Tessl

tessl review fix ./config/.claude/skills/cloudbase-document-database-in-wechat-miniprogram/SKILL.md

The canonical home for this skill is cloudbase-document-database-in-wechat-miniprogram in TencentCloudBase/CloudBase-AI-Toolkit

SKILL.md
Quality
Evals
Security

Quality

Content

50%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 a strong activation contract, canonical initialization, and concrete ownership/security rules, and the inline code is executable. The dominant problem is that every operation-detail reference file named in Quick routing is missing from the bundle, which undermines actionability and progressive disclosure, and there is no explicit error-recovery feedback loop for database operations.

Suggestions

Ship the six referenced companion files (crud-operations.md, complex-queries.md, pagination.md, aggregation.md, geolocation.md, security-rules.md) or inline minimal working snippets for each operation so the routing table is not an index of missing files.

Add a validation/feedback loop for the common failure mode, e.g. "On permission-denied errors, re-check the collection rule's ownership condition against the query shape, adjust, and retry" — this would lift workflow clarity above the database-operations cap.

Remove the redundant "Overview" use-case list (already covered by "Use this first when") and trim the generic "Best practices" items to reclaim tokens.

DimensionReasoningScore

Conciseness

The body is mostly efficient — the Activation Contract and working rules are tight — but the "Overview" section re-lists use cases already covered by "Use this first when", and "Best practices" items like "Create clear collection naming conventions" and "Use typed wrappers or model helpers" are generic padding that could be trimmed. Not 4: there are several such cuttable passages rather than minor instances.

3 / 5

Actionability

What is inline is executable and copy-paste ready (canonical init, env targeting, where-query, doc get) and the working rules are concrete ("Never set or override _openid manually"). However, the core operations the skill claims — CRUD detail, pagination, aggregation, geolocation — have no inline guidance because all six routed files (./crud-operations.md, ./complex-queries.md, ./pagination.md, ./aggregation.md, ./geolocation.md, ./security-rules.md) are missing from the bundle, leaving key details unavailable. Not 4: the gaps are not minor.

3 / 5

Workflow Clarity

The "Minimal checklist" provides a legible pre-flight sequence and rule 3 gives partial error interpretation ("Permission errors usually mean the rule/query relationship is wrong"), but there is no explicit validate-then-fix-then-retry loop. Per the rubric's scoring note, database operations without feedback loops cap workflow clarity at 3. Not 4: the error-recovery guidance is a hint, not a checkpoint.

3 / 5

Progressive Disclosure

The "Quick routing" table is well-signaled and one level deep, which is the right structure — but none of the six referenced files exist in the bundle, so the navigation promise is unfulfilled and the detail content is unreachable. Not 4: references are clear but broken; not 2: the body itself is well organized and appropriately sized as an overview rather than an inlined wall of text.

3 / 5

Total

12

/

20

Passed

Description

75%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, concrete, and highly distinct, with a clear statement of what the skill does. Its main weakness is the absence of an explicit "Use when..." trigger clause, which caps completeness and leaves trigger-term coverage a step short of comprehensive.

Suggestions

Add an explicit trigger clause, e.g. "Use when a WeChat Mini Program must read or write CloudBase collections via wx.cloud.database(), or when the user mentions Mini Program database, collections, pagination, or aggregation."

Include natural synonyms users might say — "cloud database", "collection", "miniprogram", "CRUD" — to broaden trigger-term coverage.

Consider mentioning "wx.cloud.database()" in the description since it is the exact API entry point callers would reference.

DimensionReasoningScore

Specificity

"query, create, update, and delete data" plus "complex queries, pagination, aggregation, and geolocation queries" lists multiple concrete actions with comprehensive coverage of the SDK's operation surface, matching the top anchor. Not 4: the gaps (if any) are negligible — full CRUD plus four advanced query categories are all named.

5 / 5

Completeness

The "what" is clear (query/create/update/delete data with the Mini Program SDK), but there is no "Use when..." clause or equivalent explicit trigger guidance — "Use CloudBase... SDK to query" only weakly implies the when. Per the rubric guideline, a missing when-clause caps completeness at 3.

3 / 5

Trigger Term Quality

Natural terms users would say are present ("CloudBase", "WeChat MiniProgram", "document database", "pagination", "aggregation", "geolocation"), giving good keyword coverage. Not 5: common synonyms and variations ("cloud database", "collection", "miniprogram", "CRUD", "小程序") are absent and there is no explicit list of trigger phrases.

4 / 5

Distinctiveness Conflict Risk

"CloudBase document database WeChat MiniProgram SDK" carves a clear niche that is unlikely to trigger for the Web SDK, cloud functions, or SQL skills. Not 4: the three qualifying terms together leave virtually no overlap risk with adjacent skills.

5 / 5

Total

17

/

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

config/.claude/skills/cloudbase-document-database-in-wechat-miniprogram/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.