CtrlK
BlogDocsLog inGet started
Tessl Logo

ai-model-wechat

Use this skill for WeChat Mini Program AI via wx.cloud.extend.AI (小程序, wx.cloud apps). Covers generateText and streamText with callbacks (onText, onEvent, onFinish); streamText needs a data wrapper, generateText returns the raw response. Models via wx.cloud.extend.AI.createModel with groups hunyuan-exp (小程序成长计划), cloudbase (main managed), or custom-*; model id goes in the data wrapper `model` field. MUST run two-step preflight before code — see body. NOT for browser/Web (use ai-model-web), Node.js backend (use ai-model-nodejs), or image generation (use ai-model-nodejs).

72

Quality

88%

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 ai-model-wechat in TencentCloudBase/CloudBase-AI-Toolkit

SKILL.md
Quality
Evals
Security

Quality

Content

77%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.

Highly actionable with an excellent validated two-step workflow, but the single-file body is long and repeats its key warnings across multiple sections, and it does not split detailed reference material into bundle files.

Suggestions

Deduplicate the createModel-argument warning: state it once authoritatively in the STOP section and reference back from Available Providers, the Common Mistake callout, and Best Practice #2 instead of restating it.

Move the type definitions and the detailed DescribeAIModels/DescribeManagedAIModelList/UpdateAIModel API reference into a references/ file, keeping SKILL.md as an overview with the preflight decision tree and core code patterns.

Collapse the repeated 'no model is enabled by default' reminders into a single prominent note in the Preflight ② section.

DimensionReasoningScore

Conciseness

Mostly efficient domain-specific content, but the same warnings recur many times — the createModel-argument warning appears in the STOP section, Available Providers, the Common Mistake callout, and Best Practice #2, and 'no model enabled by default' is repeated across four sections — so it could be meaningfully tightened.

3 / 5

Actionability

Provides copy-paste-ready callCloudApi/createModel/generateText/streamText/UpdateAIModel/CreateAIModel examples plus full TypeScript type definitions covering the common cases.

5 / 5

Workflow Clarity

The two-step preflight is a fixed-order sequenced workflow with explicit hit/miss criteria, error-recovery guidance (surface enrollment/purchase links, ask user), validation via DescribeAIModels before writing business code, and a self-verify checklist — including a destructive-ops warning for the full-replacement Models array.

5 / 5

Progressive Disclosure

No bundle files exist and the ~440-line body is a monolith; large API catalog tables and type definitions that could live in reference files are inlined, though section headers do provide reasonable in-page navigation.

3 / 5

Total

16

/

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.

A dense but information-rich description that answers what, when, and what-not-to-use-for, with concrete API details and clear sibling-skill routing. Every token is informative rather than padded.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — generateText, streamText with onText/onEvent/onFinish callbacks, createModel with three named groups, and the two-step preflight — giving comprehensive coverage rather than vague domain references.

5 / 5

Completeness

Explicitly states what the skill does (call AI models via wx.cloud.extend.AI) and when to use it ('Use this skill for WeChat Mini Program AI') with concrete exclusion triggers routing to ai-model-web / ai-model-nodejs.

5 / 5

Trigger Term Quality

Covers the natural phrases a developer would say ('WeChat Mini Program AI', '小程序', 'wx.cloud apps') plus the API surface names (generateText, streamText, Hunyuan), with English/Chinese synonyms present.

5 / 5

Distinctiveness Conflict Risk

Narrow niche (WeChat Mini Program only) with explicit negative triggers and named sibling skills, leaving minimal risk of firing for browser/Node/image-generation tasks.

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.