CtrlK
BlogDocsLog inGet started
Tessl Logo

ai-model-nodejs

Use this skill for Node.js backend AI via @cloudbase/node-sdk (>=3.16.0) — cloud functions, CloudRun, Express, Koa, NestJS, serverless APIs, scheduled jobs, LLM proxies. Only SDK supporting image generation (ai.createImageModel + generateImage). Text models via ai.createModel with groups cloudbase, hunyuan-exp, or custom-*. Model IDs (deepseek-v4-flash, deepseek-v3.2, hunyuan-2.0-instruct-20251111, glm-5, kimi-k2.6) go in the model field of generateText/streamText. MUST run two-step preflight before code — see body. Keywords: backend, 云函数, 云托管, serverless, LLM proxy, agent orchestration, generateText, streamText, generateImage, createModel, hunyuan-image, Token Credits, TokenHub, Hunyuan, DeepSeek, GLM, Kimi, MiniMax. NOT for browser/Web (use ai-model-web) or Mini Program (use ai-model-wechat).

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-nodejs 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.

A thorough, highly actionable guide with strong validation-gated workflows for a fragile SDK integration, weakened mainly by repetition across sections and a monolithic structure that inlines reference-grade material instead of splitting it into bundled files.

Suggestions

Move the Type Definitions and full image-generation parameter table into a references/ file (e.g. REFERENCE.md) and link to it from the body so SKILL.md stays an overview, raising progressive_disclosure.

Consolidate the createModel 'three legal values' guidance into one canonical section and have other sections link back to it instead of restating the rules four times.

Trim the Best Practices list by removing items that merely restate the preflight and createModel sections, keeping only net-new guidance.

DimensionReasoningScore

Conciseness

Mostly efficient and full of SDK-specific detail Claude would not know, but the createModel 'three legal values' rule is repeated in four places and the 13-item Best Practices section heavily recaps the preflight and createModel guidance, so it could be tightened.

3 / 5

Actionability

Copy-paste-ready JS examples for generateText, streamText, generateImage, and init, plus concrete MCP callCloudApi invocations and full type definitions cover the common cases per the 5-anchor.

5 / 5

Workflow Clarity

The mandatory two-step preflight is a clearly sequenced process with explicit pass/fail validation gates and 'stop writing code' conditions, and Best Practice #13 adds a self-verify feedback loop, matching the explicit-checkpoints anchor.

5 / 5

Progressive Disclosure

Well-organized with clear section headers, but at ~450 lines with no reference files (references/, scripts/, assets/ absent), reference-grade content such as Type Definitions and the full parameter surface is inlined; it exceeds the under-50-line simple-skill exception that would allow a 5.

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, well-targeted description that names concrete capabilities, surfaces natural trigger keywords (including Chinese synonyms), and explicitly bounds the skill against its sibling web/WeChat skills. It answers both 'what' and 'when' without vague fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and surfaces (cloud functions, CloudRun, Express, Koa, NestJS, serverless APIs, scheduled jobs, LLM proxies, image generation, text models via createModel), matching the 'comprehensive coverage' anchor rather than the 4-anchor's 'minor gaps'.

5 / 5

Completeness

'Use this skill for Node.js backend AI via @cloudbase/node-sdk' states what and when, reinforced by 'NOT for browser/Web (use ai-model-web) or Mini Program' negative guidance, hitting the explicit what-and-when anchor.

5 / 5

Trigger Term Quality

An explicit 'Keywords:' block covers natural terms plus synonyms and method/vendor names (backend, 云函数, 云托管, serverless, generateText, streamText, generateImage, hunyuan-image, Hunyuan, DeepSeek, GLM, Kimi, MiniMax), matching the comprehensive synonym/extension anchor.

5 / 5

Distinctiveness Conflict Risk

Clear niche (Node.js backend AI on the CloudBase runtime plane) with explicit routing away from ai-model-web and ai-model-wechat, giving minimal conflict risk per the 5-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.

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.