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

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 highly actionable with clear, validated workflows and executable examples across all main APIs. Its main weakness is duplication of the same guardrails across multiple sections and inlining of reference material that could be split into separate files.

Suggestions

Consolidate the createModel argument rules and 'no model is enabled by default' guardrail into a single canonical section, with other sections cross-referencing it instead of restating it verbatim.

Move the full Type Definitions, the Available Providers/Models catalog, and the 13 Best Practices into separate reference files (e.g. references/types.md, references/providers.md, references/best-practices.md) and keep SKILL.md as a lean overview with one-level-deep pointers.

Trim repeated preflight narration so the preflight section is the single source and the Best Practices list only restates the 'why', not the full step sequence.

DimensionReasoningScore

Conciseness

Content is accurate and domain-specific (no generic concept padding), but critical guardrails like the createModel argument rules and 'no model is enabled by default' are restated verbatim across 3–4 sections, so it could be tightened.

3 / 5

Actionability

Fully executable code blocks for generateText, streamText, generateImage, and init, plus exact callCloudApi MCP invocations and a wrong-vs-right contrast for createModel, covering the common cases copy-paste ready.

5 / 5

Workflow Clarity

The mandatory two-step preflight is sequenced (Step 0 → ① eligibility → ② group readiness) with enumerated pass conditions, explicit stop-and-surface failure branches, and a self-verify checklist (tsc + invoke + confirm usage.total_tokens > 0).

5 / 5

Progressive Disclosure

Well-organized single file with clear section headers and one-level sibling-skill pointers (with a no-HTTP-fetch guardrail), but no bundle files exist and sizable reference-style content (full TS type definitions, provider catalog, 13 best practices) is inlined rather than split into reference files.

4 / 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 clearly distinguishes the skill from siblings with explicit positive and negative routing. It fully answers what the skill does and when to use it.

DimensionReasoningScore

Specificity

Names concrete runtimes (cloud functions, CloudRun, Express, Koa, NestJS) and concrete SDK entry points (ai.createModel, ai.createImageModel, generateImage), giving comprehensive coverage of the skill's actions.

5 / 5

Completeness

Explicitly answers both what ('Node.js backend AI via @cloudbase/node-sdk') and when (a 'Use this skill for…' clause plus server-side runtime triggers), with explicit negative routing for browser/Mini Program.

5 / 5

Trigger Term Quality

Extensive natural trigger terms including 'cloud functions', 'serverless APIs', 'scheduled jobs', 'LLM proxy', bilingual '云函数/云托管', and concrete vendor/model keywords users would name, with synonyms and method names.

5 / 5

Distinctiveness Conflict Risk

A clear niche (server-side Node AI via this specific SDK, the only one with image generation) with explicit disambiguation against sibling skills (ai-model-web, ai-model-wechat), minimizing conflict risk.

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.