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, agent orchestration. The only SDK supporting image generation (ai.createImageModel + generateImage). Text via ai.createModel with groups cloudbase, hunyuan-exp, or custom-*; model ids (e.g. deepseek-v4-flash, glm-5, kimi-k2.6) go in the `model` field of generateText/streamText. MUST run two-step preflight before code — see body. NOT for browser/Web (use ai-model-web) or Mini Program (use ai-model-wechat).

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%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 dense, highly actionable body with an excellent validated preflight workflow and clean progressive disclosure. The main weakness is repetition of the createModel/preflight warnings across sections, which inflates length without adding new information.

Suggestions

Consolidate the createModel legal-argument warning: state the three legal shapes once in the STOP section and have Available Providers / Best Practices reference it rather than re-explaining.

Best Practices #1 re-states the full preflight procedure already detailed above; reduce it to a one-line pointer to the Mandatory Two-Step Preflight section to cut redundancy.

Tighten the "Decision procedure (when the user names a specific model)" so it does not repeat the enable-via-UpdateAIModel steps already covered in Preflight ②, keeping each step's authority in a single place.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence (no padding with basic concepts), but the legal-createModel-argument warning and the preflight summary are repeated across the STOP section, Available Providers, and Best Practices, adding noticeable redundancy that could be tightened.	3 / 5
Actionability	Guidance is fully executable: exact MCP tool calls with params, copy-paste init code, a precise decision procedure, and concrete code patterns for the common text/image cases — copy-paste ready.	5 / 5
Workflow Clarity	The mandatory two-step preflight is a clearly sequenced process with explicit validation checkpoints (pass conditions, stop-and-surface on failure, fall-back casing) and feedback loops for error recovery, satisfying the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview with two well-signaled, one-level-deep references (api-reference.md, custom-onboarding.md) that both exist in ./references/, plus a reference index — content is appropriately split for easy navigation.	5 / 5
	Total	18 / 20 Passed

Description

92%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 high-quality, specific, and well-scoped description that answers what and when clearly and actively steers away from sibling skills. Minor room for a few more natural keyword synonyms, but otherwise strong.

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete capabilities — cloud functions, CloudRun, Express/Koa/NestJS, serverless APIs, scheduled jobs, LLM proxies, agent orchestration, plus image and text generation — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	It explicitly answers both "what" (backend AI calls, image/text generation, mandatory preflight via @cloudbase/node-sdk) and "when" ("Use this skill for Node.js backend AI…") with concrete trigger framing and runtime-plane routing.	5 / 5
Trigger Term Quality	Strong natural terms users would say ("Node.js backend AI", "cloud functions", "CloudRun", "serverless APIs", "scheduled jobs", "agent orchestration") and concrete runtime names, but a few common synonyms/variations are absent, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The niche is sharply defined (Node.js backend AI via a specific SDK) and explicit disambiguation — "NOT for browser/Web (use ai-model-web) or Mini Program (use ai-model-wechat)" — leaves minimal risk of triggering the wrong skill.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
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/source/skills/ai-model-nodejs/SKILL.md
Commit: 3ce25cd

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.