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, 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).

70

Quality

86%

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

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.

A well-structured, highly actionable server-side AI skill with an explicit preflight workflow and clear reference split. The main weakness is conciseness: the anti-hallucination message about createModel's three legal arguments is repeated across multiple sections.

Suggestions

Consolidate the 'createModel accepts exactly three legal values / never guess' rule into one authoritative section (e.g. the STOP block) and have later sections reference it rather than restating it.

Move the inline DescribeAIModels/DescribeManagedAIModelList return-shape definitions into references/api-reference.md, keeping only the operational decision steps in the body.

Tighten Best Practices items 1–3, which restate the preflight and createModel rules already covered in detail above, to a brief cross-reference.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence (no basic-concept padding) but restates the 'createModel accepts exactly three legal values / never guess' warning verbatim-ish across the STOP, Available Providers, and Best Practices sections, which could be consolidated.

3 / 5

Actionability

Fully executable guidance: concrete MCP tool calls with exact params, copy-paste code for createModel+generateText, the full UpdateAIModel payload, and exact API actions (DescribeAIModels, DescribeManagedAIModelList, UpdateAIModel).

5 / 5

Workflow Clarity

The mandatory two-step preflight has an explicit sequence (Step 0 → ① eligibility → ② group readiness) with pass/fail validation checkpoints and error-recovery feedback loops (missing model → enable via full-replacement UpdateAIModel).

5 / 5

Progressive Disclosure

Clean overview with one-level-deep references to two real bundle files (api-reference.md, custom-onboarding.md) and an 'on demand' framing; minor inline API-contract detail (DescribeAIModels return shapes) that could live in the reference file.

4 / 5

Total

17

/

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 dense, concrete description that names the runtime, the SDK, the legal API shapes, and explicit use/anti-use triggers. Strong on specificity, completeness, and distinctiveness; trigger-term coverage is very good but a few natural synonyms are absent.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — cloud functions, CloudRun, Express/Koa/NestJS, serverless APIs, scheduled jobs, LLM proxies, agent orchestration, image generation, text generation — giving comprehensive coverage of the skill's surface.

5 / 5

Completeness

Explicitly answers 'what' (SDK + the createModel/generateText API shapes) and 'when' ('Use this skill for…' scenarios plus explicit 'NOT for browser/Web… or Mini Program' anti-triggers).

5 / 5

Trigger Term Quality

Strong natural runtime keywords (cloud functions, CloudRun, serverless APIs, scheduled jobs, LLM proxies, agent orchestration), but a few natural synonyms are missing (e.g. the spelled-out 'Tencent CloudBase', 'serverless functions').

4 / 5

Distinctiveness Conflict Risk

Clear niche — Node.js backend AI via @cloudbase/node-sdk — explicitly distinguished from the ai-model-web and ai-model-wechat siblings, leaving minimal conflict risk.

5 / 5

Total

19

/

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.