CtrlK
BlogDocsLog inGet started
Tessl Logo

ai-model-web

Use this skill when a browser/Web app (React, Vue, Angular, Next, Nuxt, static sites, SPAs, dashboards, AI chat UI) needs AI models via @cloudbase/js-sdk. Default routing for page/页面/Web/前端/frontend/网页/H5 AI — call directly from browser, do NOT propose a Node.js proxy. Covers generateText and streamText. 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. MUST run two-step preflight before code — see body. Keywords: 页面, Web, 前端, React, Vue, Next, Nuxt, SPA, AI chat UI, generateText, streamText, createModel, hunyuan-exp, Token Credits, TokenHub, Hunyuan, DeepSeek, GLM, Kimi, MiniMax. NOT for Node.js backend (use ai-model-nodejs), Mini Program (use ai-model-wechat), or image generation (Node SDK only).

71

Quality

88%

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

The canonical home for this skill is ai-model-web in TencentCloudBase/CloudBase-AI-Toolkit

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 body with excellent workflow sequencing and executable code, weakened mainly by repetition of the createModel/enable guidance across multiple sections and a monolithic structure that doesn't leverage progressive disclosure.

Suggestions

Consolidate the createModel 'three legal shapes' rule and the 'never assume enabled' guidance into a single section; the STOP block, Available Providers, and Best Practices currently restate the same rules.

Split the Type Definitions and the detailed preflight callCloudApi parameter references into reference files (e.g. references/types.md, references/preflight.md) and link to them from the body to apply progressive disclosure.

The standalone-install note and the routing blockquote duplicate routing guidance already in the 'When to use' and 'Do NOT use for' lists — merge to reduce token cost.

DimensionReasoningScore

Conciseness

Mostly efficient and accurate, but the createModel rules ('exactly three legal shapes') and 'never assume a model is already enabled' recur across the STOP section, Available Providers, and Best Practices, adding redundant tokens that could be tightened.

2 / 3

Actionability

Fully executable, copy-paste-ready code for install, init, generateText, streamText, and error handling, plus exact MCP callCloudApi invocations with PascalCase params and complete type definitions.

3 / 3

Workflow Clarity

The two-step preflight is clearly sequenced (Step 0 → ① eligibility → ② group readiness) with explicit pass conditions, stop-and-surface failure handling, and validate/enable-before-call feedback loops for destructive enable operations.

3 / 3

Progressive Disclosure

Well-organized into sections, but the ~390-line body is monolithic with no bundled reference files of its own; detailed material (Type Definitions, full preflight API params, custom onboarding) that could be split is kept inline.

2 / 3

Total

10

/

12

Passed

Description

100%

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 description: specific, trigger-rich, and clearly scoped with explicit 'use when' guidance and concrete routing exclusions. It uses third-person/impersonal voice and answers both what and when without padding.

DimensionReasoningScore

Specificity

Lists concrete actions — 'Covers generateText and streamText', 'Models via ai.createModel', 'call directly from browser' — naming specific SDK methods rather than vague verbs.

3 / 3

Completeness

Explicitly answers both 'what' (call AI models in browser via @cloudbase/js-sdk, generateText/streamText) and 'when' ('Use this skill when a browser/Web app...needs AI models', 'Default routing for page/页面/Web...').

3 / 3

Trigger Term Quality

Dense coverage of natural terms a user would say: browser/Web app, React, Vue, Next, Nuxt, SPA, dashboard, AI chat UI, plus 页面/前端/网页/H5 and vendor names Hunyuan/DeepSeek/GLM/Kimi/MiniMax.

3 / 3

Distinctiveness Conflict Risk

Clear niche with explicit exclusions — 'NOT for Node.js backend (use ai-model-nodejs), Mini Program (use ai-model-wechat), or image generation' — making routing unambiguous.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

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.