CtrlK
BlogDocsLog inGet started
Tessl Logo

ai-model-web

Use this skill when a browser/Web app (React, Vue, Next, Nuxt, static sites, SPAs, dashboards, AI chat UI, 页面, 前端, 网页) needs AI models via @cloudbase/js-sdk. Default routing for Web/frontend AI — call directly from the browser, do NOT propose a Node.js proxy. Covers generateText and streamText; models via ai.createModel with groups cloudbase, hunyuan-exp, or custom-*, model id in the `model` field. MUST run two-step preflight before code — see body. NOT for Node.js backend (use ai-model-nodejs), Mini Program (use ai-model-wechat), or image generation (Node SDK only).

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

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.

Highly actionable with excellent workflow sequencing and validation checkpoints, but hampered by cross-section repetition of the createModel rules and a monolithic structure that would benefit from splitting reference material into bundled files.

Suggestions

Consolidate the repeated createModel legal-value guidance into one authoritative section and have other sections reference it, reducing token cost from restating the same warnings 4+ times.

Move the Type Definitions and the detailed preflight callCloudApi API reference into files under references/ (e.g. reference/types.md, reference/preflight.md) and link to them from SKILL.md to improve progressive disclosure.

Extract the Available Providers and Models catalog into a reference file, keeping only the three legal createModel shapes and routing guidance inline.

DimensionReasoningScore

Conciseness

Mostly efficient and free of basic-concept padding, but the createModel legal-value warnings and 'never assume a model is enabled' guidance are restated across the STOP, preflight, providers, custom-onboarding, and Best Practices sections, which could be tightened.

3 / 5

Actionability

Fully executable, copy-paste-ready code for generateText, streamText, initialization, and error handling, plus exact MCP callCloudApi invocations with parameter shapes and a correct/wrong createModel table covering the common cases.

5 / 5

Workflow Clarity

The mandatory two-step preflight is a clearly sequenced process with explicit pass conditions, stop/surface-to-user branches, and a feedback loop (missing model → DescribeManagedAIModelList → UpdateAIModel → re-confirm), supported by a numbered decision procedure.

5 / 5

Progressive Disclosure

Well-organized section headers, but the ~387-line body is monolithic: type definitions, the full preflight API reference, and the provider/model catalog are all inlined rather than split into one-level-deep reference files (no references/ bundle exists).

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 strong, specific description that covers what, when, and distinctiveness with comprehensive natural trigger terms in both English and Chinese. Uses third-person voice and avoids vague fluff.

DimensionReasoningScore

Specificity

Names concrete actions (generateText, streamText, ai.createModel with specific groups, two-step preflight) with comprehensive coverage of the skill's surface.

5 / 5

Completeness

Explicitly answers both 'what' (call AI models via @cloudbase/js-sdk: generateText/streamText, createModel, preflight) and 'when' ("Use this skill when a browser/Web app ... needs AI models") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including framework names (React, Vue, Next, Nuxt, SPAs, dashboards, AI chat UI) plus Chinese synonyms (页面, 前端, 网页) that users would actually say.

5 / 5

Distinctiveness Conflict Risk

Clear niche (Web/browser AI via @cloudbase/js-sdk) with explicit disambiguation against Node.js (ai-model-nodejs), Mini Program (ai-model-wechat), and image generation, 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.