Name: ai-model-web
Rating: 70.39999999999999 (1 reviews)
Author: TencentCloudBase

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).

Quality

86%

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

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

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 content with an excellent sequenced preflight workflow, but it suffers from repetition that hurts token efficiency and relies on inlined reference material plus missing sibling-file references that weaken progressive disclosure.

Suggestions

Consolidate the repeated 'createModel argument is not a vendor name' and 'never assume a model is already enabled' warnings into a single canonical section; cross-reference it from Best Practices instead of restating.

Move the Type Definitions and the full Available Providers/Models catalog into a references/ file (e.g. references/models.md) and link to it from the body, so the SKILL.md body stays a lean overview.

Either ship the referenced sibling skills (../auth-tool-cloudbase/SKILL.md, auth-web-cloudbase, web-development/browser-testing.md) in the bundle or remove the local-path references and describe the delegation generically, since the links currently resolve to nothing.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and does not over-explain basic concepts, but the same warnings are repeated many times — 'createModel argument is not a vendor name' (STOP section, Do-NOT list, Available Providers, Best Practices #3) and 'never assume a model is already enabled' (~4 times) — making it noticeably padded.	3 / 5
Actionability	Fully executable guidance: concrete generateText/streamText code, exact callCloudApi invocations with parameters, exact purchase URLs, and complete Type Definitions; copy-paste ready and covers the common cases.	5 / 5
Workflow Clarity	The two-step preflight is a clearly sequenced workflow (Step 0 → Preflight ① eligibility → Preflight ② group readiness) with explicit pass/fail branches, validation checkpoints, and feedback loops ('if missing, jump to step 4'), including a full-replacement warning for UpdateAIModel.	5 / 5
Progressive Disclosure	The file has good section headers and signals one-level references to sibling skills (auth-web-cloudbase, ai-model-nodejs, web-development/browser-testing.md), but no bundle files or references/scripts/assets directories exist, those referenced files are missing, and bulk reference content (Type Definitions, full provider catalog) is inlined in a single ~387-line file.	3 / 5
	Total	16 / 20 Passed

Description

95%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 with excellent trigger coverage and explicit what/when guidance plus negative-scope routing. The only weakness is mild verbosity that slightly dilutes the action list.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'call AI models via @cloudbase/js-sdk', 'generateText and streamText', 'ai.createModel with groups cloudbase, hunyuan-exp, or custom-*', 'two-step preflight' — with only minor gaps in coverage; not a 5 because the action list is padded rather than maximally tight.	4 / 5
Completeness	Explicitly answers both what ('call AI models... via @cloudbase/js-sdk', generateText/streamText) and when ('Use this skill when a browser/Web app... needs AI models'), plus explicit negative scope ('NOT for Node.js backend... Mini Program... image generation').	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms and framework names a user would actually say — 'React, Vue, Next, Nuxt, static sites, SPAs, dashboards, AI chat UI' plus Chinese variants 页面/前端/网页.	5 / 5
Distinctiveness Conflict Risk	Clear niche — browser/Web AI via js-sdk — with explicit routing away from ai-model-nodejs, ai-model-wechat, and image generation, giving minimal conflict risk.	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/.claude/skills/ai-model-web/SKILL.md
Commit: ef9f182

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.