Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By webmaxru
Code browser-native AI features in web apps: prompt, translation, language detection, proofreading, summarization, writing, and on-device ML model execution via WebNN with fallback support.
npx claudepluginhub webmaxru/ai-native-dev --plugin web-ai-skillsImplements and debugs browser Language Detector API integrations in JavaScript or TypeScript web apps. Use when adding LanguageDetector support checks, availability and model download flows, session creation, detect() calls, input-usage measurement, permissions-policy handling, or compatibility fallbacks for built-in language detection. Don't use for server-side language detection SDKs, cloud translation services, or generic NLP pipelines.
Implements and debugs browser Prompt API integrations in JavaScript or TypeScript web apps. Use when adding LanguageModel availability checks, session creation, prompt or promptStreaming flows, structured output, download progress UX, or iframe permission-policy handling. Don't use for server-side LLM SDKs, REST AI APIs, or non-browser providers.
Implements and debugs browser Proofreader API integrations in JavaScript or TypeScript web apps. Use when adding Proofreader availability checks, monitored model downloads, proofread flows, correction metadata handling, or permissions-policy checks for built-in proofreading. Don't use for generic prompt engineering, server-side LLM SDKs, or cloud AI services.
Implements and debugs browser Translator API integrations in JavaScript or TypeScript web apps. Use when adding Translator support checks, language-pair availability flows, model download UX, session creation, translate() or translateStreaming() calls, input-usage measurement, or permissions-policy handling for on-device translation. Don't use for server-side translation SDKs, cloud translation services, or generic multilingual content pipelines.
Implements and debugs browser WebMCP integrations in JavaScript or TypeScript web apps. Use when exposing imperative tools through document.modelContext (with a navigator.modelContext fallback), annotating HTML forms for declarative tools, handling agent-invoked form flows, or validating WebMCP behavior in the current Chrome preview. Don't use for server-side MCP servers, REST tool backends, or non-browser providers.
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Universal Translator — media generation tools for audio, image, video, and visualization
Discipline plugins for Claude Code — prompt engineering, agent dispatch, writing, and search
Browser automation CLI for AI agents. Navigate pages, fill forms, click buttons, take screenshots, and test web apps.
Claude Code skill pack for Wispr (18 skills)
Professional Agent Skills collection for full-stack development, logic planning, and multimedia processing.
Personal collection of agent skills using the open SKILL.md standard
Agent skills for Enonic XP development: server-side APIs, content modeling, content management, Guillotine GraphQL queries, Next.js headless integration, controller generation, event handling, and local app management.
A maintained collection of agent skills for modern browser Web AI APIs: Prompt API, Language Detector API, Translator API, Writing Assistance APIs, Proofreader API, WebMCP, and WebNN.
Standards and preview implementations still shift, browser behavior changes across milestones, and many ecosystem examples go stale quickly. These skills reduce that drift so generated or assisted code stays aligned with the current public specification state instead of relying on outdated snippets or guesswork.
I maintain the skills against current specification and platform changes. That work is informed by participation in the W3C Web Machine Learning Community Group, where several of these APIs are discussed in the open, and by my work as a Google Developer Expert in Web Technologies.
The repository follows the agentskills.io style: lean SKILL.md files, progressive disclosure through references/ and assets/, and deterministic helper scripts where guessing would be brittle.
All skills are available as a single agent plugin (web-ai-skills) through the AI-Native Dev plugin marketplace.
GitHub Copilot CLI
> /plugin marketplace add webmaxru/ai-native-dev
> /plugin install web-ai-skills@webmaxru-ai-native-dev
VS Code (GitHub Copilot)
Add the marketplace to your settings.json:
"chat.plugins.marketplaces": [
"webmaxru/ai-native-dev"
]
Then open the Extensions sidebar, search @agentPlugins, and install web-ai-skills.
Alternatively, run Chat: Install Plugin From Source from the Command Palette and enter https://github.com/webmaxru/ai-native-dev.
Claude Code
> /plugin marketplace add webmaxru/ai-native-dev
> /plugin install web-ai-skills@webmaxru-ai-native-dev
Use Agent Package Manager (APM) for per-skill installs:
apm init # once per project
apm install webmaxru/web-ai-agent-skills/skills/SKILL_NAME
skills/prompt-api is the main production-style example skill in the repository. It is scoped to browser Prompt API work in JavaScript or TypeScript web apps.
Install with APM:
apm install webmaxru/web-ai-agent-skills/skills/prompt-api
Install with npm:
npx skills add webmaxru/web-ai-agent-skills --skill prompt-api
It covers:
LanguageModelIts support files are split by purpose:
references/prompt-api-reference.md for API surface, validation rules, and platform constraintsreferences/examples.md for valid prompt shapes and implementation patternsreferences/compatibility.md for availability, flags, typings, and breaking-change mappingreferences/polyfills.md for native-first polyfill strategies and backend configurationreferences/troubleshooting.md for runtime failure cases such as missing LanguageModel, iframe issues, and stale session cleanupassets/language-model-service.template.ts for a reusable wrapper templatescripts/find-frontend-targets.mjs for deterministic scanning of likely web entry points and Prompt API markersskills/language-detector-api is scoped to browser Language Detector API integrations in JavaScript or TypeScript web apps.
Install with APM:
apm install webmaxru/web-ai-agent-skills/skills/language-detector-api
Install with npm:
npx skills add webmaxru/web-ai-agent-skills --skill language-detector-api
It covers: