Writing Assistance Apis

Teaches Claude how to wire up the browser's built-in Summarizer, Writer, and Rewriter APIs in your JavaScript or TypeScript web app. You'd reach for this when you want on-device text generation without sending data to the cloud: checking availability, handling model downloads with progress UI, creating sessions with the right options, streaming or batch output, and dealing with permissions-policy constraints in iframes. The procedures walk through feature detection, choosing the right API surface for your task, building guarded session wrappers, and wiring up fallback UX for unsupported devices. It's opinionated about keeping these APIs for their intended purpose and switching to Prompt API when you're really building a chatbot. Includes a find-targets script, reference docs, and explicit TypeScript templates.

skills.sh installs: 152
GitHub stars: 31
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add webmaxru/agent-skills --skill writing-assistance-apis --agent claude-code

Installs into .claude/skills of the current project.

Files

Writing Assistance APIs

Procedures

Step 1: Identify the browser integration surface

Inspect the workspace for browser entry points, UI handlers, and any existing AI abstraction layer.
Execute node scripts/find-writing-assistance-targets.mjs . to inventory likely frontend files and existing Summarizer, Writer, or Rewriter usage when a Node runtime is available.
If a Node runtime is unavailable, inspect the nearest package.json, HTML entry point, and framework bootstrap files manually to identify the browser app boundary.
If the workspace contains multiple frontend apps, prefer the app that contains the active route, component, or user-requested feature surface.
If the inventory still leaves multiple plausible frontend targets, stop and ask which app should receive the Writing Assistance API integration.
If the project is not a browser web app, stop and explain that this skill does not apply.

SKILL.md on GitHub