writing-assistance-apis

Implements and debugs browser Summarizer, Writer, and Rewriter integrations in JavaScript or TypeScript web apps. Use when adding availability checks, model download UX, session creation, summarize or write or rewrite flows, streaming output, abort handling, or permissions-policy constraints for built-in writing assistance APIs. Don't use for generic prompt engineering, server-side LLM SDKs, or cloud AI services.

Quality

88%

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

Quality

Content

85%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.

A well-structured procedural skill with clear sequencing, validation checkpoints, and clean progressive disclosure to real bundle files. The main improvement area is adding a small inline code snippet so Claude can act without first opening the template.

Suggestions

Include a minimal inline session-creation code snippet in Step 3 so the core flow is executable without opening the template file.

Tighten a few justification clauses (e.g. the availability() capability-check note) to recover tokens.

Add a one-line example of a supported vs. unsupported language/format combination in Error Handling for NotSupportedError recovery.

Dimension	Reasoning	Score
Conciseness	Lean procedural prose with no padding about basic concepts; each step is actionable. A few explanatory clauses (e.g. 'Treat availability() as a capability check, not a guarantee') could be trimmed but earn their place.	4 / 5
Actionability	Concrete commands (`node scripts/find-writing-assistance-targets.mjs .`) and specific API calls (`availability()`, `create()`, `destroy()`, `monitor`, `AbortController`) with named error types. No inline code examples, but it correctly delegates to the template and reference files.	4 / 5
Workflow Clarity	Five clearly sequenced steps with an explicit 'Step 5: Validate behavior' checkpoint, feedback loops in the Error Handling section, and a final build/typecheck/test gate.	5 / 5
Progressive Disclosure	Overview body points to one-level-deep, clearly-signaled bundle files (references/.md, scripts/.mjs, assets/*.template.ts) with 'Read X when Y' conditions; all referenced paths exist as real files.	5 / 5
	Total	18 / 20 Passed

Description

92%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 precise, well-scoped description that names concrete capabilities, explicit trigger conditions, and clear boundaries against adjacent skills. The only minor gap is a few natural-language synonyms users might voice.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Implements and debugs', 'availability checks, model download UX, session creation, summarize or write or rewrite flows, streaming output, abort handling, or permissions-policy constraints' — giving comprehensive coverage of the capability surface.	5 / 5
Completeness	Explicitly states both what it does ('Implements and debugs browser Summarizer, Writer, and Rewriter integrations') and when to use it ('Use when adding availability checks...'), plus a 'Don't use for' boundary clause.	5 / 5
Trigger Term Quality	Strong natural and technical keywords ('summarize or write or rewrite flows', 'streaming output', 'abort handling'), but a few common synonyms a user might say (e.g. 'AI writing', 'text rewriting') are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche (built-in browser Writing Assistance APIs) with an explicit exclusion list ('Don't use for generic prompt engineering, server-side LLM SDKs, or cloud AI services'), minimizing conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: webmaxru/web-ai-agent-skills
Path: skills/writing-assistance-apis/SKILL.md
Commit: 89fee4a

Reviewed: 1 day 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.