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

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

92%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, concise procedural skill with strong actionability and validation checkpoints. Its main weakness is progressive disclosure: the body points to six bundle files (references, assets, scripts) that are not present, making the otherwise excellent reference navigation non-functional.

Suggestions

Ship the referenced bundle files (references/writing-assistance-reference.md, examples.md, compatibility.md, troubleshooting.md, assets/writing-assistance-session.template.ts, scripts/find-writing-assistance-targets.mjs) so the 'Read X when Y' navigation resolves.

If any reference is not essential, remove the dangling pointer from the body rather than leaving a dead path.

Consider inlining a minimal executable snippet of the session wrapper in SKILL.md so the skill remains actionable even before the asset file is loaded.

Dimension	Reasoning	Score
Conciseness	Lean numbered procedures with no padding about what the APIs are or basic programming concepts; every line delivers concrete guidance (e.g., 'Gate session creation behind the API's availability() method', 'Use AbortController for cancelable create and run calls').	3 / 3
Actionability	Highly actionable for an instruction-oriented skill: exact command 'node scripts/find-writing-assistance-targets.mjs .', specific API methods/options (availability(), create() monitor option, destroy()), and keyed error handling for NotAllowedError, NotSupportedError, and QuotaExceededError.	3 / 3
Workflow Clarity	Clear five-step sequence with explicit validation in Step 5 ('Validate behavior'), stop/ask checkpoints in Steps 1-2, and a feedback loop ('Run the workspace build, typecheck, or tests after editing') plus an Error Handling section mapping exceptions to fixes.	3 / 3
Progressive Disclosure	References are well-signaled and one-level-deep with clear 'Read X when Y' triggers (writing-assistance-reference.md, examples.md, compatibility.md, troubleshooting.md, the .ts template, and the .mjs script), but none of these bundle files actually exist on disk, so the navigation is broken in practice.	2 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, third-person description that names concrete capabilities, provides explicit 'Use when' triggers, and draws clear boundaries with a 'Don't use for' clause. It is concise yet comprehensive and unlikely to fire for the wrong skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Implements and debugs browser Summarizer, Writer, and Rewriter integrations' plus 'availability checks, model download UX, session creation, summarize or write or rewrite flows, streaming output, abort handling, or permissions-policy constraints'.	3 / 3
Completeness	Explicitly answers both what ('Implements and debugs browser Summarizer, Writer, and Rewriter integrations in JavaScript or TypeScript web apps') and when ('Use when adding availability checks, model download UX, session creation...'), satisfying the explicit-trigger requirement; not capped at 2.	3 / 3
Trigger Term Quality	Natural trigger terms users would say are well covered: 'Summarizer, Writer, and Rewriter', 'summarize or write or rewrite flows', 'streaming output', 'abort handling', all tied to an explicit 'Use when adding...' clause.	3 / 3
Distinctiveness Conflict Risk	Clear niche (built-in browser writing assistance APIs) with distinct triggers and an explicit exclusion clause ('Don't use for generic prompt engineering, server-side LLM SDKs, or cloud AI services') that prevents overlap with adjacent skills.	3 / 3
	Total	12 / 12 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
referenced_paths_exist	Referenced path issues: 8 missing	Warning

	Total	15 / 16 Passed

Repository: webmaxru/web-ai-agent-skills
Path: skills/writing-assistance-apis/SKILL.md
Commit: f4c5a23

Reviewed: 13 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.