proofreader-api

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.

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.

The body is concise, highly actionable, and built around a clearly sequenced five-step workflow with validation checkpoints and named error-handling paths. Its main weakness is progressive disclosure: the skill points to six bundle files in references/, scripts/, and assets/ that are not present in the workspace.

Suggestions

Provide the referenced bundle files — references/proofreader-reference.md, references/examples.md, references/compatibility.md, references/troubleshooting.md, assets/proofreader-session.template.ts, and scripts/find-proofreader-targets.mjs — so the clearly-signaled navigation actually resolves.

If some references are optional, mark which are required vs. optional and inline the single most critical one (e.g., the availability()/create() option shape) so the skill remains usable without the bundle.

Consider adding one small copy-paste-ready code snippet for the core guarded wrapper so the integration pattern is executable directly from SKILL.md when the template asset is unavailable.

Dimension	Reasoning	Score
Conciseness	Lean imperative prose with no padding about what a browser API or proofreading is; every instruction assumes Claude's competence and earns its place ('Gate session creation behind Proofreader.availability()...'). Not score 2 because there is no unnecessary explanation to tighten.	3 / 3
Actionability	Concrete commands and specific APIs throughout — 'node scripts/find-proofreader-targets.mjs .', 'Proofreader.availability()', 'create()', 'measureInputUsage()', 'AbortController', 'destroy()' — plus named error types (NotAllowedError, NotSupportedError). Per scoring notes, an instruction-only integration skill is not penalized for lacking a code block when guidance is this actionable.	3 / 3
Workflow Clarity	Five explicitly sequenced steps with a dedicated validation step (Step 5) and feedback loops — 'retry once only after confirming...', 'Run the workspace build, typecheck, or tests after editing' — matching the score-3 anchor of clear sequence with explicit validation and error-recovery checkpoints.	3 / 3
Progressive Disclosure	References are one-level-deep and clearly signaled with conditional 'Read X when Y' triggers (proofreader-reference.md, examples.md, compatibility.md, troubleshooting.md, proofreader-session.template.ts, find-proofreader-targets.mjs), but the referenced bundle directories (references/, scripts/, assets/) do not exist, so navigation is broken. Not 3 because the cited files are missing; not 1 because the structure is well-signaled rather than monolithic or nested.	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.

The description is specific, complete, and distinct: it names concrete capabilities, gives explicit 'Use when' triggers, and scopes itself with 'Don't use for' exclusions. It avoids vagueness and over-claiming throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Implements and debugs browser Proofreader API integrations', 'availability checks, monitored model downloads, proofread flows, correction metadata handling' — matching the score-3 anchor of several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ('Implements and debugs browser Proofreader API integrations in JavaScript or TypeScript web apps') and when ('Use when adding Proofreader availability checks...'), plus an explicit 'Don't use for' exclusion clause.	3 / 3
Trigger Term Quality	Natural terms a user would say are well covered — 'Proofreader', 'proofread flows', 'model downloads', 'correction metadata', 'permissions-policy checks' — giving good coverage of the user's vocabulary rather than only jargon.	3 / 3
Distinctiveness Conflict Risk	A clear niche (built-in browser Proofreader API) with distinct triggers and explicit exclusions — 'Don't use for generic prompt engineering, server-side LLM SDKs, or cloud AI services' — making it unlikely to trigger for the wrong skill.	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: 9 missing	Warning

	Total	15 / 16 Passed

Repository: webmaxru/web-ai-agent-skills
Path: skills/proofreader-api/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.