cw-voice-check

Diagnose whether writing matches the active writer, project, publication, and platform voice context, then offer a closer revision. Use when the user asks whether text sounds like them, feels generic, or has drifted from an established voice.

Quality

80%

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

82%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.

The content is a tight, well-structured instruction-only skill that assumes Claude's intelligence and gives concrete diagnostic and output guidance. Its weakness is the absence of worked examples and the external, cascading reference path.

Suggestions

Add one short worked example showing a brief input passage, a sample drift quote, and a closer revision so the Output format is unambiguous.

Inline or summarize the essential bits of context-contract.md within SKILL.md, or confirm the ../../references path resolves in the deployed plugin, so the one-level-deep reference is self-contained.

Optionally add a single diagnostic checklist item that names a quick sanity check (e.g. re-read the passage aloud against the writer's VOICE.md) to give the workflow an explicit checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: it gives an authority order, a focused diagnose checklist, and an output format with no padding or explanation of what voice or style are, so every token earns its place.	5 / 5
Actionability	Guidance is concrete and specific (numbered authority order, seven-item diagnose checklist, five-part output format), but it lacks any worked example of a diagnosis or a sample "closer revision", which keeps it just below fully copy-paste-ready.	4 / 5
Workflow Clarity	The three phases (Load Voice Context, Diagnose, Output) are clearly sequenced with headers, and "Name the sources used" acts as a soft verification checkpoint, but there is no explicit feedback loop; this is acceptable since the task is read-only analysis, not a destructive or batch operation.	4 / 5
Progressive Disclosure	The body is a concise overview with well-organized sections and one clearly signaled one-level-deep reference (../../references/context-contract.md), but that reference points outside the skill bundle and the authority order then cascades into multiple external files, a minor organization gap below the cleanly-split 5 anchor.	4 / 5
	Total	17 / 20 Passed

Description

78%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.

The description is strong: it clearly answers both what the skill does and when to use it, with natural trigger phrases and a distinct voice-matching niche. The main gap is specificity, where only two fairly abstract actions are named rather than a comprehensive concrete list.

Dimension	Reasoning	Score
Specificity	Names the voice-matching domain and two concrete actions ("Diagnose whether writing matches..." and "offer a closer revision"), matching the anchor for 1-2 concrete actions without being comprehensive; it stops short of the several specific actions needed for a 4.	3 / 5
Completeness	It explicitly states what it does (diagnose voice match and offer a revision) and when to use it with concrete trigger phrases ("Use when the user asks whether text sounds like them..."), matching the anchor for clearly answering both what and when.	5 / 5
Trigger Term Quality	Natural user phrases like "whether text sounds like them", "feels generic", and "drifted from an established voice" give good coverage, but common synonyms (e.g. "tone", "writing style", "make it sound like me") are missing, so it is not a 5.	4 / 5
Distinctiveness Conflict Risk	The voice-context niche with writer/project/publication authority is mostly distinct from generic editing or style skills, but there is minor overlap risk with broad style-guidance skills, keeping it just below the minimal-conflict 5 anchor.	4 / 5
	Total	16 / 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: EveryInc/compound-writing
Path: skills/cw-voice-check/SKILL.md
Commit: 18702f0

Reviewed: 6 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.