writing-voice

House voice for substantial prose: clear, direct, natural, and read-aloud friendly. Use for voice passes, tone work, rewrites, or prose that sounds corporate or AI-shaped.

Quality

91%

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

92%

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

A lean, highly actionable instruction-only skill with a clear workflow and no wasted tokens. Its single weak point is progressive disclosure: bundle reference files that are meant to be loaded conditionally are not navigated to from the overview.

Suggestions

Add a short section in SKILL.md pointing to the reference files, e.g. under a 'References' heading: 'For Discord/casual chat: see [discord-voice.md](references/discord-voice.md). For longer technical explanations: see [technical-explanation.md](references/technical-explanation.md).'

State when each reference should be loaded (e.g. 'Load technical-explanation.md when writing tutorials, architecture notes, or onboarding docs') so the one-level-deep navigation is explicit rather than implicit.

Dimension	Reasoning	Score
Conciseness	The body is lean throughout — it never explains concepts Claude already knows, and every section (Ear Pass, Working Style, Punctuation, Generic-Language Pass) earns its tokens with direct guidance.	3 / 3
Actionability	Concrete, copy-ready instruction throughout: a 3-step Ear Pass, specific punctuation rules ("Prefer periods. Use colons when..."), and named phrases/words to cut ("it is important to note," "leverage," "utilize," "facilitate").	3 / 3
Workflow Clarity	The Ear Pass is a clearly sequenced mark → revise → stop process with an explicit completion checkpoint ("Stop when the prose sounds natural and specific, not merely smooth"); no destructive or batch operation is involved, so the validation cap does not apply.	3 / 3
Progressive Disclosure	The body is well organized into clean sections, but two relevant reference files exist in references/ (discord-voice.md, technical-explanation.md) and neither is linked or signaled from SKILL.md, fitting the score-2 anchor of references present but not clearly signaled.	2 / 3
	Total	11 / 12 Passed

Description

90%

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 tight, well-targeted description that states both purpose and trigger conditions in natural user language. The only soft spot is specificity, where the listed actions are use-cases rather than concrete operations.

Dimension	Reasoning	Score
Specificity	Names the domain ("House voice for substantial prose") and several tasks ("voice passes, tone work, rewrites"), but these read as use-case triggers rather than concrete operational verbs like the score-3 anchor ("Extract text... fill forms, merge documents").	2 / 3
Completeness	Explicitly answers both what ("House voice... clear, direct, natural, and read-aloud friendly") and when ("Use for voice passes, tone work, rewrites, or prose that sounds corporate or AI-shaped"), matching the score-3 anchor's what-and-when-with-trigger pattern.	3 / 3
Trigger Term Quality	Natural terms a user editing prose would actually say — "voice passes," "tone work," "rewrites," and the complaint "prose that sounds corporate or AI-shaped" — give good coverage of how the need is voiced.	3 / 3
Distinctiveness Conflict Risk	The prose-voice niche with triggers around tone/rewrites/AI-shaped writing is a clear, distinct scope unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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: EpicenterHQ/epicenter
Path: .agents/skills/writing-voice/SKILL.md
Commit: cb12bcc

Reviewed: 3 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.