brand-voice-extractor

Analyze a company's published content to extract their brand voice, writing style, and tone guidelines. Reads 10-20 of their best content pieces and produces a brand voice profile covering tone, vocabulary level, sentence structure, formatting patterns, CTAs, and target persona. Useful before writing outreach, content, or campaigns that should match a client's existing voice.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

65%

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

The body is a well-structured, actionable instruction-only skill with clear sequencing, but it is longer than necessary and inlines material that would benefit from being split into reference files. It also lacks validation checkpoints in its fetch/analyze workflow.

Suggestions

Move the large Phase 4 brand-voice-profile output template and the A–F dimension checklists into a reference file (e.g. references/profile-template.md) and link to it from the body, reducing SKILL.md length and improving progressive disclosure.

Add an explicit validation checkpoint in Phase 2 (e.g., confirm each page returned substantial body text; skip and flag pages that failed to fetch) before proceeding to analysis.

Tighten the dimension checklists to the highest-signal items per category to reduce token cost without losing the actionable guidance.

Dimension	Reasoning	Score
Conciseness	It assumes Claude's competence (no preamble on what brand voice or WebFetch is) but the ~210-line body inlines an exhaustive A–F dimension enumeration and a large Phase 4 output template that could be trimmed, so it is mostly efficient but not fully lean.	2 / 3
Actionability	Despite having no code (explicitly an agent-executed skill), it gives concrete, copy-ready guidance: fixed selection counts (8-10 blog posts, 2-3 landing pages), a WebFetch extraction procedure, and a fully specified output template — actionable enough for the top anchor.	3 / 3
Workflow Clarity	The four phases are clearly sequenced, but there are no validation checkpoints (e.g., confirming a page fetched cleanly or that extracted text is substantial before analyzing), leaving checkpoints implicit.	2 / 3
Progressive Disclosure	It is well-sectioned but monolithic — the large Phase 4 template and full dimension checklists are inlined rather than split into one-level-deep reference files, and the skill exceeds the under-50-lines carve-out that would otherwise allow a 3.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 concrete, trigger-rich, and explicitly pairs what-it-does with when-to-use-it in third person, hitting the top anchor on every dimension. It is a strong, low-conflict description.

Dimension	Reasoning	Score
Specificity	It lists multiple concrete actions and outputs — 'extract their brand voice, writing style, and tone guidelines' and a profile 'covering tone, vocabulary level, sentence structure, formatting patterns, CTAs, and target persona', matching the multi-action anchor rather than the single-action level 2.	3 / 3
Completeness	It answers both what (analyze content, extract voice, produce profile) and when via the explicit 'Useful before writing outreach, content, or campaigns...' clause, satisfying the explicit-trigger requirement for level 3.	3 / 3
Trigger Term Quality	It surfaces natural terms a user would say — 'brand voice', 'writing style', 'tone guidelines', 'outreach', 'campaigns' — with good coverage; it uses third person ('Analyze', 'Reads') so no voice penalty applies.	3 / 3
Distinctiveness Conflict Risk	Its niche — extracting a company's brand voice from published content for matching future copy — is distinct with triggers unlikely to fire for unrelated skills, so it does not sit at the overlap-prone level 2.	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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/brand/capabilities/brand-voice-extractor/SKILL.md
Commit: 8866b2a

Reviewed: 2 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.