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

76%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/brand/capabilities/brand-voice-extractor/SKILL.md

Quality

Content

68%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 body is well-structured and actionable with a concrete phased process and a useful output template, and it assumes Claude's intelligence rather than padding. Its main gap is the absence of validation/verification checkpoints in a batch fetch-and-analyze workflow, which caps workflow clarity.

Suggestions

Add a validation/verification checkpoint between Phase 2 (fetch) and Phase 3 (analyze) — e.g., confirm each page fetched successfully, retry failures, and flag pages with insufficient text before analysis.

Tighten the opening paragraph (line 14) since it restates the frontmatter description, and consider trimming the output template to its essential structure.

Specify concrete methods for the vaguer analysis dimensions (e.g., how to estimate reading level, how to detect ghost-written content) so the guidance is fully executable.

Dimension	Reasoning	Score
Conciseness	Content is task-focused and assumes Claude's competence without explaining basic concepts, but the intro paragraph restates the description and the large output template could be slightly tightened, fitting the score-4 'efficient with minor trim opportunities' anchor.	4 / 5
Actionability	Provides concrete phased process, specific selection heuristics with numbers, well-defined analysis dimensions, and a copy-paste-ready output template — mostly executable guidance with minor gaps (e.g., how to estimate reading level is unspecified).	4 / 5
Workflow Clarity	Phases 1-4 are clearly sequenced, but this is a batch operation (fetching/analyzing 10-20 pages) with no validation or verification checkpoints (e.g., fetch-failure retry, completeness check), so per the batch-operation cap workflow_clarity is capped at 3.	3 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets are empty) and the skill is self-contained with well-organized sections (Quick Start, Inputs, Process, Tips, Dependencies); the large output template is appropriately inline, giving good structure with minor organization gaps.	4 / 5
	Total	15 / 20 Passed

Description

83%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 specific, well-triggered, and clearly distinct, with concrete actions and natural keywords. Its main weakness is the 'when' clause being phrased as 'Useful before...' rather than an explicit 'Use when...' trigger phrase.

Suggestions

Replace 'Useful before writing outreach...' with an explicit 'Use when writing outreach, content, or campaigns that should match a client's existing voice.' trigger clause.

Add common synonyms such as 'tone of voice' or 'style guide' to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'extract their brand voice, writing style, and tone guidelines' and 'produces a brand voice profile covering tone, vocabulary level, sentence structure, formatting patterns, CTAs, and target persona' — with comprehensive coverage, matching the score-5 anchor.	5 / 5
Completeness	Clearly states what it does and provides equivalent explicit trigger guidance via 'Useful before writing outreach, content, or campaigns that should match a client's existing voice', but the 'when' could be a more explicit 'Use when...' trigger phrase, placing it at 4 rather than 5.	4 / 5
Trigger Term Quality	Good natural keyword coverage ('brand voice', 'writing style', 'tone guidelines', 'outreach, content, or campaigns') but missing common synonyms like 'tone of voice' or 'style guide'; a few natural terms absent, fitting the score-4 anchor.	4 / 5
Distinctiveness Conflict Risk	'Brand voice extractor' is a clear niche with distinct triggers (brand voice, tone, writing style) and minimal overlap risk with other skills, matching the score-5 anchor.	5 / 5
	Total	18 / 20 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: 2523432

Reviewed: 7 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.