brand-extract

Extract a complete Brand Kit from a live website by driving the in-app browser. Use when a brand-extraction project opens with a site in the Browser tab, or when the user asks to "extract a brand", "pull the brand from <url>", "get the colors/fonts/logo from this site", or build a brand/design system from a reference website. Pairs with the agent-browser tool for measurement and pauses for the user when an anti-bot wall blocks the page.

Quality

88%

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

77%

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

The body is highly actionable with a well-sequenced, validated workflow and concrete code/schema, but it is a long monolithic document that does not offload detail into bundle reference files, and it carries some repeat padding that hurts conciseness.

Suggestions

Move the full brand.json schema and the anti-bot question-form example into reference files under references/ and link to them one level deep, splitting the monolithic body into a leaner overview.

Tighten repeated caveats — the 'that safety net is no substitute for picking/saving the real...' phrasing appears twice (logo and imagery sections); state the rule once.

Condense the logo/imagery harvesting prose into a short checklist of file conventions and selection rules to reduce token weight while keeping the guidance actionable.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence, but ~200 lines with some padded stretches — the 'that safety net is no substitute for...' caveat is repeated twice, and prose around imagery/logo selection could be tightened — so it earns the mid anchor rather than the lean top anchor.	2 / 3
Actionability	Provides fully executable commands ('agent-browser get url', 'od brand preview <brandId>', 'od brand finalize <brandId> --json'), a complete copy-paste brand.json schema, exact semantic color roles, and concrete file-path conventions (logos/, imagery/, fonts/), matching the top anchor.	3 / 3
Workflow Clarity	A clear three-step chain (Measure → Synthesize → Build) with numbered sub-steps, an explicit anti-bot checkpoint that pauses for the user, and a validation feedback loop ('If finalize reports a validation error, fix brand.json and run it again') plus progressive preview checkpoints, matching the top anchor.	3 / 3
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent), and the body is a monolithic ~200-line wall of text with all detail inline; the only mentioned reference (brand-extract/templates/brand-kit.html) is a daemon template outside the skill bundle, so content that could be split out (the JSON schema, the anti-bot form) remains inline.	2 / 3
	Total	10 / 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 strong across all dimensions: it states concrete capabilities, gives natural trigger phrases, and pairs an explicit 'Use when' clause with a distinctive niche. It is written in third person with no fluff.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Extract a complete Brand Kit from a live website by driving the in-app browser', 'get the colors/fonts/logo from this site', 'build a brand/design system' — matching the top anchor for listing specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ('Extract a complete Brand Kit...') and when with an explicit 'Use when...' clause listing multiple triggering situations, matching the top anchor.	3 / 3
Trigger Term Quality	Covers natural user phrasings directly — 'extract a brand', 'pull the brand from <url>', 'get the colors/fonts/logo from this site', 'build a brand/design system' — giving good coverage of terms users would actually say.	3 / 3
Distinctiveness Conflict Risk	A clear niche — brand extraction from a live site via the in-app browser using agent-browser — with distinct triggers unlikely to fire for unrelated skills.	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: nexu-io/open-design
Path: skills/brand-extract/SKILL.md
Commit: f2760fd

Reviewed: about 15 hours 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.