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

88%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.

An excellent, highly actionable skill body: exact commands, a complete data schema, explicit hard rules, and a validation loop. Its only real weaknesses are mild redundancy in the progressive-preview instruction and the anti-bot guidance, and a monolithic single-file layout that inlines a large JSON spec.

Suggestions

State the preview-early rule once (in the Synthesize section) and cross-reference it from the brand.html section instead of repeating it.

Move the full brand.json schema example into a reference file (e.g., references/brand-schema.md) and keep a skeletal shape inline, reducing SKILL.md's token footprint.

Fold the Safety section's anti-bot bullet into a single cross-reference to the existing anti-bot subsection to remove the duplicated guidance.

Dimension	Reasoning	Score
Conciseness	The body is dense, imperative, and assumes Claude's competence — no known concepts are re-explained — but the "preview early, don't batch" instruction is repeated nearly verbatim in the brand.html section and again in "2. Synthesize", and the anti-bot guidance is restated in the Safety section, so minor trimming is possible.	4 / 5
Actionability	Fully executable guidance throughout: exact commands ("agent-browser get url", "od brand preview <brandId>", "od brand finalize <brandId> --json"), a complete copy-paste brand.json schema with a worked example, literal question-form markup for the anti-bot pause, and explicit hard rules per field group.	5 / 5
Workflow Clarity	The three-step chain (Measure → Synthesize → Build & register) is clearly sequenced in order with an explicit validation feedback loop ("If finalize reports a validation error, fix brand.json and run it again"), a user-pause checkpoint at the anti-bot wall, and progressive preview checkpoints after each field group.	5 / 5
Progressive Disclosure	No bundle files exist and the body is a single well-sectioned, one-level document with no nested references. The ~30-line brand.json example and the BRAND.md outline are inline; they are the core spec, but they could live in a reference file to keep SKILL.md leaner, which is a minor organization gap.	4 / 5
	Total	18 / 20 Passed

Description

87%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.

A strong description: third-person, concrete about the mechanism (browser-driven measurement), with an explicit "Use when" clause and multiple natural quoted trigger phrases. The only weakness is that it names the tool integration and pause behavior but only implies the full scope of the kit it produces.

Suggestions

Enumerate the kit's outputs (identity, semantic color palette, typography, logo candidates, voice, imagery) in one clause to lift specificity to comprehensive.

Add one or two missing natural trigger variants such as "brand kit" or "brand guidelines" to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	The description states several concrete actions — "Extract a complete Brand Kit from a live website by driving the in-app browser", "Pairs with the agent-browser tool for measurement and pauses for the user when an anti-bot wall blocks the page" — but does not enumerate the kit's contents (identity, palette, typography, voice, imagery), so coverage has minor gaps rather than being comprehensive.	4 / 5
Completeness	It explicitly answers both what ("Extract a complete Brand Kit from a live website by driving the in-app browser") and when ("Use when a brand-extraction project opens with a site in the Browser tab, or when the user asks to...") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	It quotes multiple natural user phrasings — "extract a brand", "pull the brand from <url>", "get the colors/fonts/logo from this site", "build a brand/design system from a reference website" — giving good synonym coverage, though a few common variants (e.g., "brand kit", "brand guidelines") are missing.	4 / 5
Distinctiveness Conflict Risk	The niche is clear — measuring a live site in the in-app browser to produce a brand kit — with distinct quoted triggers and an explicit pairing with the agent-browser tool, so the risk of triggering for the wrong skill is minimal.	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: nexu-io/open-design
Path: skills/brand-extract/SKILL.md
Commit: 1b47e60

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.