brandkit

Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.

Quality

52%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/brandkit/SKILL.md

Quality

Content

38%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 contains genuinely useful design direction (panel systems, layout grids, palette discipline, a prompt template) but delivers it as a ~790-line monolith padded with repeated adjective lists. It would be far stronger as a lean core workflow plus one-level-deep reference files for visual modes and layout specs, with the implicit strategy-to-prompt sequence made explicit.

Suggestions

Split the eight VISUAL MODES, the layout specifications, and the category/symbol table into reference files (e.g. references/visual-modes.md, references/layouts.md) and keep SKILL.md as a lean overview with well-signaled links.

Deduplicate the repeated quality-bar sections (REFERENCE STYLE DNA, PREMIUM DETAIL LANGUAGE, ANTI-GENERIC RULES, FINAL OUTPUT STANDARD) into one compact principles section — the same adjectives currently appear four times.

State the workflow explicitly as a numbered sequence (infer strategy -> select logo concept method -> choose layout and visual mode -> apply palette/text/mockup rules -> render via the prompt template) with a final checklist validating the board against the anti-generic rules.

Dimension	Reasoning	Score
Conciseness	The ~790-line body systematically restates the same adjectival quality bar across sections — 'intentional, premium, minimal, coherent' appears in REFERENCE STYLE DNA, PREMIUM DETAIL LANGUAGE, ANTI-GENERIC RULES, and FINAL OUTPUT STANDARD — and many sections are pure adjective lists ('quiet, functional, emotional, technical'). Verbose with several padded sections; not 1 because it does not explain concepts Claude already knows, and not 3 because the redundancy is systematic rather than incidental.	2 / 5
Actionability	There are concrete artifacts — the 3x3 panel system with nine named panels, the 2x3 layout, specific palette combos ('black + cyan + muted coral'), tagline examples, and an internal prompt template — but no worked example (a filled-in prompt for a real brand) and much of the guidance is unexecutable vibe language ('feel visually expensive', 'make it abstract and premium'). Between 'some concrete guidance but incomplete' and 'mostly executable'; the gaps keep it at 3.	3 / 5
Workflow Clarity	A rough sequence is present — infer brand strategy, choose a logo concept method, pick layout and visual mode, apply palette/text/mockup rules, then use the prompt template — but it is implicit (the reader must assemble the order from section placement) and there are no checkpoints for verifying a board against the anti-generic rules. Sequence exists, checkpoints missing; not 4 because the order is never stated as an explicit workflow.	3 / 5
Progressive Disclosure	There are no bundle files at all (no references/, scripts/, or assets/ directories) and the entire ~790-line body is inlined in SKILL.md. Content that clearly belongs in separate files — the eight VISUAL MODES, the layout specs, and the category/symbol table — is inlined in one monolithic document. Not 3 because even basic splitting (modes into a reference file) would materially improve it, and the skill is far beyond the under-50-line simple-skill exception.	2 / 5
	Total	10 / 20 Passed

Description

66%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 clearly conveys what the skill produces with strong natural trigger terms, but it is written in marketing register ('Trained for', 'Optimized for', 'premium') rather than operational language, and lacks any explicit when-to-use guidance. Adding a 'Use when...' clause and trimming the buzzword-heavy second and third sentences would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for a brand kit, brand guidelines board, logo system, identity deck, or brand overview image.'

Replace the padded 'Trained for minimalist, cinematic, editorial...' and 'Optimized for intentional logo concepting...' qualifiers with one or two concrete capability statements (e.g. 'Generates a single composed brand-kit image with logo, palette, typography, and application mockup panels in a 3x3 grid').

Include common user synonyms such as 'branding', 'brand identity', and 'logo design' in the trigger coverage.

Dimension	Reasoning	Score
Specificity	Names several concrete deliverables — 'creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations' — but pads them with marketing qualifiers ('Trained for', 'Optimized for') and omits the actual generation workflow. Not 5 because coverage has gaps and filler; not 3 because it lists more than 1-2 concrete actions.	4 / 5
Completeness	The 'what' is clear (generates brand-kit overview images and identity boards), but the description contains no 'Use when...' clause or equivalent explicit usage guidance — the separate frontmatter triggers block is terse phrases, not a when-to-use statement. Per rubric guideline, missing 'when' guidance caps completeness at 3.	3 / 5
Trigger Term Quality	Natural phrases users would say — 'brand kit', 'brand-guidelines boards', 'logo systems', 'identity decks' — reinforced by the frontmatter triggers list. Not 5 because common variants like 'branding', 'brand identity', or 'logo design' are missing.	4 / 5
Distinctiveness Conflict Risk	The brand-kit/identity-board niche is clearly distinguishable from general image-generation or document skills, with distinct triggers. Not 5 due to minor overlap risk with general logo-design or design-guideline skills.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (823 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: nexu-io/open-design
Path: skills/brandkit/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.