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

61%

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 ./.agents/skills/brandkit/SKILL.md

The canonical home for this skill is brandkit in Leonxlnx/taste-skill

Quality

Content

57%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 rich with genuinely actionable, domain-specific guidance (panel system, prompt template, per-category logic) and is well-organized internally. Its weaknesses are verbosity from repeated mode blocks and overlapping avoid-lists, an implicit rather than explicit workflow, and a lack of file-level progressive disclosure for such a long skill.

Suggestions

Externalize the VISUAL MODES catalog and the COLOR DISCIPLINE palettes into a references/ file (e.g., references/visual-modes.md) referenced from the body, turning the 800-line monolith into a lean overview plus one-level-deep references.

Consolidate the redundant 'Avoid' / 'ANTI-GENERIC RULES' / 'Bad text' lists into a single anti-patterns section to remove repetition and improve conciseness.

Render the workflow as a short numbered sequence (infer strategy -> choose mode -> choose layout -> fill prompt template -> generate -> validate against output standard) with the FINAL OUTPUT STANDARD restated as concrete, checkable criteria.

Dimension	Reasoning	Score
Conciseness	Largely task-relevant rather than lecturing on basics, but the ~800-line body repeats near-identical Use-for/Visual-cues/Logo-logic/Mood blocks across 8 visual modes and stacks several overlapping 'Avoid' lists — mostly efficient but could be tightened, anchor 3 not 2.	3 / 5
Actionability	Provides concrete layouts, a defined 9-panel system, a fill-in PROMPT TEMPLATE, per-category symbol-logic examples, and example taglines — mostly executable guidance with minor gaps (no fully filled end-to-end example), anchor 4 not 5.	4 / 5
Workflow Clarity	A recognizable flow exists (infer strategy, pick mode/layout, fill template, check output) but steps are not crisply numbered and the FINAL OUTPUT STANDARD is an aspirational quality list rather than concrete validation checkpoints — anchor 3 not 4.	3 / 5
Progressive Disclosure	Internal section structure is well-organized via headers, but it is a monolithic single file with no bundle references, and an 800-line catalog (visual modes, palettes, examples) that could be externalized is inlined — anchor 3 not 4.	3 / 5
	Total	13 / 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 and names a distinct, well-scoped niche, with good natural keyword coverage. Its main weakness is the absence of any explicit 'when to use it' trigger guidance, which caps completeness at 3.

Suggestions

Add an explicit 'Use when...' clause naming concrete user triggers (e.g., 'Use when the user asks for a brand kit, brand guidelines, logo system, identity deck, or visual-world presentation board').

Trim the adjective-heavy optimization list ('intentional logo concepting, refined composition, sparse typography...') in favor of one or two more concrete output actions to lift specificity toward 5.

Include a natural synonym or file-format cue users might say (e.g., 'brand board', 'brand deck', 'logo presentation') to round out trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete deliverables ('brand-guidelines boards, logo systems, identity decks, and visual-world presentations'), but leans on quality adjectives rather than actions, leaving minor coverage gaps — fits anchor 4, not 5.	4 / 5
Completeness	The 'what' is clear (premium brand-kit image generation for boards/decks/presentations) but there is no 'Use when...' or equivalent explicit trigger clause, so completeness is capped at 3 per the guidelines.	3 / 5
Trigger Term Quality	Good coverage of natural brand-design terms ('brand-kit', 'logo systems', 'brand-guidelines boards', 'identity decks') plus a domain list, but a few natural synonyms are missing — anchor 4, not 5.	4 / 5
Distinctiveness Conflict Risk	The 'brand-kit image generation' niche is mostly distinct with minor overlap risk against general image-generation or logo-design skills — anchor 4, not 5.	4 / 5
	Total	15 / 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
skill_md_line_count	SKILL.md is long (799 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: mediago-dev/mediago
Path: .agents/skills/brandkit/SKILL.md
Commit: f2aa40a

Reviewed: ~2 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.