CtrlK
BlogDocsLog inGet started
Tessl Logo

brand-style-guide

Build or audit a comprehensive brand style guide that documents the full brand system including story, logo system, color, typography, imagery, voice, applications, and dos/don'ts. Use this skill whenever the user wants to create brand guidelines, document an existing brand, build a brand book, audit an existing style guide for completeness, or produce the artifact that other teams will reference for years. Triggers on style guide, brand guidelines, brand book, brand standards, brand manual, style sheet, brand documentation, brand reference. Also triggers when the brand identity is finished and needs to be documented for handoff to designers, developers, vendors, or future team members.

75

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is brand-style-guide in rampstackco/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

90%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.

A well-built instructional skill body: lean, specific section checklists, a clear 7-step workflow, concrete failure patterns, and a real output structure with genuine one-level-deep references. The main improvements are making the review/stress-test steps explicit validation gates and de-duplicating the section checklists against the template reference.

Suggestions

Reframe workflow steps 4-5 as explicit validation gates, e.g. "For every rule, attach a real example; only proceed to review when each section passes" and "Incorporate reviewer feedback and re-check before publishing", to reach the explicit validate-fix-retry pattern.

Trim the inlined 8-section checklists to section names plus a one-line scope and move the per-item detail into references/style-guide-template.md, reducing duplication with the 407-line fillable template.

Consider a short "If validation fails" branch (e.g. what to do when inputs like voice documentation or application examples are missing at step 1) to give the workflow an error-recovery loop.

DimensionReasoningScore

Conciseness

The body is dense, checklist-driven guidance with no explanation of concepts Claude already knows; lines like "Build it like a reference manual, not a presentation" and "Rules without examples get ignored" each carry actionable guidance, matching the 'lean and efficient; assumes Claude's competence; every token earns its place' anchor.

5 / 5

Actionability

Guidance is concrete and executable throughout for an instruction-only skill: "Per color: hex, RGB, HSL, CMYK, Pantone (if print-relevant)", "Minimum sizes (smallest acceptable size for print and digital)", a 7-step workflow, a concrete output file tree, and a fillable template reference. Per the scoring notes, absence of code is not penalized when guidance is this specific.

5 / 5

Workflow Clarity

The 7-step workflow ("Inventory the inputs" through "Publish in the format the team will actually open") is clearly sequenced, and steps 4-5 ("Stress-test with real examples", "Get review from the people who will use it") act as checkpoints. It falls short of the 5 anchor because they are not framed as explicit validation gates (no validate-fix-retry loop or 'only proceed when' condition); it is above 3 because checkpoints are present, just implicit. No destructive/batch cap applies.

4 / 5

Progressive Disclosure

Two real, one-level-deep references (style-guide-template.md, maintenance-playbook.md) are clearly signaled in both the workflow and a dedicated "Reference files" section. It falls short of the 5 anchor because the ~100-line inlined 8-section checklist substantially duplicates the fillable 407-line template reference, so content placement is not cleanly split.

4 / 5

Total

18

/

20

Passed

Description

96%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: it states concrete capabilities in third person, explicitly defines when to use it, and lists a comprehensive set of natural trigger synonyms. The only weakness is minor overlap risk with sibling brand-domain skills (identity, voice, design-standards) that share some of its trigger vocabulary.

DimensionReasoningScore

Specificity

"Build or audit a comprehensive brand style guide that documents the full brand system including story, logo system, color, typography, imagery, voice, applications, and dos/don'ts" names multiple concrete actions (build, audit, document) with comprehensive coverage of the skill's scope, matching the 'multiple specific concrete actions; comprehensive coverage' anchor.

5 / 5

Completeness

The description explicitly answers both what ("Build or audit a comprehensive brand style guide that documents the full brand system...") and when ("Use this skill whenever the user wants to create brand guidelines... Also triggers when the brand identity is finished and needs to be documented for handoff"), with concrete trigger phrases matching the top anchor.

5 / 5

Trigger Term Quality

"Triggers on style guide, brand guidelines, brand book, brand standards, brand manual, style sheet, brand documentation, brand reference" plus natural user phrasings like "create brand guidelines" and "build a brand book" provides comprehensive synonym coverage users would naturally say; no file extensions exist naturally for this domain.

5 / 5

Distinctiveness Conflict Risk

The niche is clear (documenting a finished identity for handoff to designers, developers, vendors) and the "brand identity is finished" trigger signals the boundary against a brand-identity skill, but broad terms like "brand documentation" and "brand reference" and coverage of "voice" create minor overlap risk with sibling brand skills that are not explicitly disambiguated.

4 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
rampstackco/claude-skills
Reviewed

Table of Contents

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.