Skip to content
Beta Multi-model support (OpenAI, Gemini, and more) launching soon.
RBA RBA Skills

rba-brand-voice

Standalone Web-only skill. Copy it into Claude, or drop it into your project.
Open Claude.ai

Paste into Claude Code, Claude.ai, the desktop app, or the browser extension — ⌘/Ctrl+V.

ExperimentalNo security review

RBA Brand Voice

This is the single canonical source for RBA Consulting's brand voice. Other skills (case studies, sales/marketing copy, proposals, email) should reference or call this skill rather than re-defining tone locally.

Status — starting point, not the final brand book

The voice rules in this skill are grounded in RBA's public brand (rbaconsulting.com) and are a faithful tone starting point. They are not yet RBA's complete internal brand book. Several brand areas are intentionally captured as placeholders in reference.md:

  • Visual identity (logo, color palette with exact values, typography, imagery, motion) — placeholder
  • Messaging pillars / message hierarchy (primary + supporting messages, per-audience value props, boilerplate lengths) — placeholder
  • Approved / avoid lists — a working baseline exists; the full RBA-ratified term list still needs to be added
  • Founding year — messaging cites "20 years" (~2006); some sources say 2005 — confirm before using in copy

When a task depends on one of these placeholder areas, prompt the user for the missing brand detail — do not fabricate visual identity, message hierarchy, or claim language. As official brand assets land, fill in reference.md and treat them as the source of truth.

reference.md is the fast at-a-glance summary (verified attributes + the placeholders above). The references/ folder holds the full depth.

Purpose

Two jobs: (1) write content in RBA Consulting's brand voice, and (2) audit existing content against that voice and return a numbered findings list plus a revised draft.

When to apply

Apply this skill on tasks that touch RBA Consulting work, including any of:

  • Content that mentions "RBA", "RBA Consulting", or rbaconsulting.com
  • Content using any RBA named service: Artificial Intelligence, Software Engineering, Digital Experience, Data / Analytics, Digital Workplace, Digital Strategy, User Experience, Cloud Infrastructure, Modern Operations
  • Content using approved taglines: "Powered by People. Enhanced by AI.", "Designed to Deliver.", "We meet you where you are and help you get where you're going, faster.", "Exploration inspires innovation."
  • Explicit requests to write or audit RBA marketing, blog, case study, email, proposal, LinkedIn, or careers copy

Skip when the content is unrelated to RBA, or when the user explicitly requests a different brand voice.

Workflow—write mode

  1. Identify the channel. Tone shifts by channel—see references/voice-pillars.md (Tone by channel table). Website differs from blog differs from proposal.
  2. Draft with approved vocabulary. Use the words in references/vocabulary.md (Use these words list). Never use a banned word from the Avoid → Replace table.
  3. Apply grammar mechanics from references/grammar-and-style.md: active voice in 80%+ of sentences, Oxford comma always, em-dash with NO surrounding spaces, en-dash with NO surrounding spaces (number and date ranges only), spell out one through nine and numerals for 10 and above, no hedging words ("potentially", "possibly", "hope to"), one CTA per content unit, vary sentence openers.
  4. Apply inclusive language. Check references/inclusive-language.md for any term that needs replacement. Default to singular "they/them" for unknown gender. Never use clinical diagnoses as casual adjectives.
  5. For any content touching risk, compliance, legal, regulatory, or governance topics, apply references/risk-and-compliance.md. No absolutes ("ensures", "guarantees", "eliminates", "fully compliant", "will prevent"). Use probabilistic phrases ("helps", "supports", "is designed to", "can reduce the likelihood of"). Include an approved closing qualifier on compliance topics.
  6. Self-check before finalizing. Ask: "Does this sound like a confident, human expert who cares about the client's results—not a generic consulting firm?" If the answer is no, revise.

Workflow—audit mode

When the user provides existing content to audit:

  1. Load all five references: voice-pillars.md, vocabulary.md, grammar-and-style.md, inclusive-language.md, risk-and-compliance.md.
  2. Scan the content for violations, grouped by category:
    • Voice pillar misses—cite which pillar (confident, human-centered, clear, results-oriented) the text falls short of, with a concrete reason
    • Banned vocabulary—cite each offending word and the replacement from references/vocabulary.md
    • Grammar mechanics—em-dash/en-dash spacing, Oxford comma, passive voice, hedging, sentence-opener variety, CTA count
    • Inclusive-language issues—cite the category (gender, ableist, racially coded, neurodiversity, age, socioeconomic, exclusionary idiom) and the replacement
    • Risk/compliance absolutes—cite the offending phrase and the probabilistic replacement
  3. Produce a numbered findings list and a revised version of the content.
  4. Apply the self-check question to the revised version.

References

  • reference.md—fast at-a-glance summary: verified brand attributes today + the placeholder areas that still need fuller brand detail (visual identity, messaging pillars, full approved/avoid lists). Start here.
  • references/voice-pillars.md—the four voice pillars, company identity, core values, tone-by-channel matrix
  • references/vocabulary.md—use-these-words list, avoid→replace table, named services, approved taglines, what RBA is NOT
  • references/grammar-and-style.md—active voice, Oxford comma, sentence/title case, numbers, em-dash and en-dash mechanics, contractions, CTA, sentence openers, hedging
  • references/inclusive-language.md—gender-neutral, ableist (general + tech), racially coded (general + tech), neurodiversity, age, socioeconomic, exclusionary idioms (military, sports, religious/cultural)
  • references/risk-and-compliance.md—never-use absolutes, always-use probabilistic phrases, no-legal-advice framing, approved closing qualifiers, scope

Hard rules

  • Never claim guaranteed compliance, elimination of risk, or any absolute regulatory outcome—always probabilistic language.
  • Never use a banned word from references/vocabulary.md without explicit RBA approval to override.
  • Never write "rba", "R.B.A.", or "RBA Inc."—always "RBA Consulting" (short: "RBA").
  • Em-dash and en-dash NEVER take spaces around them.
  • Singular "they/them" is the default pronoun for unknown gender—never "he/she" or "s/he".
  • For any compliance-touching content, include an approved closing qualifier from references/risk-and-compliance.md.
  • Do not provide legal advice—frame all recommendations as operational, technical, or strategic support.
Technical details
Source
Standalone skill
Author
Tyler Schroeder
Skill name
rba-brand-voice
Maturity
experimental
Security review
No security review
Allowed tools
  • Read
File
skills/rba-brand-voice/SKILL.md

To use this skill in Claude Code, copy SKILL.md into your local .claude/skills/rba-brand-voice/ directory. Standalone skills are not exposed via claude plugin install — that path is reserved for plugin bundles.

Edit this skill on GitHub — opens GitHub's web editor. No git knowledge needed.