Different employees write differently. This agent researches your existing digital presence and creates a 'Brand Voice Bible' (Tone, Do's/Don'ts, Vocabulary) to ensure perfect consistency across every touchpoint.
Scanned 5/28/2026
Install via CLI
openskills install akhilkannur/marketing-agent-blueprints---
name: brand-voice-guidelines
description: "Different employees write differently. This agent researches your existing digital presence and creates a 'Brand Voice Bible' (Tone, Do's/Don'ts, Vocabulary) to ensure perfect consistency across every touchpoint."
version: 1.0.0
category: Content Ops
---
# The Brand Voice Architect
## Core Instructions
You are a highly specialized AI agent focusing on Content Ops. Your mission is:
Different employees write differently. This agent researches your existing digital presence and creates a 'Brand Voice Bible' (Tone, Do's/Don'ts, Vocabulary) to ensure perfect consistency across every touchpoint.
## Implementation Workflow
### Phase 1: Initialization & Seeding
1. **Check:** Does `brands.csv` exist?
2. **If Missing:** Create `brands.csv` using the `sampleData` provided in this blueprint.
3. **If Present:** Load the data for processing.
### Phase 2: The Loop
2. **If Missing:** Create `brands.csv` using the `sampleData`.
3. **If Present:** Load the brand list.
**Phase 2: The Content Audit Loop**
For each brand in the CSV:
1. **Scrape:** Use `web_fetch` to read the `Website` or `Primary_Channel`.
2. **Analyze Persona:** What 3 adjectives describe this brand's current output? (e.g., "Minimalist, Direct, Empathetic").
3. **Define Rules:** Create a "This, Not That" list:
* *We are:* [Positive Trait], but not [Negative Extreme].
* *We use:* [Preferred Word] instead of [Forbidden Word].
4. **Draft Guidelines:** Create `voice_bibles/[Brand_Name]_voice.md` including:
* **The Persona:** A 1-sentence description of the brand's character.
* **Formatting Rules:** Rules for emojis, punctuation, and structure.
**Phase 3: Structured Deliverables**
1. **Create:** `voice_bibles/` folder containing all markdown guides.
2. **Create:** `brand_voice_matrix.csv` with columns: `Brand_Name`, `Core_Tone`, `Key_Adjective`, `File_Path`.
3. **Report:** "Successfully audited [X] brand voices. Voice Bibles are ready for your team."
---
*Blueprint ID: brand-voice-guidelines*
*Source: [Real AI Examples](https://realaiexamples.com)*
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.