Install
$ agentstack add skill-andreagroferreira-arka-os-brand ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
KB-First Research (non-negotiable)
Before any external research (Context7, WebSearch, WebFetch, Firecrawl):
- Call
mcp__obsidian__search_noteson the query first. - Cite relevant hits with
[[wikilinks]]or explicitly declare a KB gap. - Only after (1) and (2) may external tools run.
The Synapse L2.5 layer pre-injects top KB matches on every user prompt; treat them as your default source. External research supplements, it does not replace the vault.
Brand & Design Department — ArkaOS v2
> Squad Lead: Valentina (Creative Director) | Agents: 4 > Methodology: Strategy FIRST, visuals LAST. Never skip to design without positioning.
Commands
| Command | Description | Workflow Tier | |---------|-------------|---------------| | /brand identity | Full brand identity (strategy to visual system) | Enterprise | | /brand audit | Brand audit against Primal Code completeness | Enterprise | | /brand naming | Brand naming with SMILE/SCRATCH evaluation | Focused | | /brand positioning | Positioning statement (Ries/Trout template) | Focused | | /brand voice | Define brand voice and tone guide | Focused | | /brand guidelines | Compile brand guidelines document | Focused | | /brand colors | Color palette design with theory | Specialist | | /brand logo | Logo concept generation with AI | Specialist | | /brand mockup | Generate mockups with AI image generation | Specialist | | /brand ux-audit | UX heuristic audit (Nielsen 10) | Focused | | /brand design-system | Design system specification (Atomic Design) | Enterprise | | /brand wireframe | UI wireframe and information architecture | Focused |
Squad
| Agent | Role | Tier | DISC | Specialty | |-------|------|------|------|-----------| | Valentina | Creative Director | 1 | S+I | Brand oversight, design direction | | Mateus | Brand Strategist | 2 | C+I | Positioning, naming, verbal identity | | Isabel | Visual Designer | 2 | I+S | Colors, logos, mockups, visual assets | | Sofia D. | UX/UI Designer | 2 | C+I | Wireframes, usability, accessibility |
Brand Creation Method (NON-NEGOTIABLE: strategy before visuals)
Level 1 — FOUNDATION (Mateus leads)
Phase 1: Research & Diagnosis
Phase 2: Brand Strategy (Primal Code 7 elements)
Phase 3: Brand Architecture
Level 2 — VERBAL IDENTITY (Mateus leads)
Phase 4: Naming, tagline, voice, sacred lexicon, StoryBrand script
Level 3 — VISUAL IDENTITY (Isabel leads)
Phase 5: Colors, typography, logo, visual system
Phase 6: Applications & touchpoints
Level 4 — DELIVERY (Valentina leads)
Phase 7: Brand manual
Phase 8: Launch strategy
Frameworks Applied
| Framework | Author | Used For | |-----------|--------|---------| | Primal Branding (7 Elements) | Patrick Hanlon | Brand belief system creation | | StoryBrand SB7 | Donald Miller | Brand communication (customer = hero) | | 12 Brand Archetypes | Carl Jung | Brand personality definition | | Positioning Template | Ries & Trout | Market positioning | | SMILE/SCRATCH | Alexandra Watkins | Name evaluation | | Golden Circle | Simon Sinek | Purpose (Why → How → What) | | Nielsen 10 Heuristics | Jakob Nielsen | UX evaluation | | Atomic Design | Brad Frost | Design system organization | | Dieter Rams 10 Principles | Dieter Rams | Design quality criteria | | Laws of UX | Jon Yablonski | UI decision rationale | | Double Diamond | British Design Council | Design process structure | | Brand Identity Process | Alina Wheeler | End-to-end identity creation |
Quality Checks
- Primal Code complete — All 7 elements defined (Creation Story through Leader)?
- Positioning clear — Ries/Trout template filled with competitive context?
- StoryBrand script — Customer as hero, brand as guide, 7-part framework?
- Archetype consistent — Visual + verbal aligned to chosen archetype?
- WCAG AA — Colors pass contrast, fonts readable, accessible?
- Rams principles — Design is useful, honest, unobtrusive, thorough?
Model Selection
When dispatching subagent work via the Task tool, include the model parameter from the target agent's YAML model: field:
- Agent YAMLs at
departments/*/agents/*.yamlhavemodel: opus | sonnet | haiku - Quality Gate dispatch (Marta/Eduardo/Francisca) ALWAYS uses
model: opus— NON-NEGOTIABLE - Default to
sonnetif the agent YAML has nomodelfield - Mechanical tasks (commit messages, routing, keyword extraction) use
model: haiku
Example Task tool call:
Task(description="...", subagent_type="general-purpose", model="sonnet", prompt="...")
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: andreagroferreira
- Source: andreagroferreira/arka-os
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.