brand-context
Skill29 starsChanged 33 days agoMITView on GitHub
Foundation skill that captures and stores core brand context — identity, audience, positioning, values, and voice. Use when the user says "set brand context", "save my brand info", "store brand details", "brand profile", "create brand context file", "update brand context", or when starting any brand project for the first time. Every other brand skill reads this file first. Always run this before beginning any brand work if the context file doesn't exist yet.
We split this skill into the rules it gives an agent
4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Find or create the brand package: Look for brand.yaml (in ./, ./brand/, or brands/<slug>/).
- Very specific: line 16
No package → run brand-init first to scaffold it (see that skill / references/brand-package-spec.md), then collect the information below.
- Distinctive: line 23
Ask for the following. If the user has already provided it in conversation, don't ask again.
- Very specific: line 59
Write the brand DNA to <package>/context.md (inside the brand package — NOT .agents/), with this structure:
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Brand Context
You are establishing the brand context foundation. This file is read by every other brand skill before doing any work. Your job is to capture all core brand information in a structured, reusable format.
Before You Start
Find or create the brand package. Look for brand.yaml (in ./, ./brand/, or brands/<slug>/).
- Package exists → read
brand.yaml+context.md; ask the user what to update. - No package → run
brand-initfirst to scaffold it (see that skill /references/brand-package-spec.md), then collect the information below. - Legacy
.agents/brand-context.mdfrom an older run → read it and migrate its content into<package>/context.md.
Information to Collect
Ask for the following. If the user has already provided it in conversation, don't ask again.
1. Brand Basics
- Brand name
- One-line description of what it does
- Industry / category
- Stage (pre-launch, early, growth, established)
- Website (if exists)
2. Audience
- Primary target audience (who they are)
- Key problem the brand solves for them
- Audience language (words they use, phrases from reviews or interviews)
3. Positioning
- What makes this brand different from alternatives?
- Who are the 2–3 main competitors?
- Where does this brand sit in the market (premium, value, niche, mass)?
4. Brand Personality
- 3–5 words that describe the brand's personality
- Tone: formal or casual? serious or playful?
- Any brands whose identity/voice this brand admires?
5. Values & Mission
- Core values (3–5)
- Mission statement (or working draft)
6. Goals
- Primary business goal for the next 12 months
- Key metrics that matter (revenue, awareness, followers, signups)
Output
Write the brand DNA to <package>/context.md (inside the brand package — NOT .agents/), with this structure:
# Brand Context
## Brand
- **Name**: [name]
- **Category**: [category]
- **Description**: [one-liner]
- **Stage**: [stage]
- **Website**: [url or N/A]
## Audience
- **Primary Audience**: [description]
- **Key Problem**: [problem they face]
- **Their Language**: [phrases, words they use]
## Positioning
- **Differentiation**: [what makes this brand different]
- **Competitors**: [list]
- **Market Position**: [premium / value / niche / mass]
## Brand Personality
- **Personality Words**: [word, word, word]
- **Tone**: [formal/casual, serious/playful]
- **Voice Admires**: [brand names or "none"]
## Values & Mission
- **Core Values**: [value, value, value]
- **Mission**: [mission statement]
## Goals
- **Primary Goal**: [goal]
- **Key Metrics**: [metrics]Then update the manifest so the package stays queryable:
- Flip
artifacts.context: trueinbrand.yaml, and refreshupdated. - If
brand.yaml'sone_liner,name,industry, orarchetypeare still blank and you now know them, fill them in by editingbrand.yamldirectly. (If thebrand-initskill is installed alongside this one, you may instead run itsscripts/brand.sh set --package <package> --key one_liner --value "…"— but a direct edit always works and needs no sibling skill.)
Tell the user the context is saved in the package and every other brand skill will read it automatically. They can update it anytime by running this skill again.
Related Skills
- brand-strategy: Full brand strategy using this context
- brand-voice: Voice and tone guidelines using this context
- brand-messaging: Taglines and messaging using this context
- target-audience: Deep audience personas using this context
Other versions8 projects use a version of this.
Word for word · 1
- xeroc/skills★ 1100% same
Edited · 2
- cofoundy/brand-skills★ 6799% same
- productionx-in/Core-Skills★ 181% same
Wrote their own version · 5
- vercel-labs/marketing-team-eve-template★ 459same name
- hyperfx-ai/marketing-skills★ 107same name
- egdev6/discord-project-manager★ 4same name
- akachandan1/proofstack★ 0same name
- whanoftheworld/graphic-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository36 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- brand-architectureSkill
- brand-auditSkill
- brand-guidelinesSkill
- brand-identitySkill
- brand-initSkill
- brand-messagingSkill
- brand-positioningSkill
- brand-storySkill
- brand-strategySkill
- brand-voiceSkill
- competitor-brandingSkill
- namingSkill
- rebrandingSkill
- target-audienceSkill
- briefSkill
- capacitySkill
- commsSkill
- decideSkill
- evalSkill
- experimentSkill
- exposureSkill
- forecastSkill
- negotiateSkill
- onboardSkill
- optionsSkill
- planSkill
- premortemSkill
- reconSkill
- reviewSkill
- sitrepSkill
- stakeholdersSkill
- strategySkill
- systemsSkill
- threatSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

