Use this skill at the start of any new content project, before any other Hiruno skill runs. It walks the user through a one-time brand setup and writes `.agents/brand-content-context.md`, the single source of truth for brand voice, audience symptoms, content pillars, format library, and the why anchor. Every other content skill in this repo reads that file first. Trigger this skill whenever the user mentions "set up the brand", "brand context", "new client", "onboard a brand", "brand voice", "audience research", "content pillars", "find the niche", or starts a content project for a brand that has no `.agents/brand-content-context.md` yet. Also trigger when the user wants to update an existing brand context with new pains, desires, pillars, or voice notes.
How this skill is triggered — by the user, by Claude, or both
Slash command
/hiruno-content-skills:brand-content-contextThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Brand context: !`cat .agents/brand-content-context.md 2>/dev/null || echo "No brand context found. Run /brand-content-context first to set up."`
Brand context: !cat .agents/brand-content-context.md 2>/dev/null || echo "No brand context found. Run /brand-content-context first to set up."
You help users create and maintain the brand content context document. This file captures everything the agent needs to write content in the brand's voice for the brand's audience, so the user does not repeat themselves across every skill.
The document is stored at .agents/brand-content-context.md.
First check if .agents/brand-content-context.md already exists.
You can also auto-draft from existing material. If the user has a website, social account, deck, or other brand collateral, offer to study it and produce a V1 draft, then walk through corrections section by section. This is faster than starting from scratch and most users prefer it.
This file replaces the "AI sounds generic" problem. With brand context, every downstream skill (hook generation, scripts, carousels, audits) is calibrated to one specific brand. Without it, every output is flavoured like the average internet creator. The schema below is engineered around Jun Yuh's 1×5×3 system, so the fields map directly to what hook-generator, the format skills, and content-audit need.
See references/schema-template.md for the full template you'll fill in, and references/jun-yuh-system.md at the repo root for the system this is built around.
Walk through each section conversationally, one at a time. Don't dump all questions at once. Be specific in your asks. Ask "what's the number-one frustration that brings them to you" not "what problem do they solve". Capture exact words from the customer wherever possible — verbatim language beats polished descriptions because it makes downstream copy resonate.
Validate as you go. Summarise each section back to the user and confirm before moving on.
This calibrates every line the agent writes.
This is Jun's doctor-patient lens. Every hook the agent writes will pull from this section. Insist on customer's exact words.
Jun's mindset layer. Captures what carries this brand through the inflection dip.
The agent will pick from these formats. Capture one example of each, in this brand's voice, so format skills produce on-brand work.
Helps the agent benchmark and audit. Skip if the brand is brand new.
Write the file to .agents/brand-content-context.md. Use the template in references/schema-template.md for the exact format.
After writing, tell the user:
Brand context saved. Every other Hiruno skill will now read this file automatically. Run /brand-content-context anytime to update it.
If the user wants to immediately use the context for content work, suggest the next skill based on what they need:
When users give vague answers, push back kindly. Vague brand context produces vague content. Specifically:
Specificity downstream comes from specificity here. This is the foundation.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub angelobaricante/hiruno-content-skills --plugin hiruno-content-skills