/digital-marketing-pro:import-guidelines

/digital-marketing-pro:import-guidelines

Purpose

Import and structure brand guidelines into the persistent brand knowledge layer. Converts unstructured guideline documents, style guides, restriction lists, and messaging playbooks into structured, enforceable markdown files that are automatically applied across all modules and commands.

Input Required

The user provides one or more of:

• Pasted guideline content: Text from an existing brand guide, style guide, or restriction list
• Verbal description: Spoken/typed rules ("we never use exclamation marks", "always lead with data")
• Category to update: Which guideline category to add to (voice-and-tone, messaging, restrictions, channel-styles, visual-identity, or custom)
• Source document reference: Description of where these guidelines come from

If the user doesn't specify a category, analyze the content and route it to the correct category automatically.

Process

1. Load brand context: Read ~/.claude-marketing/brands/_active-brand.json for the active slug, then load ~/.claude-marketing/brands/{slug}/profile.json. Apply brand voice, compliance rules for target markets (skills/context-engine/compliance-rules.md), and industry context. Also check for existing guidelines at ~/.claude-marketing/brands/{slug}/guidelines/_manifest.json — if present, load existing guidelines to merge with (not overwrite). If no brand exists, ask: "Set up a brand first (/digital-marketing-pro:brand-setup)?" — or proceed with defaults.

2. Classify the content — Determine which guideline category (or categories) the input belongs to:

   • Voice rules, writing style, tone → voice-and-tone.md
   • Key messages, taglines, positioning, value props → messaging.md
   • Banned words, restricted claims, disclaimers, prohibited topics → restrictions.md
   • Per-channel format/tone rules → channel-styles.md
   • Colors, fonts, logo rules, imagery style → visual-identity.md
   • Anything else → custom/{descriptive-name}.md

3. Structure the content — Convert unstructured input into organized markdown:

   • Extract individual rules as bullet points
   • Group by sub-topic with clear headings
   • Add before/after examples where the input provides them
   • Preserve the user's intent — don't add rules they didn't specify
   • Use the framework structure from skills/context-engine/guidelines-framework.md

4. Check for conflicts — Compare new guidelines against existing profile settings:

   • If guidelines say "casual tone" but profile has formality=8, flag the conflict
   • If restrictions ban words that appear in existing brand messaging, flag it
   • Present conflicts to the user and ask which takes precedence