Saves brand knowledge to persistent vector memory (Pinecone or Qdrant) with metadata tagging for semantic retrieval across sessions.
How this skill is triggered — by the user, by Claude, or both
Slash command
/digital-marketing-pro:save-knowledgeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Save brand knowledge to the persistent memory layer (Pinecone or Qdrant vector database) for semantic retrieval in future sessions. Stores campaign learnings, competitive intelligence, brand guidelines, and performance insights with proper metadata tagging so that valuable knowledge is never lost between sessions. Every stored item is content-hashed for deduplication, tagged with brand context,...
Save brand knowledge to the persistent memory layer (Pinecone or Qdrant vector database) for semantic retrieval in future sessions. Stores campaign learnings, competitive intelligence, brand guidelines, and performance insights with proper metadata tagging so that valuable knowledge is never lost between sessions. Every stored item is content-hashed for deduplication, tagged with brand context, and indexed for natural language search — turning ad-hoc learnings into durable institutional memory that every agent can draw from. Designed for targeted, intentional knowledge capture — for bulk session syncing, use /digital-marketing-pro:sync-memory instead.
The user must provide (or will be prompted for):
guideline (brand rules, voice standards, style restrictions), campaign-learning (what worked or failed in a campaign with supporting evidence), competitive-intel (competitor findings, positioning, pricing, strategy moves), performance-insight (metrics, benchmarks, trends, statistical patterns), or brand-asset (approved copy, templates, creative references, messaging frameworks)high (surface this knowledge proactively in relevant contexts), normal (standard retrieval weight), or low (archive-grade, retrieve only on direct queries). Default is normal~/.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 guidelines at ~/.claude-marketing/brands/{slug}/guidelines/_manifest.json — if present, load restrictions. Check for agency SOPs at ~/.claude-marketing/sops/. If no brand exists, ask: "Set up a brand first (/digital-marketing-pro:brand-setup)?" — or proceed with defaults.memory-manager.py --action prepare-store with content_type, tags, and source context. The script normalizes the content, generates a SHA-256 content hash, structures the metadata payload (brand_slug, content_type, tags, source, timestamp, priority, expiration), and validates that all required fields are present. If tags were not provided, auto-generate them from content analysis.~/.claude-marketing/brands/{slug}/memory/. If a match exists, report the duplicate — show the existing entry's tags, date, and summary — and offer to update its metadata (add new tags, refresh timestamp, change priority) rather than creating a duplicate. If no match, proceed to storage.memory-manager.py --action get-memory-status to determine which vector database is connected — Pinecone, Qdrant, or local-only fallback. Verify API connectivity, available storage capacity, and index health. If no vector DB is connected, store locally and recommend persistent storage setup for cross-session access.memory-manager.py --action log-stored to register the new entry in the local content hash registry with storage ID, vector DB reference, timestamp, and priority. Update sync state so future /digital-marketing-pro:sync-memory runs skip this item as already persisted.A structured storage confirmation containing:
/digital-marketing-pro:search-knowledgenpx claudepluginhub indranilbanerjee/digital-marketing-proSearches stored brand knowledge via semantic search across vector database and knowledge graph. Useful for recalling past learnings, voice guidelines, or competitor insights.
Manages brand and client context for marketing sessions with cross-conversation continuity. Supports creation, switching, listing, updates, and task gating behind active brand.
Manages a three-tier HOT/WARM/COLD memory system for SEO/GEO projects. Automatically loads hot cache (80 lines) each session, promotes/demotes entries, archives stale data, and supports cross-session memory queries.