Content Pipeline
About
Scraping the HubSpot ecosystem for high-signal content gaps, running them through a Claude SDK curation workflow, and pushing drafts to Buffer for distribution.
Pieces
- Scraping layer: ingest HubSpot community + ecosystem data, identify high-value content opportunities.
- Curation logic: multi-step Claude SDK workflow that turns raw signal into brand-aligned drafts.
- Distribution: Buffer API integration to automate delivery to social queues.
Paused while I get clearer on what manually-distributed content actually performs before automating it.
Tech Stack
Discussion & Feedback
Have questions about this project? Built something similar? Share your thoughts!
(Requires GitHub account to comment)
Related Projects
Brand System
## Voice Profile System Built LinkedIn voice DNA profiles for both Daeda founders by ranking the top 10 posts each (weighted reactions × engagement rate) and reverse-engineering the patterns into reusable style guides the AI curation pipeline can draft against. ### Outputs - **tikita-voice.md** - short, punchy fragments, problem-first hooks, British-casual builder-sharing-workshop tone, moderate emoji, Unicode bold for emphasis. Average post 150-300 words. - **jack-voice.md** - long-form thesis-argument-conclusion (300-500+ words), provocative claim hooks, tab-indented numbered lists, gaming and fantasy metaphors, almost no emoji or hashtags. - Side-by-side comparison table so the right voice can be picked consciously when drafting. - Source data preserved as CSV per founder per year. ### Why It Matters Tone is the hardest thing to keep consistent across an AI writing pipeline. By turning each founder's top performers into a documented style, the curation workflow drafts in either voice on command instead of producing generic LinkedIn-ese. ## Branded Asset Library A reusable library of branded assets - UI animation clips, motion templates, type treatments, colour pairings, product UI captures - aggregated to slot into the AI loop for video production. Why a library rather than per-asset generation: brand consistency at volume is hard. Pulling from a tagged, curated set means generated content can't drift off-brand. Currently used as the constraint layer in the daeda_tech YouTube AI loop.
Personal 2nd Brain (Brain 2.0)
My personal life and learning OS. ## What It Does - **Library:** Book collection with Goodreads CSV and Kindle sync import, status tracking, ratings, tags, and a dismissed-books recovery view. - **Articles:** Save web articles via a proxy reader, group them, and add notes alongside the source. - **Knowledge Graph:** Interactive concept mapping with ReactFlow - multi-board so different domains stay separate. - **Whiteboard:** Excalidraw canvas for sketching systems, kept alongside the notes they belong to. - **Study Partner (AI):** Context-aware Claude chat with full library awareness, now wired to the Claude Code CLI SDK. - **Dream Diary:** Dream logging with scenes, symbols, and Gemini image generation. Atmosphere toggles (blue vibes, realistic, surreal, dark/moody, warm/golden, custom) modify the prompts sent to Gemini. - **Dancing:** YouTube dance video collection, organised by style. - **Music Making Center:** Live-coded music with Strudel and live-coded visuals with Hydra, in a browser code editor with pattern saving and atmosphere presets. - **Task Board:** Local-first task tracking with pipelines, dependencies, and notes - imported from ClickUp via MCP so I could move off the subscription. - **Health Tracking:** Calisthenics logging (sets, reps, duration), skincare routines, progress photos, measurements, and consistency stats via Chart.js. - **Map with Pins & Photos:** Leaflet + OpenStreetMap with categorised pins (visited, want to visit, lived, favourite), photos and notes per pin, filterable sidebar. - **Dashboard & Import/Export:** Stats and charts across the modules, full JSON backup, and per-module import/export.
Daeda 2nd Brain (Business OS)
The Daeda Tech business OS - a centralized hub where the AI has full context of the business, including Stripe revenue snapshots and growth metrics. This is distinct from my personal 2nd brain; this one is purely about running Daeda. ## What It Does - **Custom MCP Servers:** Developed internal Model Context Protocol (MCP) servers to expose 2nd Brain data (Stripe, PostHog, Kanban) directly to AI chat interfaces, allowing for real-time data retrieval and business analysis. - **Custom Infrastructure:** Rebuilt a custom Kanban board with integrated timers and journey mapping (allowing me to cancel my ClickUp subscription). - **Analytics Integration:** Hooked into the PostHog API to track site impressions and monitored YouTube growth/video stats in a single view.