Add 6 real-world use cases from YouTube creator workflow

- YouTube Content Pipeline: Automated video idea scouting with X/Twitter integration - Personal CRM: Contact discovery and meeting prep automation - AI Earnings Tracker: Tech earnings monitoring and summaries - Knowledge Base (RAG): Searchable repository of saved content - Health & Symptom Tracker: Food and symptom logging with pattern analysis - Multi-Channel Assistant: Unified interface across Telegram, Slack, Google Workspace All use cases verified in daily production use by @matthewberman
2026-02-20 01:35:11 +00:00 · 2026-02-08 17:40:01 -08:00
parent a200a6fe64
commit 8da7261fa0
7 changed files with 275 additions and 1 deletions
--- a/usecases/earnings-tracker.md
+++ b/usecases/earnings-tracker.md
@@ -0,0 +1,35 @@
+# AI-Powered Earnings Tracker
+
+Following earnings season across dozens of tech companies means checking multiple sources and remembering report dates. You want to stay on top of AI/tech earnings without manually tracking every company.
+
+This workflow automates earnings tracking and delivery:
+
+• Weekly Sunday preview: scans the upcoming earnings calendar and posts relevant tech/AI companies to Telegram
+• You pick which companies you care about, and OpenClaw schedules one-shot cron jobs for each earnings date
+• After each report drops, OpenClaw searches for results, formats a detailed summary (beat/miss, key metrics, AI highlights), and delivers it
+
+## Skills you Need
+
+- `web_search` (built-in)
+- Cron job support in OpenClaw
+- Telegram topic for earnings updates
+
+## How to Set it Up
+
+1. Create a Telegram topic called "earnings" for updates.
+2. Prompt OpenClaw:
+```text
+Every Sunday at 6 PM, run a cron job to:
+1. Search for the upcoming week's earnings calendar for tech and AI companies
+2. Filter for companies I care about (NVDA, MSFT, GOOGL, META, AMZN, TSLA, AMD, etc.)
+3. Post the list to my Telegram "earnings" topic
+4. Wait for me to confirm which ones I want to track
+
+When I reply with which companies to track:
+1. Schedule one-shot cron jobs for each earnings date/time
+2. After each report drops, search for earnings results
+3. Format a summary including: beat/miss, revenue, EPS, key metrics, AI-related highlights, guidance
+4. Post to Telegram "earnings" topic
+
+Keep a memory of which companies I typically track so you can auto-suggest them each week.
+```
--- a/usecases/health-symptom-tracker.md
+++ b/usecases/health-symptom-tracker.md
@@ -0,0 +1,41 @@
+# Health & Symptom Tracker
+
+Identifying food sensitivities requires consistent logging over time, which is tedious to maintain. You need reminders to log and analysis to spot patterns.
+
+This workflow tracks food and symptoms automatically:
+
+• Message your food and symptoms in a dedicated Telegram topic and OpenClaw logs everything with timestamps
+• 3x daily reminders (morning, midday, evening) prompt you to log meals
+• Over time, analyzes patterns to identify potential triggers
+
+## Skills you Need
+
+- Cron jobs for reminders
+- Telegram topic for logging
+- File storage (markdown log file)
+
+## How to Set it Up
+
+1. Create a Telegram topic called "health-tracker" (or similar).
+2. Create a log file: `~/clawd/memory/health-log.md`
+3. Prompt OpenClaw:
+```text
+When I message in the "health-tracker" topic:
+1. Parse the message for food items and symptoms
+2. Log to ~/clawd/memory/health-log.md with timestamp
+3. Confirm what was logged
+
+Set up 3 daily reminders:
+- 8 AM: "🍳 Log your breakfast"
+- 1 PM: "🥗 Log your lunch"
+- 7 PM: "🍽️ Log your dinner and any symptoms"
+
+Every Sunday, analyze the past week's log and identify patterns:
+- Which foods correlate with symptoms?
+- Are there time-of-day patterns?
+- Any clear triggers?
+
+Post the analysis to the health-tracker topic.
+```
+
+4. Optional: Add a memory file for OpenClaw to track known triggers and update it as patterns emerge.
--- a/usecases/knowledge-base-rag.md
+++ b/usecases/knowledge-base-rag.md
@@ -0,0 +1,36 @@
+# Personal Knowledge Base (RAG)
+
+You read articles, tweets, and watch videos all day but can never find that one thing you saw last week. Bookmarks pile up and become useless.
+
+This workflow builds a searchable knowledge base from everything you save:
+
+• Drop any URL into Telegram or Slack and it auto-ingests the content (articles, tweets, YouTube transcripts, PDFs)
+• Semantic search over everything you've saved: "What did I save about agent memory?" returns ranked results with sources
+• Feeds into other workflows — e.g., the video idea pipeline queries the KB for relevant saved content when building research cards
+
+## Skills you Need
+
+- [knowledge-base](https://clawhub.ai) skill (or build custom RAG with embeddings)
+- `web_fetch` (built-in)
+- Telegram topic or Slack channel for ingestion
+
+## How to Set it Up
+
+1. Install the knowledge-base skill from ClawdHub.
+2. Create a Telegram topic called "knowledge-base" (or use a Slack channel).
+3. Prompt OpenClaw:
+```text
+When I drop a URL in the "knowledge-base" topic:
+1. Fetch the content (article, tweet, YouTube transcript, PDF)
+2. Ingest it into the knowledge base with metadata (title, URL, date, type)
+3. Reply with confirmation: what was ingested and chunk count
+
+When I ask a question in this topic:
+1. Search the knowledge base semantically
+2. Return top results with sources and relevant excerpts
+3. If no good matches, tell me
+
+Also: when other workflows need research (e.g., video ideas, meeting prep), automatically query the knowledge base for relevant saved content.
+```
+
+4. Test it by dropping a few URLs and asking questions like "What do I have about LLM memory?"
--- a/usecases/multi-channel-assistant.md
+++ b/usecases/multi-channel-assistant.md
@@ -0,0 +1,62 @@
+# Multi-Channel Personal Assistant
+
+Context-switching between apps to manage tasks, schedule events, send messages, and track work is exhausting. You want one interface that routes to all your tools.
+
+This workflow consolidates everything into a single AI assistant:
+
+• Telegram as primary interface with topic-based routing (different topics for video ideas, CRM, earnings, config, etc.)
+• Slack integration for team collaboration (task assignment, knowledge base saves, video idea triggers)
+• Google Workspace: create calendar events, manage email, upload to Drive — all from chat
+• Todoist for quick task capture
+• Asana for project management
+• Automated reminders: trash day, weekly company letter, etc.
+
+## Skills you Need
+
+- `gog` CLI (Google Workspace)
+- Slack integration (bot + user tokens)
+- Todoist API or skill
+- Asana API or skill
+- Telegram channel with multiple topics configured
+
+## How to Set it Up
+
+1. Set up Telegram topics for different contexts:
+   - `config` — bot settings and debugging
+   - `updates` — status and notifications
+   - `video-ideas` — content pipeline
+   - `personal-crm` — contact management
+   - `earnings` — financial tracking
+   - `knowledge-base` — RAG ingestion and queries
+
+2. Connect all your tools via OpenClaw config:
+   - Google OAuth (Gmail, Calendar, Drive)
+   - Slack (app + user tokens)
+   - Todoist API token
+   - Asana API token
+
+3. Prompt OpenClaw:
+```text
+You are my multi-channel assistant. Route requests based on context:
+
+Telegram topics:
+- "config" → system settings, debugging
+- "updates" → daily summaries, reminders, calendar
+- "video-ideas" → content pipeline and research
+- "personal-crm" → contact queries and meeting prep
+- "earnings" → financial tracking
+- "knowledge-base" → save and search content
+
+When I ask you to:
+- "Add [task] to my todo" → use Todoist
+- "Create a card for [topic]" → use Asana Video Pipeline project
+- "Schedule [event]" → use gog calendar
+- "Email [person] about [topic]" → draft email via gog gmail
+- "Upload [file] to Drive" → use gog drive
+
+Set up automated reminders:
+- Monday 6 PM: "🗑️ Trash day tomorrow"
+- Friday 3 PM: "✍️ Time to write the weekly company update"
+```
+
+4. Test each integration individually, then test cross-workflow interactions (e.g., saving a Slack link to knowledge base, then using it in a video research card).
--- a/usecases/personal-crm.md
+++ b/usecases/personal-crm.md
@@ -0,0 +1,46 @@
+# Personal CRM with Automatic Contact Discovery
+
+Keeping track of who you've met, when, and what you discussed is impossible to do manually. Important follow-ups slip through the cracks, and you forget context before important meetings.
+
+This workflow builds and maintains a personal CRM automatically:
+
+• Daily cron job scans email and calendar for new contacts and interactions
+• Stores contacts in a structured database with relationship context
+• Natural language queries: "What do I know about [person]?", "Who needs follow-up?", "When did I last talk to [person]?"
+• Daily meeting prep briefing: before each day's meetings, researches external attendees via CRM + email history and delivers a briefing
+
+## Skills you Need
+
+- `gog` CLI (for Gmail and Google Calendar)
+- Custom CRM database (SQLite or similar) or use the [crm-query](https://clawhub.ai) skill if available
+- Telegram topic for CRM queries
+
+## How to Set it Up
+
+1. Create a CRM database:
+```sql
+CREATE TABLE contacts (
+  id INTEGER PRIMARY KEY,
+  name TEXT,
+  email TEXT,
+  first_seen TEXT,
+  last_contact TEXT,
+  interaction_count INTEGER,
+  notes TEXT
+);
+```
+2. Set up a Telegram topic called "personal-crm" for queries.
+3. Prompt OpenClaw:
+```text
+Run a daily cron job at 6 AM to:
+1. Scan my Gmail and Calendar for the past 24 hours
+2. Extract new contacts and update existing ones
+3. Log interactions (meetings, emails) with timestamps and context
+
+Also, every morning at 7 AM:
+1. Check my calendar for today's meetings
+2. For each external attendee, search my CRM and email history
+3. Deliver a briefing to Telegram with: who they are, when we last spoke, what we discussed, and any follow-up items
+
+When I ask about a contact in the personal-crm topic, search the database and give me everything you know.
+```
--- a/usecases/youtube-content-pipeline.md
+++ b/usecases/youtube-content-pipeline.md
@@ -0,0 +1,48 @@
+# YouTube Content Pipeline
+
+As a daily YouTube creator, finding fresh, timely video ideas across the web and X/Twitter is time-consuming. Tracking what you've already covered prevents duplicates and helps you stay ahead of trends.
+
+This workflow automates the entire content scouting and research pipeline:
+
+• Hourly cron job scans breaking AI news (web + X/Twitter) and pitches video ideas to Telegram
+• Maintains a 90-day video catalog with view counts and topic analysis to avoid re-covering topics
+• Stores all pitches in a SQLite database with vector embeddings for semantic dedup (so you never get pitched the same idea twice)
+• When you share a link in Slack, OpenClaw researches the topic, searches X for related posts, queries your knowledge base, and creates an Asana card with a full outline
+
+## Skills you Need
+
+- `web_search` (built-in)
+- [x-research-v2](https://clawhub.ai) or custom X/Twitter search skill
+- [knowledge-base](https://clawhub.ai) skill for RAG
+- Asana integration (or Todoist)
+- `gog` CLI for YouTube Analytics
+- Telegram topic for receiving pitches
+
+## How to Set it Up
+
+1. Set up a Telegram topic for video ideas and configure it in OpenClaw.
+2. Install the knowledge-base skill and x-research skill.
+3. Create a SQLite database for pitch tracking:
+```sql
+CREATE TABLE pitches (
+  id INTEGER PRIMARY KEY,
+  timestamp TEXT,
+  topic TEXT,
+  embedding BLOB,
+  sources TEXT
+);
+```
+4. Prompt OpenClaw:
+```text
+Run an hourly cron job to:
+1. Search web and X/Twitter for breaking AI news
+2. Check against my 90-day YouTube catalog (fetch from YouTube Analytics via gog)
+3. Check semantic similarity against all past pitches in the database
+4. If novel, pitch the idea to my Telegram "video ideas" topic with sources
+
+Also: when I share a link in Slack #ai_trends, automatically:
+1. Research the topic
+2. Search X for related posts
+3. Query my knowledge base
+4. Create an Asana card in Video Pipeline with a full outline
+```