Skip to content

Commit 9913682

Browse files
hesamsheikhhesamsheikh
authored
Merge pull request #1 from mberman84/add-matt-berman-usecases
Add 6 real-world use cases by Matthew Berman
2 parents a200a6f + 8da7261 commit 9913682

File tree

7 files changed

+275
-1
lines changed

7 files changed

+275
-1
lines changed

‎README.md‎

Lines changed: 7 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -11,7 +11,7 @@
1111
<br />
1212

1313
[![Awesome](https://awesome.re/badge.svg)](https://awesome.re)
14-
![Use Cases](https://img.shields.io/badge/usecases-4-blue?style=flat-square)
14+
![Use Cases](https://img.shields.io/badge/usecases-10-blue?style=flat-square)
1515
![Last Update](https://img.shields.io/github/last-commit/hesamsheikh/awesome-openclaw-usecases?label=Last%20Update&style=flat-square)
1616
</div>
1717

@@ -32,17 +32,23 @@ Solving the bottleneck of OpenClaw adaptation: Not ~~skills~~, but finding **way
3232
| Name | Description |
3333
|------|-------------|
3434
| [Overnight mini-App Builder](usecases/overnight-mini-app-builder.md) | Wake up to a fresh micro-app idea, built and ready to try |
35+
| [YouTube Content Pipeline](usecases/youtube-content-pipeline.md) | Automate video idea scouting, research, and tracking for a YouTube channel. |
3536

3637
## Productivity
3738

3839
| Name | Description |
3940
|------|-------------|
4041
| [Inbox De-clutter](usecases/inbox-declutter.md) | Summarize Newsletters and send you a digest as an email. |
42+
| [Personal CRM](usecases/personal-crm.md) | Automatically discover and track contacts from your email and calendar, with natural language queries. |
43+
| [Health & Symptom Tracker](usecases/health-symptom-tracker.md) | Track food intake and symptoms to identify triggers, with scheduled check-in reminders. |
44+
| [Multi-Channel Personal Assistant](usecases/multi-channel-assistant.md) | Route tasks across Telegram, Slack, email, and calendar from a single AI assistant. |
4145

4246
## Research & Learning
4347

4448
| Name | Description |
4549
|------|-------------|
50+
| [AI Earnings Tracker](usecases/earnings-tracker.md) | Track tech/AI earnings reports with automated previews, alerts, and detailed summaries. |
51+
| [Personal Knowledge Base (RAG)](usecases/knowledge-base-rag.md) | Build a searchable knowledge base by dropping URLs, tweets, and articles into chat. |
4652

4753
## 🤝 Contributing
4854

‎usecases/earnings-tracker.md‎

Lines changed: 35 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,35 @@
1+
# AI-Powered Earnings Tracker
2+
3+
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.
4+
5+
This workflow automates earnings tracking and delivery:
6+
7+
• Weekly Sunday preview: scans the upcoming earnings calendar and posts relevant tech/AI companies to Telegram
8+
• You pick which companies you care about, and OpenClaw schedules one-shot cron jobs for each earnings date
9+
• After each report drops, OpenClaw searches for results, formats a detailed summary (beat/miss, key metrics, AI highlights), and delivers it
10+
11+
## Skills you Need
12+
13+
- `web_search` (built-in)
14+
- Cron job support in OpenClaw
15+
- Telegram topic for earnings updates
16+
17+
## How to Set it Up
18+
19+
1. Create a Telegram topic called "earnings" for updates.
20+
2. Prompt OpenClaw:
21+
```text
22+
Every Sunday at 6 PM, run a cron job to:
23+
1. Search for the upcoming week's earnings calendar for tech and AI companies
24+
2. Filter for companies I care about (NVDA, MSFT, GOOGL, META, AMZN, TSLA, AMD, etc.)
25+
3. Post the list to my Telegram "earnings" topic
26+
4. Wait for me to confirm which ones I want to track
27+
28+
When I reply with which companies to track:
29+
1. Schedule one-shot cron jobs for each earnings date/time
30+
2. After each report drops, search for earnings results
31+
3. Format a summary including: beat/miss, revenue, EPS, key metrics, AI-related highlights, guidance
32+
4. Post to Telegram "earnings" topic
33+
34+
Keep a memory of which companies I typically track so you can auto-suggest them each week.
35+
```

‎usecases/health-symptom-tracker.md‎

Lines changed: 41 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,41 @@
1+
# Health & Symptom Tracker
2+
3+
Identifying food sensitivities requires consistent logging over time, which is tedious to maintain. You need reminders to log and analysis to spot patterns.
4+
5+
This workflow tracks food and symptoms automatically:
6+
7+
• Message your food and symptoms in a dedicated Telegram topic and OpenClaw logs everything with timestamps
8+
• 3x daily reminders (morning, midday, evening) prompt you to log meals
9+
• Over time, analyzes patterns to identify potential triggers
10+
11+
## Skills you Need
12+
13+
- Cron jobs for reminders
14+
- Telegram topic for logging
15+
- File storage (markdown log file)
16+
17+
## How to Set it Up
18+
19+
1. Create a Telegram topic called "health-tracker" (or similar).
20+
2. Create a log file: `~/clawd/memory/health-log.md`
21+
3. Prompt OpenClaw:
22+
```text
23+
When I message in the "health-tracker" topic:
24+
1. Parse the message for food items and symptoms
25+
2. Log to ~/clawd/memory/health-log.md with timestamp
26+
3. Confirm what was logged
27+
28+
Set up 3 daily reminders:
29+
- 8 AM: "🍳 Log your breakfast"
30+
- 1 PM: "🥗 Log your lunch"
31+
- 7 PM: "🍽️ Log your dinner and any symptoms"
32+
33+
Every Sunday, analyze the past week's log and identify patterns:
34+
- Which foods correlate with symptoms?
35+
- Are there time-of-day patterns?
36+
- Any clear triggers?
37+
38+
Post the analysis to the health-tracker topic.
39+
```
40+
41+
4. Optional: Add a memory file for OpenClaw to track known triggers and update it as patterns emerge.

‎usecases/knowledge-base-rag.md‎

Lines changed: 36 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,36 @@
1+
# Personal Knowledge Base (RAG)
2+
3+
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.
4+
5+
This workflow builds a searchable knowledge base from everything you save:
6+
7+
• Drop any URL into Telegram or Slack and it auto-ingests the content (articles, tweets, YouTube transcripts, PDFs)
8+
• Semantic search over everything you've saved: "What did I save about agent memory?" returns ranked results with sources
9+
• Feeds into other workflows — e.g., the video idea pipeline queries the KB for relevant saved content when building research cards
10+
11+
## Skills you Need
12+
13+
- [knowledge-base](https://clawhub.ai) skill (or build custom RAG with embeddings)
14+
- `web_fetch` (built-in)
15+
- Telegram topic or Slack channel for ingestion
16+
17+
## How to Set it Up
18+
19+
1. Install the knowledge-base skill from ClawdHub.
20+
2. Create a Telegram topic called "knowledge-base" (or use a Slack channel).
21+
3. Prompt OpenClaw:
22+
```text
23+
When I drop a URL in the "knowledge-base" topic:
24+
1. Fetch the content (article, tweet, YouTube transcript, PDF)
25+
2. Ingest it into the knowledge base with metadata (title, URL, date, type)
26+
3. Reply with confirmation: what was ingested and chunk count
27+
28+
When I ask a question in this topic:
29+
1. Search the knowledge base semantically
30+
2. Return top results with sources and relevant excerpts
31+
3. If no good matches, tell me
32+
33+
Also: when other workflows need research (e.g., video ideas, meeting prep), automatically query the knowledge base for relevant saved content.
34+
```
35+
36+
4. Test it by dropping a few URLs and asking questions like "What do I have about LLM memory?"

‎usecases/multi-channel-assistant.md‎

Lines changed: 62 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,62 @@
1+
# Multi-Channel Personal Assistant
2+
3+
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.
4+
5+
This workflow consolidates everything into a single AI assistant:
6+
7+
• Telegram as primary interface with topic-based routing (different topics for video ideas, CRM, earnings, config, etc.)
8+
• Slack integration for team collaboration (task assignment, knowledge base saves, video idea triggers)
9+
• Google Workspace: create calendar events, manage email, upload to Drive — all from chat
10+
• Todoist for quick task capture
11+
• Asana for project management
12+
• Automated reminders: trash day, weekly company letter, etc.
13+
14+
## Skills you Need
15+
16+
- `gog` CLI (Google Workspace)
17+
- Slack integration (bot + user tokens)
18+
- Todoist API or skill
19+
- Asana API or skill
20+
- Telegram channel with multiple topics configured
21+
22+
## How to Set it Up
23+
24+
1. Set up Telegram topics for different contexts:
25+
- `config` — bot settings and debugging
26+
- `updates` — status and notifications
27+
- `video-ideas` — content pipeline
28+
- `personal-crm` — contact management
29+
- `earnings` — financial tracking
30+
- `knowledge-base` — RAG ingestion and queries
31+
32+
2. Connect all your tools via OpenClaw config:
33+
- Google OAuth (Gmail, Calendar, Drive)
34+
- Slack (app + user tokens)
35+
- Todoist API token
36+
- Asana API token
37+
38+
3. Prompt OpenClaw:
39+
```text
40+
You are my multi-channel assistant. Route requests based on context:
41+
42+
Telegram topics:
43+
- "config" → system settings, debugging
44+
- "updates" → daily summaries, reminders, calendar
45+
- "video-ideas" → content pipeline and research
46+
- "personal-crm" → contact queries and meeting prep
47+
- "earnings" → financial tracking
48+
- "knowledge-base" → save and search content
49+
50+
When I ask you to:
51+
- "Add [task] to my todo" → use Todoist
52+
- "Create a card for [topic]" → use Asana Video Pipeline project
53+
- "Schedule [event]" → use gog calendar
54+
- "Email [person] about [topic]" → draft email via gog gmail
55+
- "Upload [file] to Drive" → use gog drive
56+
57+
Set up automated reminders:
58+
- Monday 6 PM: "🗑️ Trash day tomorrow"
59+
- Friday 3 PM: "✍️ Time to write the weekly company update"
60+
```
61+
62+
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).

‎usecases/personal-crm.md‎

Lines changed: 46 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,46 @@
1+
# Personal CRM with Automatic Contact Discovery
2+
3+
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.
4+
5+
This workflow builds and maintains a personal CRM automatically:
6+
7+
• Daily cron job scans email and calendar for new contacts and interactions
8+
• Stores contacts in a structured database with relationship context
9+
• Natural language queries: "What do I know about [person]?", "Who needs follow-up?", "When did I last talk to [person]?"
10+
• Daily meeting prep briefing: before each day's meetings, researches external attendees via CRM + email history and delivers a briefing
11+
12+
## Skills you Need
13+
14+
- `gog` CLI (for Gmail and Google Calendar)
15+
- Custom CRM database (SQLite or similar) or use the [crm-query](https://clawhub.ai) skill if available
16+
- Telegram topic for CRM queries
17+
18+
## How to Set it Up
19+
20+
1. Create a CRM database:
21+
```sql
22+
CREATE TABLE contacts (
23+
id INTEGER PRIMARY KEY,
24+
name TEXT,
25+
email TEXT,
26+
first_seen TEXT,
27+
last_contact TEXT,
28+
interaction_count INTEGER,
29+
notes TEXT
30+
);
31+
```
32+
2. Set up a Telegram topic called "personal-crm" for queries.
33+
3. Prompt OpenClaw:
34+
```text
35+
Run a daily cron job at 6 AM to:
36+
1. Scan my Gmail and Calendar for the past 24 hours
37+
2. Extract new contacts and update existing ones
38+
3. Log interactions (meetings, emails) with timestamps and context
39+
40+
Also, every morning at 7 AM:
41+
1. Check my calendar for today's meetings
42+
2. For each external attendee, search my CRM and email history
43+
3. Deliver a briefing to Telegram with: who they are, when we last spoke, what we discussed, and any follow-up items
44+
45+
When I ask about a contact in the personal-crm topic, search the database and give me everything you know.
46+
```

‎usecases/youtube-content-pipeline.md‎

Lines changed: 48 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,48 @@
1+
# YouTube Content Pipeline
2+
3+
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.
4+
5+
This workflow automates the entire content scouting and research pipeline:
6+
7+
• Hourly cron job scans breaking AI news (web + X/Twitter) and pitches video ideas to Telegram
8+
• Maintains a 90-day video catalog with view counts and topic analysis to avoid re-covering topics
9+
• Stores all pitches in a SQLite database with vector embeddings for semantic dedup (so you never get pitched the same idea twice)
10+
• 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
11+
12+
## Skills you Need
13+
14+
- `web_search` (built-in)
15+
- [x-research-v2](https://clawhub.ai) or custom X/Twitter search skill
16+
- [knowledge-base](https://clawhub.ai) skill for RAG
17+
- Asana integration (or Todoist)
18+
- `gog` CLI for YouTube Analytics
19+
- Telegram topic for receiving pitches
20+
21+
## How to Set it Up
22+
23+
1. Set up a Telegram topic for video ideas and configure it in OpenClaw.
24+
2. Install the knowledge-base skill and x-research skill.
25+
3. Create a SQLite database for pitch tracking:
26+
```sql
27+
CREATE TABLE pitches (
28+
id INTEGER PRIMARY KEY,
29+
timestamp TEXT,
30+
topic TEXT,
31+
embedding BLOB,
32+
sources TEXT
33+
);
34+
```
35+
4. Prompt OpenClaw:
36+
```text
37+
Run an hourly cron job to:
38+
1. Search web and X/Twitter for breaking AI news
39+
2. Check against my 90-day YouTube catalog (fetch from YouTube Analytics via gog)
40+
3. Check semantic similarity against all past pitches in the database
41+
4. If novel, pitch the idea to my Telegram "video ideas" topic with sources
42+
43+
Also: when I share a link in Slack #ai_trends, automatically:
44+
1. Research the topic
45+
2. Search X for related posts
46+
3. Query my knowledge base
47+
4. Create an Asana card in Video Pipeline with a full outline
48+
```

0 commit comments

Comments
 (0)