openclaw-rss
Skill0 starsChanged 8 months agoMITView on GitHub
Use sfeed to parse RSS/Atom feeds and push updates to OpenClaw. Use when: user wants to monitor RSS feeds and get notifications via OpenClaw.
- Installs packages
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ccswitchSkill
- code-rulesSkill
- leanmgr-cache-managerSkill
- learn-math-by-lean-notebookSkill
- lmfdb-cliSkill
- mathlib-styleSkill
- mathlib-workflowSkill
- pre-initSkill
- pr-worktree-workflowSkill
- sshSkill
- tmuxSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 0 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Use sfeed CLI to parse RSS/Atom feeds and integrate with OpenClaw for automated feed monitoring, notifications, and AI-powered feed …
- Very specific: line 112
Create ~/bin/watch_feed.sh for continuous monitoring:
- Very specific: line 145
Create ~/bin/rss_openclaw_summary.sh to use OpenClaw for AI summarization:
- Very specific: line 166
Add to crontab (crontab -e):
- Very specific: line 276
SSL errors: Use curl -ksL instead of curl -sL
- Very specific: line 278
Debug: Run curl -sL "FEED_URL" | sfeed to see raw parsed output
- Very specific: line 279
Missing items: Check cache files in ~/.sfeed/feeds/
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
OpenClaw RSS Reader
Use sfeed CLI to parse RSS/Atom feeds and integrate with OpenClaw for automated feed monitoring, notifications, and AI-powered feed summarization.
Installation
brew tap frankieew/tap && brew install sfeedVerify installation:
ls /opt/homebrew/Cellar/sfeed/*/bin/Quick Start
Basic RSS Parsing
# Parse RSS feed to plain text
curl -sL "FEED_URL" | sfeed | sfeed_plain
# Example: AppInn feed
curl -sL "https://www.appinn.com/feed/" | sfeed | sfeed_plainOutput Formats
| Command | Description |
sfeed | RSS/Atom parser (TAB-separated) |
sfeed_plain | Convert to plain text |
sfeed_html | Convert to HTML |
sfeed_json | Convert to JSON Feed |
sfeed_mbox | Convert to mbox format |
sfeed_curses | TUI feed reader |
sfeed_frames | HTML frames output |
Common Feeds
| Feed | URL |
| AppInn | https://www.appinn.com/feed/ |
| Hacker News | https://hnrss.org/frontpage |
| GitHub Releases | https://github.com/chneukirchen/sfeed/releases.atom |
| TechCrunch | https://techcrunch.com/feed/ |
| Ars Technica | https://feeds.arstechnica.com/arstechnica/index |
OpenClaw Integration
This is the core feature: automatically monitor RSS feeds and send updates to OpenClaw for AI-powered notifications.
1. Feed Monitoring with Notification
Create ~/bin/rss_notify.sh:
#!/bin/bash
# Monitor RSS feeds and send updates to OpenClaw
FEEDS=(
"https://www.appinn.com/feed/"
"https://github.com/chneukirchen/sfeed/releases.atom"
"https://hnrss.org/frontpage"
)
CACHE_DIR="$HOME/.sfeed/feeds"
mkdir -p "$CACHE_DIR"
for feed in "${FEEDS[@]}"; do
feed_name=$(echo "$feed" | md5)
cache_file="$CACHE_DIR/$feed_name"
# Fetch and parse feed
content=$(curl -sL "$feed" | sfeed)
# Compare with cached version to get new items
if [[ -f "$cache_file" ]]; then
new_items=$(diff "$cache_file" <(echo "$content") | grep "^>" | sed 's/^> //')
else
new_items="$content"
fi
# Save current state
echo "$content" > "$cache_file"
# Send new items to OpenClaw
if [[ -n "$new_items" ]]; then
echo "$new_items" | sfeed_plain | while read -r line; do
# Send to OpenClaw (adjust based on your setup)
echo "📰 $line"
done
fi
doneMake it executable:
chmod +x ~/bin/rss_notify.sh2. Real-time Feed Watch
Create ~/bin/watch_feed.sh for continuous monitoring:
#!/bin/bash
# Watch a feed and output new items in real-time
FEED_URL="${1:-https://www.appinn.com/feed/}"
POLL_INTERVAL="${2:-300}" # Default: 5 minutes
echo "Watching $FEED_URL every $POLL_INTERVAL seconds..."
echo "Press Ctrl+C to stop"
echo ""
while true; do
data=$(curl -sL "$FEED_URL" | sfeed)
title=$(echo "$data" | cut -f2 | head -1)
url=$(echo "$data" | cut -f3 | head -1)
echo "[$(date '+%Y-%m-%d %H:%M:%S')] 📰 $title"
echo " ↳ $url"
echo ""
sleep "$POLL_INTERVAL"
doneUsage:
./watch_feed.sh "https://www.appinn.com/feed/" 6003. OpenClaw AI Summary Integration
Create ~/bin/rss_openclaw_summary.sh to use OpenClaw for AI summarization:
#!/bin/bash
# Get RSS feed and use OpenClaw to summarize
FEED_URL="${1:-https://www.appinn.com/feed/}"
# Get latest 5 items
items=$(curl -sL "$FEED_URL" | sfeed | sfeed_plain | head -5)
# Send to OpenClaw for processing
# This assumes OpenClaw is configured with a command that accepts stdin
echo "$items" | openclaw --print-only << 'EOF'
Please summarize these RSS feed updates in Chinese:
{input}
EOF4. cron Job for Automatic Updates
Add to crontab (crontab -e):
# Check feeds every hour
0 * * * * /Users/fwmbam4/bin/rss_notify.sh >> /Users/fwmbam4/.sfeed/logs/notify.log 2>&1
# Check every 30 minutes
*/30 * * * * /Users/fwmbam4/bin/watch_feed.sh "https://www.appinn.com/feed/" 1800 >> /Users/fwmbam4/.sfeed/logs/watch.log 2>&1Create log directory:
mkdir -p ~/.sfeed/logssfeed_update Configuration
The recommended way to manage multiple feeds. Create ~/.sfeed/sfeedrc:
#!/bin/sh
# ~/.sfeed/sfeedrc - Feed configuration
# Feed definition function
feeds() {
# format: feed "name" "url" "encoding"
feed "appinn" "https://www.appinn.com/feed/" "UTF-8"
feed "github" "https://github.com/chneukirchen/sfeed/releases.atom" "UTF-8"
feed "hn" "https://hnrss.org/frontpage" "UTF-8"
feed "techcrunch" "https://techcrunch.com/feed/" "UTF-8"
}
# Custom merge function to keep only latest items
merge() {
awk -F'\t' '!seen[$1]++ { print }' "$1" "$2"
}Initialize and run:
mkdir -p ~/.sfeed/feeds
cp /opt/homebrew/Cellar/sfeed/*/sfeedrc.example ~/.sfeed/sfeedrc
$EDITOR ~/.sfeed/sfeedrc
sfeed_updateFormat output:
# Plain text
sfeed_plain ~/.sfeed/feeds/* > ~/.sfeed/feeds.txt
# HTML
sfeed_html ~/.sfeed/feeds/* > ~/.sfeed/feeds.html
# JSON (for programmatic use)
sfeed_json ~/.sfeed/feeds/* > ~/.sfeed/feeds.jsonFilter Examples
# Get only titles from all feeds
cat ~/.sfeed/feeds/* | cut -f2
# Filter by keyword
curl -sL "https://www.appinn.com/feed/" | sfeed | sfeed_plain | grep -i "OpenClaw"
# Extract URLs only
curl -sL "FEED_URL" | sfeed | cut -f3
# Get items newer than timestamp
curl -sL "FEED_URL" | sfeed | awk -F'\t' '$1 > 1773289469'
# Show only unread (new) items
curl -sL "FEED_URL" | sfeed | sfeed_plain | grep "^N"Advanced Usage
HTML Output with Styles
# Generate HTML with default style
curl -sL "FEED_URL" | sfeed | sfeed_html > feeds.html
# Copy style.css for better presentation
cp /opt/homebrew/Cellar/sfeed/*/share/doc/sfeed/style.css ./OPML Import/Export
# Import from other readers (e.g., newsboat)
newsboat -e | sfeed_opml_import > ~/.sfeed/sfeedrc
# Export to OPML
sfeed_opml_export ~/.sfeed/feeds/* > subscriptions.opmlmbox Format for Email
# Convert feed to mbox format
curl -sL "FEED_URL" | sfeed | sfeed_mbox > feed.mbox
# Import to email clientTroubleshooting
- SSL errors: Use
curl -ksLinstead ofcurl -sL - Encoding issues: Specify encoding in sfeedrc:
feed "name" "url" "GB2312" - Debug: Run
curl -sL "FEED_URL" | sfeedto see raw parsed output - Missing items: Check cache files in
~/.sfeed/feeds/ - Man pages:
man sfeed,man sfeed_update,man sfeedrc
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

