RSS Feed Digest

Fetch, filter, and summarize RSS/Atom feeds into a clean daily or weekly digest. Supports multiple feeds, keyword filtering, deduplication, and outputs Markd...

Security Scan

The skill's code, instructions, and requirements align with its stated purpose of fetching, filtering, and summarizing RSS/Atom feeds; nothing in the package requests unrelated credentials or installs unexpected software.

Purpose & Capability

Name/description match the provided code and SKILL.md. The Python script implements feed fetching, keyword include/exclude, deduplication, time filtering, and Markdown/plain-text output as described. The single dependency (feedparser) is appropriate for RSS/Atom parsing.

Instruction Scope

Runtime instructions tell the agent to run the included script against user-specified feed URLs or a feed-file. The script only fetches URLs, filters items, and writes local output. Caution: because it fetches arbitrary URLs, running this in an environment with access to internal networks could fetch internal endpoints (SSRF-like risk) if untrusted feed URLs are supplied; SKILL.md also suggests running via heartbeat/cron which increases frequency but is implementation-level, not inherent to the skill.

Install Mechanism

No install spec; the only runtime dependency is feedparser (pip3 install feedparser). This is a standard PyPI dependency and consistent with the script. No downloads from unknown hosts or archive extraction are present.

Credentials

The skill declares no required environment variables, credentials, or config paths. The code does not attempt to read environment secrets or other system configuration.

Persistence & Privilege

always is false and the skill is user-invocable. The skill does not modify other skills or system settings and only writes output to a user-specified local file (or stdout).

Assessment

This skill appears internally consistent and appropriate for aggregating RSS/Atom feeds. Before installing or running it: (1) only supply trusted feed URLs (untrusted feeds could point to internal services or malicious endpoints); (2) install feedparser from PyPI in a controlled environment (virtualenv) and review the script if you plan to run it in an automated/privileged context (cron/heartbeat); (3) be aware output contains links and summaries—treat links like any external link and avoid executing downloaded content. If you need the agent to run autonomously against feeds you don't control, consider running it in network-isolated infrastructure.

Aggregate multiple RSS/Atom feeds into a clean, summarized digest. Perfect for automated newsletters, news monitoring, or daily briefings.

Usage

Fetch and display recent items

python3 {baseDir}/scripts/rss_digest.py fetch \
  --feeds "https://hnrss.org/frontpage" "https://feeds.arstechnica.com/arstechnica/technology-lab" \
  --hours 24 \
  --limit 20

Filter by keywords

python3 {baseDir}/scripts/rss_digest.py fetch \
  --feeds "https://hnrss.org/frontpage" \
  --keywords "AI,LLM,agent,OpenClaw" \
  --hours 48

Output as Markdown file

python3 {baseDir}/scripts/rss_digest.py fetch \
  --feeds "https://hnrss.org/frontpage" \
  --output digest.md \
  --format markdown

Use a feed list file

# Create feeds.txt with one URL per line
python3 {baseDir}/scripts/rss_digest.py fetch \
  --feed-file feeds.txt \
  --hours 24

Features

• 📰 Supports RSS 2.0 and Atom feeds
• 🔍 Keyword filtering (include/exclude)
• 🔄 Deduplication across multiple feeds
• 📅 Time-based filtering (last N hours)
• 📝 Markdown or plain text output
• 📋 Feed list file support for managing many sources

Dependencies

pip3 install feedparser

Example: Daily AI News Digest

# feeds.txt
https://hnrss.org/frontpage
https://feeds.arstechnica.com/arstechnica/technology-lab
https://www.artificialintelligence-news.com/feed/
https://openai.com/blog/rss.xml

# Run daily via cron
python3 rss_digest.py fetch --feed-file feeds.txt --keywords "AI,LLM,GPT,Claude,agent" --hours 24 --output /tmp/daily-ai-digest.md

Use Cases

• Daily briefings: Summarize industry news for your team
• Newsletter automation: Generate content for Beehiiv/Substack newsletters
• Competitive monitoring: Track mentions of competitors or keywords
• Research: Aggregate academic/industry feeds on a topic
• Heartbeat integration: Run during OpenClaw heartbeat to check for relevant news