letta-ai/ai-news
tools/ai-news/SKILL.md
Fetch and summarize recent AI news from curated RSS feeds (Hugging Face, VentureBeat, The Verge, OpenAI, Anthropic, DeepMind, etc.) and YouTube channels (Yannic Kilcher, Two Minute Papers, AI Explained, etc.). Also fetches full transcripts for specific YouTube videos. Use when the user asks about recent AI news, what's happened in AI lately, summaries of AI research or product announcements, or wants a digest of what's going on in the AI space.
$ install --global
skillsauthnpx skillsauth add letta-ai/skills ai-newsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 23, 2026, 12:53 PM57.5s6 files scanned
SKILL.md
- name:
- ai-news
- description:
- Fetch and summarize recent AI news from curated RSS feeds (Hugging Face, VentureBeat, The Verge, OpenAI, Anthropic, DeepMind, etc.) and YouTube channels (Yannic Kilcher, Two Minute Papers, AI Explained, etc.). Also fetches full transcripts for specific YouTube videos. Use when the user asks about recent AI news, what's happened in AI lately, summaries of AI research or product announcements, or wants a digest of what's going on in the AI space.
AI News
Fetch recent AI news from RSS feeds and YouTube channel feeds, then synthesize into a digest. Optionally fetch full transcripts for YouTube videos.
Setup (one-time)
cd ~/.letta/skills/ai-news/scripts && npm install
Workflow
1. Fetch recent news
npx tsx scripts/fetch-news.ts [--days 7] [--limit 5] [--sources all|rss|youtube]
- Outputs a JSON object with
items[]sorted newest-first - Each item has:
source,type(rss/youtube),title,url,publishedAt,summary,videoId - Failed sources are listed in
errors[]— safe to ignore individual failures
2. Synthesize a digest
Read the JSON output and write a digest grouped by theme (e.g. model releases, research, tools, policy). Lead with the most significant items. For YouTube videos, note they have transcripts available.
3. (Optional) Fetch a video transcript
For any YouTube item worth deeper coverage:
npx tsx scripts/fetch-transcript.ts <video-url-or-id> [--summary] [--lang en]
--summaryreturns first ~4000 chars (good for quick context)- Without
--summary, returns full transcript + timestamped segments - Works with any YouTube URL format or bare video ID
Customizing Sources
See references/sources.md for the full list of default RSS feeds and YouTube channels, how to find channel IDs, and additional feed recommendations.
To add/remove sources, edit the RSS_FEEDS and YOUTUBE_CHANNELS arrays at the top of scripts/fetch-news.ts.
Tips
- Use
--days 1for daily briefings,--days 7for weekly digests - Use
--sources rssif YouTube fetches are slow or failing - Some feeds (arXiv) can be very high volume — use a lower
--limitor filter by keyword after fetching - Transcripts require captions to be enabled on the video; auto-generated captions work fine
Related Skills
letta-ai/navigating-chatgpt-history
testing
VerifiedTrustedCommunity
Navigates archived ChatGPT or Claude-style conversation exports and a MemFS reference archive on demand. Use when recalling what a past assistant knew, searching old conversations, rendering specific chats, seeding reference memory from export sidecars, or mining historical context without doing a full import.
106SKILL.mdUpdated May 23, 2026
letta-ai/letta-filesystem-to-memfs
testing
VerifiedTrustedCommunity
Migrates deprecated Letta Filesystem folders/files to MemFS using markdown document corpora, chunking, local lexical search, and QMD semantic search via the memfs-search skill. Use when replacing folders.files.upload, working with PDFs or document QA, or emulating open_file, grep_file, and search_file behavior.
106SKILL.mdUpdated May 23, 2026
letta-ai/compaction-prompts
data-ai
VerifiedTrustedCommunity
Configures Letta agent compaction settings and custom summarization prompts. Use when a user asks to change an agent's compaction prompt, improve summaries after context eviction, tune sliding-window or all-message compaction, or design companion/coding-agent continuity summaries.
106SKILL.mdUpdated May 23, 2026
letta-ai/memfs-search
development
VerifiedTrustedCommunity
Semantic search over agent memory files. Use when you need to find conceptually related memory blocks, discover forgotten reference files, check what you already know before creating new memory, or search beyond exact keyword matching. Currently supports QMD (local, no API keys).
106SKILL.mdUpdated Apr 6, 2026