etanhey/youtube-pipeline
skills/golem-powers/_archive/youtube-pipeline/SKILL.md
Extract knowledge from YouTube videos into BrainLayer. Use when user shares a YouTube link or asks to process/watch/extract from a video. Chains exa (transcript) -> brain_digest (entities/relations) -> brain_store (conclusions). Works with any YouTube URL.
$ install --global
skillsauthnpx skillsauth add etanhey/golems youtube-pipelineInstall 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 17, 2026, 12:12 PM98.1s3 files scanned
SKILL.md
- name:
- youtube-pipeline
- description:
- Extract knowledge from YouTube videos into BrainLayer. Use when user shares a YouTube link or asks to process/watch/extract from a video. Chains exa (transcript) -> brain_digest (entities/relations) -> brain_store (conclusions). Works with any YouTube URL.
YouTube Pipeline
Extract knowledge from YouTube videos and store permanently in BrainLayer.
Pipeline
YouTube URL
↓
1. exa web_search (full URL as query)
→ title, transcript, metadata
↓
2. brain_digest (raw transcript + metadata)
→ entities, relations, action items, decisions
↓
3. brain_store (structured conclusions)
→ searchable knowledge forever
Usage
When user shares a YouTube link:
Step 1: Extract via Exa
web_search_exa(query: "https://youtube.com/watch?v=VIDEO_ID", num_results: 1)
Exa returns: title, URL, full transcript text, publish date, author.
IMPORTANT: WebFetch does NOT work for YouTube. Always use exa.
Step 2: Digest raw content
brain_digest(content: "<title>\n<author>\n<date>\n\n<full transcript text>")
This extracts: entities (people, tools, companies), relations, sentiment, action items, decisions, questions. Creates a searchable chunk with source='digest'.
Step 3: Store conclusions
brain_store(
content: "Video: '<title>' by <author> (<date>)\nURL: <url>\n\nKey findings:\n1. ...\n2. ...\n3. ...\n\nAction items:\n- ...\n\nRelevant to: <projects>",
tags: ["youtube", "<author-slug>", "<topic-tags>"],
importance: 6-8
)
Step 4: Report to user
Summarize:
- Video title and author
- Top 3-5 key takeaways
- Action items (things to build/try/investigate)
- How it connects to current projects
- BrainLayer chunk IDs for future reference
Batch Mode
For multiple videos (e.g., a playlist or "process these 5 videos"):
- Run exa searches in parallel (up to 5 concurrent)
- Digest each transcript
- Store individual conclusions + one synthesis
- Report all findings in a single summary
Tag Convention
| Tag | When |
|-----|------|
| youtube | Always |
| <author-slug> | e.g., theo-browne, matt-pocock, primeagen |
| <topic> | e.g., ai-agents, typescript, rust, career |
| <project> | If directly relevant: golem-terminal, voicelayer, etc. |
Tips
- Exa sometimes returns partial transcripts for very long videos (3h+). Note this in the summary.
- For livestreams/podcasts, extract the segments that matter — don't store 3 hours of chat.
- If exa returns no transcript, try
web_search_exa("<video title> transcript")as fallback. - Cross-reference findings with existing BrainLayer knowledge:
brain_search("<key topic>")before storing to avoid duplicates.
Related Skills
etanhey/phoenix-human-view
tools
VerifiedTrustedCommunity
The human-eval UX contract for Phoenix views: turn-by-turn scrollable replay (not a scorecard), hide-but-copyable IDs, collapsed thinking, identity chips, tool filters, tiny frozen starter datasets, mark-wrong-in-thread, mobile-first. Use when: building or reviewing ANY Phoenix/eval view, annotation UI, session replay, or human-grading surface. Triggers: phoenix view, eval UI, annotation view, session replay, human eval UX, grading interface. NOT for: Phoenix data pipelines/ingest (capture scripts have their own specs).
3SKILL.mdUpdated Jun 7, 2026
etanhey/mac-systems
tools
VerifiedTrustedCommunity
macOS systems specialist — AppKit NSPanel architecture, launchd services, socket activation, MCP bridge resilience, syspolicyd, and high-frequency SwiftUI dashboards. Use when building menu-bar apps, LaunchAgents, debugging syspolicyd/Gatekeeper/TCC, resilient UDS/MCP bridges, or SwiftUI dashboards at 10Hz+.
3SKILL.mdUpdated Jun 7, 2026
etanhey/judge-fleet
development
VerifiedTrustedCommunity
Bulk LLM-judging protocol for fleet-dispatched verdict runs (KG cluster, eval harness). Use when: dispatching or running judge workers (J1/J2/RT), planning bulk-apply from verdict JSONL, or triaging evidence_degraded outputs. Triggers: judge fleet, bulk judge, R3 verdicts, kg-judge, RT gate, evidence_degraded. NOT for: single-item code review, Phoenix view UX (use phoenix-human-view), or non-judge eval pipelines.
3SKILL.mdUpdated Jun 7, 2026
etanhey/fleet-wrap
development
VerifiedTrustedCommunity
Quiet-down protocol for sprint close: when the fleet wraps, delete ALL polling crons and monitors, send ONE final dashboard + ONE message, then go SILENT. Use when: fleet wraps, all workers done, overnight queue exhausted, sprint close, Etan asleep/away with nothing approved left. Triggers: fleet wrap, wrap the fleet, stand down, going quiet, sprint close. NOT for: mid-sprint monitoring (keep your loops), spawning a successor (use /session-handoff first).
3SKILL.mdUpdated Jun 7, 2026