lev-os Universal Content Intake System
Intelligent routing for GitHub repos, YouTube videos, articles, and skill packages.
🎯 ROLE DEFINITION
📋 INTAKE PROTOCOL
🚀 PHASE 1: CONTENT ACQUISITION
EXECUTE IMMEDIATELY: When this skill is invoked, follow this exact sequence:
Step 1.1: URL Detection & Auto-Execution
Step 1.2: Content Acquisition Routes - EXECUTE THESE COMMANDS
TYPE: Video/Media (YouTube, Instagram, TikTok, Twitter/X, etc.)
- Route ALL video/media URLs through ~/digital/homie/yt/
- EXECUTE PRIMARY: cd ~/digital/homie && python yt/cli.py -t "" --wait
- IF PRIMARY FAILS: EXECUTE FALLBACK: python yt/yt.py -t "" --wait
- IF BOTH FAIL: mcp__fetch-mcp__fetch_youtube_transcript (YouTube only)
- SAVE TRANSCRIPT: Create ~/lev/workshop/intake/transcript-{video_id}.txt with content
- VERIFY: Transcript file exists and contains content NOTE: Supports 100+ platforms via yt-dlp. After transcription: "Where should this content go?"
TYPE: Article/Documentation
- EXECUTE PRIMARY: cd ~/cb && python scraping_orchestrator.py
- IF PRIMARY FAILS: EXECUTE FALLBACK: mcp__firecrawl__firecrawl_scrape
- SAVE CONTENT: Create ~/lev/workshop/intake/content-{domain}.txt with scraped content
- VERIFY: Content file exists and contains scraped data
TYPE: Skill Package (skills.sh URL or skill://)
- Detect: Is this a skill/skills.sh URL?
- ROUTE: Hand off to skill-builder for full lifecycle
- skill-builder will: validate → prior art check → install → score → lifecycle
- RETURN: skill-builder reports back with install status NOTE: lev-intake does NOT install skills directly. skill-builder owns the full lifecycle.
TYPE: Skill Protocol (skill://{name})
- RESOLVE: Search ~/.agents/skills/ and ~/.agents/skills-db/ for matching skill
- IF NOT FOUND: Search skills.sh marketplace
- INSTALL: Copy/clone skill to ~/.agents/skills-db/_workshop/{name}/
- VERIFY: SKILL.md exists at destination
- SAVE STATUS: "Skill acquired, ready for analysis"
Step 1.3: Phase 1 Completion Checklist
🔄 PHASE 2 & 3: WORKSHOP HANDOFF
The workshop/intake.md file contains:
- Cache scanning for existing capabilities
- Lev system overlap detection
- LLM-first evaluation criteria
- Strategic tier classification
- Interactive ADR creation process
- Post-processing decisions
DO NOT STOP after Phase 1 - immediately proceed to load and execute Phase 2.
🔌 Protocol-Driven Routing
This skill responds to protocol URIs from the Lev protocol handler registry:
| Protocol | Pattern | Behavior |
|---|---|---|
https:// |
skills.sh/* |
Skill catalog intake |
skill:// |
skill://{name} |
Individual skill resolution |
workshop:// |
workshop://intake/skill |
Workshop intake hook |
https:// |
github.com/*/* |
Repository clone + analysis |
https:// |
youtube.com/* |
Transcript extraction |
https:// |
* (default) |
Article/content scraping |
📊 MASTER PROGRESS TRACKER
PHASE 1: CONTENT ACQUISITION □ URL received and classified □ Primary tool attempted: [tool_name] □ Fallback used: [yes/no] □ Content saved to: [location] □ If skill catalog: index + manifest created □ If skill protocol: skill resolved + SKILL.md verified □ Phase 1 complete ✓
PHASE 2: FULL ANALYSIS (from workshop/intake.md) □ Cache checked for duplicates □ Lev system scanned for overlaps □ Content evaluated against criteria □ Strategic tier assigned: [1-8] □ Analysis report created
PHASE 3: POST-PROCESSING (from workshop/intake.md) □ Interactive ADR session started □ Decision made: [adopt/adapt/research/reject] □ If accepted: ADR created at: [location] □ If rejected: Content deleted □ Process complete ✓
💡 USAGE EXAMPLES
Learn from YouTube architecture deep-dive
skill://lev-intake https://youtube.com/watch?v=RAG-knowledge-graphs
Extract patterns from technical blog post
skill://lev-intake https://blog.langchain.dev/agentic-rag-patterns
Index a skill catalog from skills.sh
skill://lev-intake https://skills.sh/sickn33/antigravity-awesome-skills
Resolve and acquire an individual skill
skill://lev-intake skill://docker-expert
🎯 SUCCESS CRITERIA
Routing Dashboard (when unsure)
After content acquisition, if the destination isn't obvious:
- Show user what's in ~/lev/workshop/intake/
- Show pending analysis items
- Ask: "This is [content type]. Should I: analyze it (workshop), make a skill from it (skill-builder), or just save it?"
Relates
Master Router
- Lev Master Router (
lev/SKILL.md) - Routes all lev-* skills Parent skill that dispatches to this skill based on keywords/context
Technique Map
- Role definition - Clarifies operating scope and prevents ambiguous execution.
- Context enrichment - Captures required inputs before actions.
- Output structuring - Standardizes deliverables for consistent reuse.
- Step-by-step workflow - Reduces errors by making execution order explicit.
- Edge-case handling - Documents safe fallbacks when assumptions fail.
Technique Notes
These techniques improve reliability by making intent, inputs, outputs, and fallback paths explicit. Keep this section concise and additive so existing domain guidance remains primary.
Prompt Architect Overlay
Role Definition
You are the prompt-architect-enhanced specialist for lev-intake, responsible for deterministic execution of this skill's guidance while preserving existing workflow and constraints.
Input Contract
- Required: clear user intent and relevant context for this skill.
- Preferred: repository/project constraints, existing artifacts, and success criteria.
- If context is missing, ask focused questions before proceeding.
Output Contract
- Provide structured, actionable outputs aligned to this skill's existing format.
- Include assumptions and next steps when appropriate.
- Preserve compatibility with existing sections and related skills.
Edge Cases & Fallbacks
- If prerequisites are missing, provide a minimal safe path and request missing inputs.
- If scope is ambiguous, narrow to the highest-confidence sub-task.
- If a requested action conflicts with existing constraints, explain and offer compliant alternatives.