saidrassai/ai_as_infra/parser

Customization

Before executing, check for user customizations at: ~/.claude/skills/PAI/USER/SKILLCUSTOMIZATIONS/Parser/

If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults.

🚨 MANDATORY: Voice Notification (REQUIRED BEFORE ANY ACTION)

You MUST send this notification BEFORE doing anything else when this skill is invoked.

1. Send voice notification:

``bash curl -s -X POST http://localhost:8888/notify \ -H "Content-Type: application/json" \ -d '{"message": "Running the WORKFLOWNAME workflow in the Parser skill to ACTION"}' \ > /dev/null 2>&1 & ``

1. Output text notification:

`` Running the **WorkflowName** workflow in the **Parser** skill to ACTION... ``

This is not optional. Execute this curl command immediately upon skill invocation.

Parser

Parse any content into structured JSON with entity extraction and collision detection.

Workflow Routing

When executing a workflow, output this notification:

Running the **WorkflowName** workflow in the **Parser** skill to ACTION...

Content Type Workflows

Security Workflows

Context Files

• EntitySystem.md - Entity extraction, GUIDs, collision detection reference

Core Paths

• Schema: Schema/content-schema.json
• Entity Index: entity-index.json
• Output: Output/

Examples

Example 1: Parse YouTube video

User: "parse this YouTube video for the newsletter"
--> Invokes Youtube workflow
--> Extracts transcript via YouTube API
--> Identifies people, companies, topics mentioned
--> Returns structured JSON with entities and key insights

Example 2: Batch parse article URLs

User: "parse these 5 URLs into JSON for the database"
--> Invokes ParseContent workflow for each
--> Detects content type for each URL
--> Extracts entities with collision detection
--> Assigns GUIDs, checks for duplicates
--> Returns validated JSON per schema

Example 3: Check for duplicate content

User: "have I already parsed this article?"
--> Invokes CollisionDetection workflow
--> Checks URL against entity index
--> Returns existing content ID if found
--> Skips re-parsing, saves time

Quick Reference

• Schema Version: 1.0.0
• Output Format: JSON validated against Schema/content-schema.json
• Entity Types: people, companies, links, sources, topics
• Deduplication: Via entity-index.json with UUID v4 GUIDs