Customization
Before executing, check for user customizations at:
${PAI_USER_DIR}/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.
- 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...
| Workflow |
Trigger |
File |
| ParseContent |
"parse this", "extract from URL" |
Workflows/ParseContent.md |
| BatchEntityExtractionGemini3 |
"batch extract", "Gemini extraction" |
Workflows/BatchEntityExtractionGemini3.md |
| CollisionDetection |
"check duplicates", "entity collision" |
Workflows/CollisionDetection.md |
| DetectContentType |
"what type is this", "auto-detect" |
Workflows/DetectContentType.md |
Content Type Workflows
| Workflow |
Trigger |
File |
| ExtractNewsletter |
"parse newsletter" |
Workflows/ExtractNewsletter.md |
| ExtractTwitter |
"parse tweet", "X thread" |
Workflows/ExtractTwitter.md |
| ExtractArticle |
"parse article", "web page" |
Workflows/ExtractArticle.md |
| ExtractYoutube |
"parse YouTube", "video transcript" |
Workflows/ExtractYoutube.md |
| ExtractPdf |
"parse PDF", "document" |
Workflows/ExtractPdf.md |
Security Workflows
| Workflow |
Trigger |
File |
| ExtractBrowserExtension |
"analyze extension", "browser extension security" |
Workflows/ExtractBrowserExtension.md |
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
1---2name: parser3description: Extract structured JSON from URLs, files, videos, PDFs with entity extraction and batch support. USE WHEN parse, extract, URL, transcript, entities, JSON, batch, content, YouTube, PDF, article, newsletter, Twitter, browser extension, collision detection, detect content type, extract article, extract newsletter, extract YouTube, extract PDF, parse content.4---56## Customization78**Before executing, check for user customizations at:**9`${PAI_USER_DIR}/SKILLCUSTOMIZATIONS/Parser/`1011If 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.121314<!-- ## 🚨 MANDATORY: Voice Notification (REQUIRED BEFORE ANY ACTION)1516**You MUST send this notification BEFORE doing anything else when this skill is invoked.**17181. **Send voice notification**:19 ```bash20 curl -s -X POST http://localhost:8888/notify \21 -H "Content-Type: application/json" \22 -d '{"message": "Running the WORKFLOWNAME workflow in the Parser skill to ACTION"}' \23 > /dev/null 2>&1 &24 ```25-->26272. **Output text notification**:28 ```29 Running the **WorkflowName** workflow in the **Parser** skill to ACTION...30 ```3132**This is not optional. Execute this curl command immediately upon skill invocation.**3334# Parser3536Parse any content into structured JSON with entity extraction and collision detection.3738---394041## Workflow Routing4243**When executing a workflow, output this notification:**4445```46Running the **WorkflowName** workflow in the **Parser** skill to ACTION...47```4849| Workflow | Trigger | File |50|----------|---------|------|51| **ParseContent** | "parse this", "extract from URL" | `Workflows/ParseContent.md` |52| **BatchEntityExtractionGemini3** | "batch extract", "Gemini extraction" | `Workflows/BatchEntityExtractionGemini3.md` |53| **CollisionDetection** | "check duplicates", "entity collision" | `Workflows/CollisionDetection.md` |54| **DetectContentType** | "what type is this", "auto-detect" | `Workflows/DetectContentType.md` |5556### Content Type Workflows5758| Workflow | Trigger | File |59|----------|---------|------|60| **ExtractNewsletter** | "parse newsletter" | `Workflows/ExtractNewsletter.md` |61| **ExtractTwitter** | "parse tweet", "X thread" | `Workflows/ExtractTwitter.md` |62| **ExtractArticle** | "parse article", "web page" | `Workflows/ExtractArticle.md` |63| **ExtractYoutube** | "parse YouTube", "video transcript" | `Workflows/ExtractYoutube.md` |64| **ExtractPdf** | "parse PDF", "document" | `Workflows/ExtractPdf.md` |6566### Security Workflows6768| Workflow | Trigger | File |69|----------|---------|------|70| **ExtractBrowserExtension** | "analyze extension", "browser extension security" | `Workflows/ExtractBrowserExtension.md` |7172---7374## Context Files7576- **EntitySystem.md** - Entity extraction, GUIDs, collision detection reference7778---7980## Core Paths8182- **Schema:** `Schema/content-schema.json`83- **Entity Index:** `entity-index.json`84- **Output:** `Output/`8586---8788## Examples8990**Example 1: Parse YouTube video**91```92User: "parse this YouTube video for the newsletter"93--> Invokes Youtube workflow94--> Extracts transcript via YouTube API95--> Identifies people, companies, topics mentioned96--> Returns structured JSON with entities and key insights97```9899**Example 2: Batch parse article URLs**100```101User: "parse these 5 URLs into JSON for the database"102--> Invokes ParseContent workflow for each103--> Detects content type for each URL104--> Extracts entities with collision detection105--> Assigns GUIDs, checks for duplicates106--> Returns validated JSON per schema107```108109**Example 3: Check for duplicate content**110```111User: "have I already parsed this article?"112--> Invokes CollisionDetection workflow113--> Checks URL against entity index114--> Returns existing content ID if found115--> Skips re-parsing, saves time116```117118---119120## Quick Reference121122- **Schema Version:** 1.0.0123- **Output Format:** JSON validated against `Schema/content-schema.json`124- **Entity Types:** people, companies, links, sources, topics125- **Deduplication:** Via entity-index.json with UUID v4 GUIDs
mj-deving