feat(reference-curator): Add pipeline orchestrator and refactor skill format

Pipeline Orchestrator:
- Add 07-pipeline-orchestrator skill with code/CLAUDE.md and desktop/SKILL.md
- Add /reference-curator-pipeline slash command for full workflow automation
- Add pipeline_runs and pipeline_iteration_tracker tables to schema.sql
- Add v_pipeline_status and v_pipeline_iterations views
- Add pipeline_config.yaml configuration template
- Update AGENTS.md with Reference Curator Skills section
- Update claude-project files with pipeline documentation

Skill Format Refactoring:
- Extract YAML frontmatter from SKILL.md files to separate skill.yaml
- Add tools/ directories with MCP tool documentation
- Update SKILL-FORMAT-REQUIREMENTS.md with new structure
- Add migrate-skill-structure.py script for format conversion

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

custom-skills/90-reference-curator/claude-project/INDEX.md

@@ -1,11 +1,27 @@
 # Reference Curator - Claude.ai Project Knowledge
 
-This project knowledge enables Claude to curate, process, and export reference documentation through 6 modular skills.
+This project knowledge enables Claude to curate, process, and export reference documentation through 7 modular skills.
+
+## Quick Start - Pipeline Orchestrator
+
+Run the full curation workflow with a single command:
+
+```
+# Full pipeline from topic
+curate references on "Claude Code best practices"
+
+# From URLs (skip discovery)
+curate these URLs: https://docs.anthropic.com/en/docs/prompt-caching
+
+# With auto-approve
+curate references on "MCP servers" with auto-approve
+```
 
 ## Skills Overview
 
 | Skill | Purpose | Trigger Phrases |
 |-------|---------|-----------------|
+| **pipeline-orchestrator** | Full 6-skill workflow with QA loops | "curate references", "run full pipeline", "automate curation" |
 | **reference-discovery** | Search & validate authoritative sources | "find references", "search documentation", "discover sources" |
 | **web-crawler** | Multi-backend crawling orchestration | "crawl URL", "fetch documents", "scrape pages" |
 | **content-repository** | MySQL storage management | "store content", "save to database", "check duplicates" |
@@ -16,37 +32,43 @@ This project knowledge enables Claude to curate, process, and export reference d
 ## Workflow
 
 ```
-[Topic Input]
-     │
-     ▼
-┌─────────────────────┐
-│ reference-discovery │ → Search & validate sources
-└─────────────────────┘
-     │
-     ▼
+                ┌───────────────────────────┐
+                │   pipeline-orchestrator   │  (Coordinates all stages)
+                └───────────────────────────┘
+                            │
+        ┌───────────────────┼───────────────────┐
+        ▼                   ▼                   ▼
+   [Topic Input]      [URL Input]        [Manifest Input]
+        │                   │                   │
+        ▼                   │                   │
+┌─────────────────────┐     │                   │
+│ reference-discovery │ ◄───┴───────────────────┘
+└─────────────────────┘                  (skip if URLs/manifest)
+        │
+        ▼
 ┌─────────────────────┐
 │ web-crawler         │ → Crawl (Firecrawl/Node.js/aiohttp/Scrapy)
 └─────────────────────┘
-     │
-     ▼
+        │
+        ▼
 ┌─────────────────────┐
 │ content-repository  │ → Store in MySQL
 └─────────────────────┘
-     │
-     ▼
+        │
+        ▼
 ┌─────────────────────┐
-│ content-distiller   │ → Summarize & extract
-└─────────────────────┘
-     │
-     ▼
-┌─────────────────────┐
-│ quality-reviewer    │ → QA loop
-└─────────────────────┘
-     │
-     ├── REFACTOR → content-distiller
-     ├── DEEP_RESEARCH → web-crawler
-     │
-     ▼ APPROVE
+│ content-distiller   │ → Summarize & extract  ◄────┐
+└─────────────────────┘                             │
+        │                                           │
+        ▼                                           │
+┌─────────────────────┐                             │
+│ quality-reviewer    │ → QA loop                   │
+└─────────────────────┘                             │
+        │                                           │
+        ├── REFACTOR (max 3) ───────────────────────┤
+        ├── DEEP_RESEARCH (max 2) → crawler ────────┘
+        │
+        ▼ APPROVE
 ┌─────────────────────┐
 │ markdown-exporter   │ → Project files / Fine-tuning
 └─────────────────────┘
@@ -74,16 +96,28 @@ This project knowledge enables Claude to curate, process, and export reference d
 ## Files in This Project
 
 - `INDEX.md` - This overview file
-- `reference-curator-complete.md` - All 6 skills in one file
+- `reference-curator-complete.md` - All 7 skills in one file (recommended)
 - `01-reference-discovery.md` - Source discovery skill
 - `02-web-crawler.md` - Crawling orchestration skill
 - `03-content-repository.md` - Database storage skill
 - `04-content-distiller.md` - Content summarization skill
 - `05-quality-reviewer.md` - QA review skill
 - `06-markdown-exporter.md` - Export skill
+- `07-pipeline-orchestrator.md` - Full pipeline orchestration
 
 ## Usage
 
 Upload all files to a Claude.ai Project, or upload only the skills you need.
 
 For the complete experience, upload `reference-curator-complete.md` which contains all skills in one file.
+
+## Pipeline Orchestrator Options
+
+| Option | Default | Description |
+|--------|---------|-------------|
+| max_sources | 10 | Max sources to discover |
+| max_pages | 50 | Max pages per source |
+| auto_approve | false | Auto-approve above threshold |
+| threshold | 0.85 | Approval threshold |
+| max_iterations | 3 | Max QA loop iterations |
+| export_format | project_files | Output format |