crawl_config.json 1.71 KB
{
  "skill_name": "ceo_leadership",
  "target_agent": "ceo",
  "data_sources": [
    {
      "name": "OKR Best Practices",
      "type": "rss",
      "url": "https://www.whatmatters.com/feed",
      "relevance": "elite",
      "crawl_frequency": "weekly"
    },
    {
      "name": "Multi-Agent Research Papers",
      "type": "api",
      "url": "https://arxiv.org/search/?query=multi+agent+management&format=rss",
      "relevance": "elite",
      "crawl_frequency": "daily"
    },
    {
      "name": "CEO Management Articles",
      "type": "web_scrape",
      "url": "https://hbr.org/topic/leadership",
      "selector": {
        "title": "h3.hed",
        "summary": "p.dek",
        "author": "span.byline",
        "date": "time"
      },
      "relevance": "average",
      "crawl_frequency": "weekly"
    }
  ],
  "extraction_rules": {
    "strategy_planning": {
      "keywords": ["vision", "strategy", "planning", "roadmap", "market analysis"],
      "weight": 0.25
    },
    "team_building": {
      "keywords": ["team building", "org design", "hiring", "management"],
      "weight": 0.25
    },
    "okr_management": {
      "keywords": ["OKR", "objective", "key result", "goal setting"],
      "weight": 0.25
    },
    "task_delegation": {
      "keywords": ["delegation", "task assignment", "dispatch", "execution"],
      "weight": 0.25
    }
  },
  "quality_filters": {
    "min_content_length": 500,
    "required_fields": ["title", "content"],
    "deduplicate_by": "title"
  },
  "output_format": {
    "file_type": "json",
    "schema": {
      "title": "string",
      "content": "string",
      "source": "string",
      "date": "datetime",
      "relevance": "enum[elite,average,broad]",
      "category": "string"
    }
  }
}