{
    "kind": "meta",
    "name": "meta-knowledge-base-bootstrap",
    "always": false,
    "triggers": [
        "搭建知识库",
        "knowledge base",
        "kb 启动",
        "bootstrap kb"
    ],
    "provenance": {
        "origin": "opensquilla-original",
        "license": "Apache-2.0"
    },
    "composition": {
        "steps": [
            {
                "id": "classify",
                "kind": "llm_classify",
                "with": {
                    "text": "Inspect this user input and decide its primary source type.\n\nDecision rules:\n- URL  → input contains an http\/https link to a webpage (not a PDF, not a git host).\n- PDF  → input references a .pdf path or URL ending in .pdf.\n- GIT  → input references github.com \/ gitlab \/ a .git URL \/ a local repo path.\n- TEXT → everything else (free-text topic, question, concept).\n\nInput:\n{{ inputs.user_message | xml_escape | truncate(400) }}\n"
                },
                "output_choices": [
                    "URL",
                    "PDF",
                    "GIT",
                    "TEXT"
                ]
            },
            {
                "id": "ingest",
                "kind": "skill_exec",
                "skill": "multi-search-engine",
                "depends_on": [
                    "classify"
                ]
            },
            {
                "id": "memorize",
                "kind": "tool_call",
                "tool": "memory_save",
                "tool_args": {
                    "mode": "append",
                    "path": "memory\/kb-bootstrap.md",
                    "content": "# KB Bootstrap: {{ inputs.user_message | xml_escape | truncate(80) }}\nClassifier verdict: {{ outputs.classify }}\nIngestion (multi-search-engine, JSON):\n{{ outputs.ingest | truncate(2000) }}\n"
                },
                "depends_on": [
                    "ingest"
                ]
            },
            {
                "id": "index",
                "with": {
                    "task": "Create a workbook 'kb-index.xlsx' with columns [Engine, Title, URL, Snippet]. Populate it from this multi-search-engine JSON output: {{ outputs.ingest | truncate(3000) }}"
                },
                "skill": "xlsx",
                "depends_on": [
                    "ingest"
                ]
            }
        ]
    },
    "description": "Bootstrap a domain knowledge base from a single seed (URL \/ PDF path \/ git repo \/ free-text topic): classify source → ingest with the right tool → persist to memory + xlsx index.",
    "meta_priority": 40
}