跳到正文
cccskills
免费在 GitHub 公开

hugegraph-data-importer

Route HugeGraph MCP graph data extraction and controlled import/delete tasks to stable public tools. Use when the user asks to extract graph data from text, import structured vertices or edges, verify an import, or asks whether table, SQL, update, or delete graph writes are available.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(2)

  • SKILL.md2.3 KB
  • agents/openai.yaml1.0 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

HugeGraph Data Importer

Tool Routes

GoalTool
Inspect schema, primary keys, or edge endpointsinspect_graph_tool(include_raw_schema=true)
Extract candidate graph data from textextract_graph_data_tool(text, graph_schema?, example_prompt?)
Preview structured vertex/edge importimport_graph_data_tool(mode="ingest", graph_data, dry_run=true)
Execute confirmed importUnavailable: preview-only, no plan_id; confirmation returns FEATURE_DISABLED
Preview controlled vertex/edge deletedelete_graph_data_tool(change_plan, dry_run=true)
Execute confirmed controlled deleteconfirm_write_tool(plan_id) for a confirmable exact edge delete only
Verify imported dataquery_graph_data_tool (bounded page or exact ID query)

change_plan must contain exact operations. For example, a vertex delete preview (not executable) is:

{"operations":[{"op":"delete_vertex","label":"person","match":{"name":"Alice"}}]}

Edge deletion uses op: "delete_edge", label, source_label, source_match, target_label, and target_match. Each operation must resolve to exactly one target during dry-run; bulk and cascade deletes are not supported.

Order

inspect_graph_tool -> extract_graph_data_tool or prepare graph_data
-> import_graph_data_tool(dry_run=true)
-> review preview (stop: no executable import plan)

For controlled deletes:

inspect_graph_tool(include_raw_schema=true)
-> delete_graph_data_tool(dry_run=true)
-> confirm_write_tool(plan_id), only for confirmable exact edge deletes
-> get_write_status_tool(plan_id) -> query_graph_data_tool

Structured query and plan lifecycle tools require the default core toolset. For a legacy deployment, enable HUGEGRAPH_MCP_TOOLSET=core and restart before using them.

These skills describe current source. Published 1.7.1 uses v2_core / v1; see the migration guide.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Route HugeGraph MCP operational checks to status, schema, MCP read-only state, AI availability, and read-only verification tools. Use when the user asks to check the current graph, schema, MCP connection, readonly state, HugeGraph-AI state, counts, indexes, or readiness.

中文简介正在准备中。当前显示原文说明。

apache/hugegraph-ai1442026年10月18日 更新

Route HugeGraph MCP structured graph query tasks to stable read-only tools. Use when the user asks graph questions, asks to generate Gremlin, provides Gremlin to explain, or needs read-only graph exploration.

中文简介正在准备中。当前显示原文说明。

apache/hugegraph-ai1442026年10月18日 更新

Route HugeGraph MCP regression testing tasks to the current public tool surface, including inspection, read-only queries, Gremlin generation, extraction, controlled import, schema validate/dry-run, safety guards, and admin-gated tool checks.

中文简介正在准备中。当前显示原文说明。

apache/hugegraph-ai1442026年10月18日 更新

Route HugeGraph MCP schema design, validation, and dry-run preview tasks to stable public tools. Use when the user asks to design vertex labels, edge labels, properties, primary keys, indexes, or preview schema operations.

中文简介正在准备中。当前显示原文说明。

apache/hugegraph-ai1442026年10月18日 更新

查看 apache 的全部技能

报告此技能的问题