Skip to main content

hugegraph-schema-designer

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.

معلومات المصدر

المستودع
apache/hugegraph-ai
آخر نشاط في المصدر
١٣ أكتوبر ٢٠٢٦ في ٠٧:٣٥
لغة SKILL.md المكتشفة
الإنجليزية
النجوم
١٤٤
التفرعات
٩١

خيارات التثبيت

يُحدَّد Prompt الذي يراجع المصدر أولًا بشكل افتراضي. يمكنك التبديل إلى أمر مباشر أو تنزيل نسخة محلية.

مراجعة ملفات المصدر

اقرأ SKILL.md وأي ملفات مرافقة يعرضها SkillsMP قبل أن تقرر التثبيت.

مستكشف الملفات
2 ملفات

عرض SKILL.md

SKILL.md
تعليمات المصدر · معاينة للقراءة فقط
name
hugegraph-schema-designer
description
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.
# HugeGraph Schema Designer ## Tool Routes | Goal | Tool | | --- | --- | | Inspect current schema | `inspect_graph_tool(include_raw_schema=true)` | | Design schema operations | `design_schema_tool(operations?)` | | Validate schema operations | `apply_schema_tool(mode="validate", operations)` | | Dry-run schema operations | `apply_schema_tool(mode="dry_run", operations)` | | Execute real schema apply | `confirm_write_tool(plan_id)` in default `core`, one supported schema create per plan | | Delete or roll back schema | No V1 stable tool | The default `core` toolset permits confirmed apply only for `create_property_key`, `create_vertex_label`, and `create_edge_label`. In `HUGEGRAPH_MCP_TOOLSET=legacy`, real schema apply remains disabled. Review the dry-run response before applying it. Confirm only a returned, confirmable `plan_id` with `confirm_write_tool(plan_id)`, then query `get_write_status_tool(plan_id)`. Schema create operations use a closed field contract. Property keys accept `data_type`, `cardinality`, `aggregate_type`, and `user_data`; vertex labels accept `id_strategy`, `properties`, `primary_keys`, `nullable_keys`, `index_labels`, `enable_label_index`, and `user_data`; edge labels accept `source_label`, `target_label`, `properties`, `nullable_keys`, `sort_keys`, `frequency`, `enable_label_index`, and `user_data`. Unsupported fields, including `ttl*`, are rejected during validation instead of being silently dropped. Supported fields are forwarded and checked by a live-schema post-read. ## Order ```text inspect_graph_tool -> design_schema_tool -> apply_schema_tool(mode="validate") -> apply_schema_tool(mode="dry_run") -> review operations and preview -> confirm_write_tool(plan_id) -> get_write_status_tool(plan_id) ``` 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](../../hugegraph-mcp/README.md#toolset-naming-and-migration).
عرض على GitHub