graph-operations — for Claude Code graph-operations, 1C-Enterprise_Framework, community, for Claude Code, ide skills, graph_embeddings, "EntityName (TYPE): key=val", ## Конфиг, GraphChangeDetector, IncrementalGraphUpdater

v1.0.0
GitHub

关于此技能

适用场景： Ideal for AI agents that need когда использовать. 本地化技能摘要： graph-operations helps AI agents handle repository-specific developer workflows with documented implementation details.

功能特性

Когда использовать
"граф знаний", "сущности", "связи", "entities"
"LightRAG", "GraphRAG", "graph traversal"
Построение графа, поиск по графу, entity extraction
Режимы поиска по графу

# 核心主题

for Claude Code graph_embeddings "EntityName (TYPE): key=val" ## Конфиг GraphChangeDetector IncrementalGraphUpdater
Alex1980Alex Alex1980Alex
[0]
[1]
更新于: 3/29/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 8/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution
Review Score
8/11
Quality Score
43
Canonical Locale
ru
Detected Body Locale
ru

适用场景： Ideal for AI agents that need когда использовать. 本地化技能摘要： graph-operations helps AI agents handle repository-specific developer workflows with documented implementation details.

核心价值

推荐说明： graph-operations helps agents когда использовать. graph-operations helps AI agents handle repository-specific developer workflows with documented implementation details.

适用 Agent 类型

适用场景： Ideal for AI agents that need когда использовать.

↓ 赋予的主要能力 · graph-operations

适用任务： Applying Когда использовать
适用任务： Applying "граф знаний", "сущности", "связи", "entities"
适用任务： Applying "LightRAG", "GraphRAG", "graph traversal"

! 使用限制与门槛

  • 限制说明： Requires repository-specific context from the skill documentation
  • 限制说明： Works best when the underlying tools and dependencies are already configured

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

评审后的下一步

先决定动作，再继续看上游仓库材料

Killer-Skills 的主价值不应该停在“帮你打开仓库说明”，而是先帮你判断这项技能是否值得安装、是否应该回到可信集合复核，以及是否已经进入工作流落地阶段。

安装路径

先进入安装与验证

如果这项技能值得继续，下一步应该先确认安装命令、CLI 写入路径与环境验证。
可信复核

回到可信合集再做一次复核

如果你还在比较不同技能或供应方，先回到可信合集做二次判断，而不是继续放大仓库噪音。
工作流

如果要进团队流转，转到工作流集合

当你的目标已经不是单个技能，而是团队协作、审批和交接，就应该转到工作流合集继续决策。
实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致，便于搜索引擎理解页面内容。

? FAQ

graph-operations 是什么？

适用场景： Ideal for AI agents that need когда использовать. 本地化技能摘要： graph-operations helps AI agents handle repository-specific developer workflows with documented implementation details.

如何安装 graph-operations？

运行命令：npx killer-skills add Alex1980Alex/1C-Enterprise_Framework/graph-operations。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

graph-operations 适用于哪些场景？

典型场景包括：适用任务： Applying Когда использовать、适用任务： Applying "граф знаний", "сущности", "связи", "entities"、适用任务： Applying "LightRAG", "GraphRAG", "graph traversal"。

graph-operations 支持哪些 IDE 或 Agent？

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

graph-operations 有哪些限制？

限制说明： Requires repository-specific context from the skill documentation；限制说明： Works best when the underlying tools and dependencies are already configured。

↓ 安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行：npx killer-skills add Alex1980Alex/1C-Enterprise_Framework/graph-operations。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    graph-operations 已启用，可立即在当前项目中调用。

! 参考页模式

此页面仍可作为安装与查阅参考，但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论，再决定是否继续查看上游仓库说明。

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

graph-operations

安装 graph-operations，这是一款面向AI agent workflows and automation的 AI Agent Skill。查看评审结论、使用场景与安装路径。

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Graph Operations

Когда использовать

  • "граф знаний", "сущности", "связи", "entities"
  • "LightRAG", "GraphRAG", "graph traversal"
  • Построение графа, поиск по графу, entity extraction

Режимы поиска по графу

РежимСтоимостьЛатентностьКогда
LightRAG~100 tokens<500msПростые/средние вопросы (default)
GraphRAG Local~2000 tokens2-5sСложные вопросы с контекстом
GraphRAG Global~5000 tokens5-10sТематические обзоры, map-reduce
AutovariesvariesКлассификатор → LightRAG или Full

LightRAG (Phase 38)

Поиск по embeddings сущностей/связей в Qdrant graph_embeddings collection:

  • 6694 точек (3166 entities + 3528 relations)
  • Entity text: "EntityName (TYPE): key=val"
  • Relation text: "Source -[TYPE]-> Target: key=val"
  • Auto-select: simple/moderate → LightRAG, complex/thematic → Full GraphRAG

Операции

python
1# Построение графа из чанков
2builder = GraphBuilder(extractor, graph_store, concurrency=5)
3stats = await builder.build_from_chunks(chunks)
4
5# Построение entity embeddings
6entity_builder = EntityEmbeddingBuilder(embedding_engine, lightrag_settings)
7await entity_builder.build(graph_store)
8
9# Поиск соседей
10neighbors = await graph_store.get_neighbors(entity_id, depth=2)
11
12# Поиск пути
13path = await graph_store.find_path(source_id, target_id, max_depth=5)

Конфиг

env
1GRAPHRAG__COMMUNITY_DETECTION_ENABLED=true
2GRAPHRAG__LEIDEN_RESOLUTION=1.0
3GRAPHRAG__LOCAL_SEARCH_DEPTH=1
4GRAPHRAG__GLOBAL_SEARCH_MAX_COMMUNITIES=20
5LIGHTRAG__ENABLED=true
6LIGHTRAG__ENTITY_TOP_K=10
7LIGHTRAG__RELATION_TOP_K=10
8LIGHTRAG__AUTO_SELECT_ENABLED=true
9GRAPHSTORE__PROVIDER=networkx     # networkx|neo4j

Incremental Graph Update (Phase 61)

Инкрементальное обновление графа без полной перестройки:

КомпонентКлассНазначение
Change DetectorGraphChangeDetectorСравнивает entities/relations с предыдущей версией
Incremental UpdaterIncrementalGraphUpdaterДобавляет/удаляет/обновляет только изменения

Pipeline: Re-extract entities → Change Detector (diff) → Incremental Updater (apply delta)

Экономит 80-95% времени при обновлении документа (только изменённые entity/relation).

Диагностика

СимптомПричинаРешение
Пустой графEntity extraction без результатовПроверить LLM prompt + token limits
LightRAG fallback на vectorНет entity embeddingsЗапустить entity_builder.build(graph_store)
Дубли сущностейDedup key mismatchКлюч: name.lower().strip() + entity_type
NetworkX медленный>10K entitiesИспользовать set_batch_mode(True) + flush()

Файлы

  • Base: src/pdf_framework/graph_store/base.py
  • NetworkX: src/pdf_framework/graph_store/providers/networkx_store.py
  • Neo4j: src/pdf_framework/graph_store/providers/neo4j_store.py
  • Builder: src/pdf_framework/graph_store/construction/builder.py
  • Entity embeddings: src/pdf_framework/graph_store/entity_embeddings.py
  • Change Detector: src/pdf_framework/graph_store/change_detector.py
  • Incremental Updater: src/pdf_framework/graph_store/incremental.py
  • Strategies: src/pdf_framework/search/strategies/graph_search.py, graphrag_light.py, graphrag_global.py, graphrag_auto.py
  • Extractor: src/pdf_framework/processing/extractors/entity_extractor.py

相关技能

寻找 graph-operations 的替代方案 (Alternative) 或可搭配使用的同类 community Skill？探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

★ 333.8k
⑂ 0
AI

widget-generator

Logo of f
f

为prompts.chat的信息反馈系统生成可定制的插件小部件

★ 149.6k
⑂ 0
AI

flags

Logo of vercel
vercel

React 框架

★ 138.4k
⑂ 0
浏览器

pr-review

Logo of pytorch
pytorch

Python中具有强大GPU加速的张量和动态神经网络

★ 98.6k
⑂ 0
开发者工具