graph-retrieval
Exposes graph-based retrieval as a tool capability via `query_graph`. Reads normalized graph store files, builds a query-relevant subgraph, and returns LLM-friendly semantic triples with replayable evidence metadata.
来源信息
- 仓库
- study8677/repobrain
- 最近来源活动
- 2026年8月26日 07:44
- 检测到的 SKILL.md 语言
- 英语
- 星标
- 1,356
- Forks
- 266
安装方式
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
检查来源文件
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
文件资源管理器
3 个文件正在显示 SKILL.md
SKILL.md
来源说明 · 只读预览- name
- graph-retrieval
- description
- Exposes graph-based retrieval as a tool capability via `query_graph`. Reads normalized graph store files, builds a query-relevant subgraph, and returns LLM-friendly semantic triples with replayable evidence metadata.
# Graph Retrieval Skill
## Purpose
Expose graph-based retrieval as a tool capability without breaking the
existing RepoBrain execution chain.
## Tool
- `query_graph(query, max_hops=2, workspace='.')`
## Behavior
- Reads normalized graph store files under `.repobrain/graph/`.
- Builds a query-relevant subgraph.
- Returns LLM-friendly semantic triples plus replayable evidence metadata.
## Output Contract
```json
{
"summary": "...",
"triples": [["subject", "predicate", "object"]],
"evidence": [{"retrieval_id": "...", "tool_name": "..."}],
"nodes": [...],
"edges": [...]
}
```
## Design Notes
- Keeps tool-driven and replayable architecture.
- Does not bypass pipeline.
- Intended for structure/dependency questions and context enrichment.
在 GitHub 查看