librag-knowledge-recall-zh
使用 LibRAG 本地 `/api/v1/librag/knowbase/recall` 接口做知识库数据召回。适用于中文场景下的知识库检索、资料召回、证据段落提取、出处定位、基于知识库的问答取证，以及用户用“知识库查询”“数据召回”“从文档里找答案”等表达发起的任务。
Best use case
librag-knowledge-recall-zh is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
使用 LibRAG 本地 `/api/v1/librag/knowbase/recall` 接口做知识库数据召回。适用于中文场景下的知识库检索、资料召回、证据段落提取、出处定位、基于知识库的问答取证，以及用户用“知识库查询”“数据召回”“从文档里找答案”等表达发起的任务。
Teams using librag-knowledge-recall-zh should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/librag-knowledge-recall/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How librag-knowledge-recall-zh Compares
| Feature / Agent | librag-knowledge-recall-zh | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
使用 LibRAG 本地 `/api/v1/librag/knowbase/recall` 接口做知识库数据召回。适用于中文场景下的知识库检索、资料召回、证据段落提取、出处定位、基于知识库的问答取证，以及用户用“知识库查询”“数据召回”“从文档里找答案”等表达发起的任务。
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# LibRAG 中文知识库召回
优先使用附带脚本调用 LibRAG，不要手写 HTTP 请求。
## 触发语义
遇到下列表达时优先使用本 Skill：
- “去知识库里查一下”
- “做一下数据召回”
- “从 LibRAG 找相关段落”
- “把出处和原文召回出来”
- “根据知识库检索证据”
- “从文档中找到答案”
## 输入
必需输入：
- `question`：用户要检索的问题或条件。
配置文件 `config.json`：
- `base_url`：LibRAG 服务地址。
- `api_key`：与目标知识库绑定的 API Key。
- `kb_id`：默认知识库 ID。
- `recall_mode`：默认召回模式。
- `vector_top_k`：向量召回 top-k。
- `fulltext_top_k`：全文召回 top-k。
- `return_tree`：是否返回树形结构。
- `has_source_text`：是否包含原文。
- `has_score`：是否保留分数字段。
- `filter_effective`：是否过滤无效结果。
- `reasoning_enhance`：是否启用推理增强。
- `score_threshold`：打分过滤阈值。
可选覆盖：命令行参数优先于 `config.json`：
- `kb_id`：覆盖 `config.json` 里的默认知识库 ID。
- `recall_mode`：`reasoning`、`hybrid`、`vector`，默认 `hybrid`。
- `vector_top_k`：默认 `20`。
- `fulltext_top_k`：默认 `20`。
- `return_tree`：默认 `true`。
- `has_source_text`：默认 `true`。
- `has_score`：默认 `true`。
- `score_threshold`：默认 `0`，作为打分过滤的分数阈值。
- `filter_effective`：默认 `true`。
- `reasoning_enhance`：默认 `true`。
## 执行
默认使用 `config.json` 中的知识库：
```bash
python {baseDir}/scripts/recall.py --config {baseDir}/config.json --question "<问题>"
```
需要覆盖知识库时：
```bash
python {baseDir}/scripts/recall.py --config {baseDir}/config.json --kb-id 12 --question "这个产品的违约金标准是什么？"
```
## 输出
默认直接返回脚本输出 JSON。
关键字段：
- `request`
- `response.msg`
- `response.data`
- `summary.item_count`
- `summary.result_shape`
## 约束
- 缺少 `config.json`，或其中的 `base_url`、`api_key`、`kb_id`，或缺少 `question` 时直接失败。
- 默认使用非流式调用。
- 默认使用 `return_tree=true`，只有明确要求平铺段落结果时才改成 `false`。
- 不要输出完整 API Key。
- 若返回 `401` 或 `403`，明确提示密钥无效或没有该知识库权限。
- 若返回 `404`，明确提示知识库不存在。Related Skills
Knowledge Management System
> Turn tribal knowledge into searchable, maintained organizational intelligence. Stop losing expertise when people leave.
rag-knowledge-assistant
基于向量数据库的 RAG(检索增强生成) 知识库助手。支持语义检索、多格式文档 (PDF/Word/Excel/Markdown) 处理、智能问答。使用 Chroma 向量库 + BGE-M3 Embedding 模型。适用于从 knowledge 目录快速检索信息、回答基于文档的问题。触发词："从知识库查"、"检索文档"、"RAG 查询"、"向量搜索"、"语义检索"等。
marketing-copy-knowledge
小黑老師 邱煜庭設計。Meta 廣告文案、Google 廣告文案、社群貼文：用 FABE x SPIN 產出更能轉換的廣告文案。支援 freemium/付費（X-Api-Key credits）。
feishu-memory-recall
Cross-group memory, search, and event sharing for OpenClaw Feishu agents
knowledge-gaps
Track questions Hans failed to answer and flag missing knowledge
memory-totalrecall
Total Recall memory backend — git-branch-based persistent memory store with time-decay relevance.
knowledge-forge
Transform raw personal experience, case studies, business documents, or draft content into transferable cognitive assets -- structured knowledge that others can understand, remember, and apply. Use this skill when users want to turn experience or case studies into teachable content, redesign presentations for maximum retention, create course outlines from domain expertise, crystallize knowledge into shareable documents or knowledge cards, convert know-how into teachable answers, or any scenario where experience must become portable and transferable.
knowledge-answer
Current Date: $DATE$. Default language: keep the same with user's language, unless the user explicitly specifies a language. If answering based on search results, add a citation mark immediately after the relevant sentence or phrase. 2. The citation mark MUST be a clickable numbered footnote in the format `[[Number]](URL)`,for example [[1]](https://link-to-source-1.com). At the end, there shoul...
knowledge-sync
Real-time knowledge base synchronization for AI assistants. Supports inotifywait file monitoring, Git auto-push/pull, Nutstore sync, and multi-device consistency. Use for maintaining knowledge continuity across servers and local devices.
lexiang-knowledge-base
用于访问乐享知识库平台的专用 skill。当用户明确提到「乐享」「lexiang」「知识库」「知识」「文档」等关键词，或用户提供的链接 host 为 lexiangla.com，应优先调用本 skill。本 skill 支持：获取文档内容与元数据、搜索文档内容、查询知识库与目录结构、创建/编辑/移动文档、管理标签与评论、上传文件及维护附件等知识库操作能力。
reading-knowledge
Curious knowledge companion with deep expertise in space, universe, and history. Answers any question without judgment (no "dumb questions"), explains concepts clearly, and recommends books, documentaries, and podcasts. Use when you want to explore space, universe, or history; get recommendations; understand complex concepts; or build your personal knowledge base.
Roofing Knowledge Mentor
Senior-level roofing, estimating, and operations guidance for contractors, adjusters, inspectors, and sales teams. Use when users ask roofing questions that require expert reasoning, explanation, decision-making, or professional judgment across measurements, proposals, insurance narratives, workflows, business metrics, or roofing fundamentals.