Install
$ agentstack add skill-shihan-1147-skillmcp-agent-knowledge ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
知识检索技能
此技能使用 RAG(Retrieval-Augmented Generation)技术从本地知识库中检索相关信息。
能力范围
- 语义检索: 基于向量相似度的语义搜索
- 关键词匹配: 精确关键词检索
- 多文档整合: 从多个文档中提取相关片段
- 上下文增强: 将检索结果注入 Prompt 增强回答
使用场景
当用户提出以下类型的问题时,应激活此技能:
- "根据文档,XXX 是什么意思?"
- "在知识库中查找关于 XXX 的信息"
- "帮我找找有关 XXX 的资料"
- 任何需要基于文档回答的问题
依赖工具
| 工具名称 | 用途 | 必需 | |---------|------|-----| | rag_retriever | 向量检索 | ✅ | | rag_indexer | 文档索引 | ❌ |
输入参数
| 参数 | 类型 | 必填 | 说明 | |-----|------|-----|------| | query | string | ✅ | 检索查询 | | top_k | int | ❌ | 返回结果数量,默认 3 | | filter | object | ❌ | 过滤条件(文档类型、日期等) | | threshold | float | ❌ | 相似度阈值,默认 0.7 |
输出格式
{
"success": true,
"data": {
"query": "什么是机器学习",
"results": [
{
"content": "机器学习是人工智能的一个分支...",
"source": "ai_basics.md",
"score": 0.92,
"metadata": {
"page": 1,
"chunk_id": "chunk_001"
}
}
],
"total": 3,
"context_for_llm": "相关上下文拼接文本..."
}
}
处理流程
- 接收用户查询
- 将查询文本向量化
- 在 FAISS 索引中执行相似度搜索
- 获取 Top-K 相关文档片段
- 整合为可用于 LLM 的上下文
检索策略
- 混合检索: 结合向量检索和关键词匹配
- 重排序: 对检索结果进行二次排序
- 去重: 移除重复或高度相似的片段
- 截断: 控制上下文长度不超过 LLM 限制
注意事项
- 需要先完成文档索引
- 检索结果质量依赖 Embedding 模型
- 建议定期更新索引
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: shihan-1147
- Source: shihan-1147/SkillMCP-Agent
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.