lore

TotalClaw 作者 totalclaw v1.0

从 Lore(带有引文的研究存储库)中搜索和获取知识

安装 / 下载方式

TotalClaw CLI推荐
totalclaw install totalclaw:totalclaw~mishkinf-lore
cURL直接下载,无需登录
curl -fsSL https://skills.taituai.com/api/skills/totalclaw%3Atotalclaw~mishkinf-lore/file -o mishkinf-lore.md
# Lore Knowledge Base

Lore is a research knowledge repository you have access to via MCP tools. It stores documents, meeting notes, interviews, and decisions with full citations — not just summaries, but the original content linked back to its source. Use it to ground your answers in evidence and to preserve important context from your conversations.

## When to Ingest Content into Lore

Push content into Lore using the `ingest` tool whenever you encounter information worth preserving:

- **After conversations**: When a user shares meeting notes, interview transcripts, or important documents, ingest them so they're searchable later.
- **External content**: When you fetch content from Slack, Notion, GitHub, email, or other systems, ingest the relevant parts into Lore.
- **Decisions and context**: When important decisions are made or context is shared that future conversations will need.

Always include:
- `source_url`: The original URL (Slack permalink, Notion page URL, GitHub issue URL) for citation linking.
- `source_name`: A human-readable label like "Slack #product-team" or "GitHub issue #42".
- `project`: The project this content belongs to.

Ingestion is idempotent — calling `ingest` with the same content twice is safe and cheap (returns immediately with `deduplicated: true`).

## When to Search Lore

Before answering questions about past decisions, user feedback, project history, or anything that might already be documented:

1. **Use `search`** for quick lookups. Pick the right mode:
   - `hybrid` (default): Best for most queries
   - `keyword`: For exact terms, names, identifiers
   - `semantic`: For conceptual queries ("user frustrations", "pain points")

2. **Use `research`** only when the question requires cross-referencing multiple sources or synthesizing findings. It costs 10x more than `search` — don't use it for simple lookups.

3. **Use `get_source`** with `include_content=true` when you need the full original text of a specific document.

## When to Retain Insights

Use `retain` (not `ingest`) for short, discrete pieces of knowledge:
- Key decisions: "We chose X because Y"
- Synthesized insights: "3/5 users mentioned Z as their top issue"
- Requirements: "Must support SSO for enterprise"

## Citation Best Practices

When presenting information from Lore, always cite your sources:
- Reference the source title and date
- Quote directly when possible
- If a `source_url` is available, link to the original

## Example Workflows

**User asks about past decisions:**
1. `search("authentication approach decisions", project: "my-app")`
2. Review results, get full source if needed: `get_source(source_id, include_content: true)`
3. Present findings with citations

**User shares meeting notes:**
1. `ingest(content: "...", title: "Sprint Planning Jan 15", project: "my-app", source_type: "meeting", source_name: "Google Meet", participants: ["Alice", "Bob"])`
2. Confirm ingestion to user

**User asks a broad research question:**
1. `research(task: "What do users think about our onboarding flow?", project: "my-app")`
2. Present the synthesized findings with citations

---

## 中文说明

# Lore 知识库

Lore 是一个研究知识库,你可以通过 MCP 工具访问它。它存储文档、会议记录、访谈和决策,并附带完整引文——不仅仅是摘要,而是链接回其来源的原始内容。用它来让你的回答有据可循,并保留对话中的重要上下文。

## 何时将内容导入 Lore

每当你遇到值得保留的信息时,使用 `ingest` 工具将内容推送到 Lore:

- **对话之后**:当用户分享会议记录、访谈记录或重要文档时,将它们导入,以便日后可以搜索。
- **外部内容**:当你从 Slack、Notion、GitHub、电子邮件或其他系统获取内容时,将相关部分导入 Lore。
- **决策与上下文**:当做出重要决策,或分享了未来对话所需的上下文时。

务必包含:
- `source_url`:用于引文链接的原始 URL(Slack 永久链接、Notion 页面 URL、GitHub issue URL)。
- `source_name`:人类可读的标签,例如 "Slack #product-team" 或 "GitHub issue #42"。
- `project`:该内容所属的项目。

导入是幂等的——用相同内容两次调用 `ingest` 是安全且开销很低的(会立即返回 `deduplicated: true`)。

## 何时搜索 Lore

在回答有关过往决策、用户反馈、项目历史或任何可能已被记录的内容的问题之前:

1. **使用 `search`** 进行快速查找。选择合适的模式:
   - `hybrid`(默认):适用于大多数查询
   - `keyword`:适用于精确的术语、名称、标识符
   - `semantic`:适用于概念性查询("user frustrations"、"pain points")

2. **仅在**问题需要交叉引用多个来源或综合各项发现时**使用 `research`**。它的成本是 `search` 的 10 倍——不要用它做简单查找。

3. 当你需要某个特定文档的完整原文时,**使用 `get_source`** 并设置 `include_content=true`。

## 何时保留洞见

对于简短、独立的知识片段,使用 `retain`(而非 `ingest`):
- 关键决策:"We chose X because Y"
- 综合洞见:"3/5 users mentioned Z as their top issue"
- 需求:"Must support SSO for enterprise"

## 引文最佳实践

在呈现来自 Lore 的信息时,务必注明来源:
- 引用来源标题和日期
- 尽可能直接引述原文
- 如果有 `source_url`,链接到原始来源

## 示例工作流

**用户询问过往决策:**
1. `search("authentication approach decisions", project: "my-app")`
2. 查看结果,如有需要获取完整来源:`get_source(source_id, include_content: true)`
3. 带引文呈现各项发现

**用户分享会议记录:**
1. `ingest(content: "...", title: "Sprint Planning Jan 15", project: "my-app", source_type: "meeting", source_name: "Google Meet", participants: ["Alice", "Bob"])`
2. 向用户确认已导入

**用户提出宽泛的研究问题:**
1. `research(task: "What do users think about our onboarding flow?", project: "my-app")`
2. 带引文呈现综合后的各项发现