search-company-knowledge

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Search Company Knowledge

搜索公司知识库

Keywords

关键词

find information, search company knowledge, look up, what is, explain, company docs, internal documentation, Confluence search, Jira search, our documentation, internal knowledge, knowledge base, search for, tell me about, get information about, company systems, terminology, find everything about, what do we know about, deployment, authentication, infrastructure, processes, procedures, how to, how does, our systems, our processes, internal systems, company processes, technical documentation, engineering docs, architecture, configuration, search our docs, search internal docs, find in our docs
查找信息, 搜索公司知识, 查阅, 是什么, 解释, 公司文档, 内部文档, Confluence搜索, Jira搜索, 我方文档, 内部知识, 知识库, 搜索, 介绍一下, 获取相关信息, 公司系统, 术语, 查找全部相关内容, 关于某事物我们了解什么, 部署, 认证, 基础设施, 流程, 步骤, 如何操作, 如何运作, 我方系统, 我方流程, 内部系统, 公司流程, 技术文档, 工程文档, 架构, 配置, 搜索我方文档, 搜索内部文档, 在我方文档中查找

Overview

概述

Search across siloed company knowledge systems (Confluence, Jira, internal documentation) to find comprehensive answers to questions about internal concepts, systems, and terminology. This skill performs parallel searches across multiple sources and synthesizes results with proper citations.
Use this skill when: Users ask about internal company knowledge that might be documented in Confluence pages, Jira tickets, or internal documentation.

跨孤立的公司知识系统(Confluence、Jira、内部文档)进行搜索,为关于内部概念、系统和术语的问题查找全面答案。此技能可跨多来源并行搜索,并整合结果且附上恰当引用。
使用此技能的场景: 用户询问可能记录在Confluence页面、Jira工单或内部文档中的公司内部知识。

Workflow

工作流程

Follow this 5-step process to provide comprehensive, well-cited answers:
遵循以下5步流程,提供全面且引用规范的答案:

Step 1: Identify Search Query

步骤1:确定搜索查询词

Extract the core search terms from the user's question.
Examples:
  • User: "Find everything about Stratus minions" → Search: "Stratus minions"
  • User: "What do we know about the billing system?" → Search: "billing system"
  • User: "Explain our deployment process" → Search: "deployment process"
Consider:
  • Main topic or concept
  • Any specific system/component names
  • Technical terms or jargon

从用户的问题中提取核心搜索词。
示例:
  • 用户:"查找关于Stratus minions的全部内容" → 搜索词:"Stratus minions"
  • 用户:"关于计费系统我们了解什么?" → 搜索词:"billing system"
  • 用户:"解释我们的部署流程" → 搜索词:"deployment process"
需考虑:
  • 主题或核心概念
  • 特定系统/组件名称
  • 技术术语或行话

Step 2: Execute Parallel Search

步骤2:执行并行搜索

Search across all available knowledge sources simultaneously for comprehensive coverage.
同时在所有可用知识源中搜索,确保覆盖全面。

Option A: Cross-System Search (Recommended First)

选项A:跨系统搜索(推荐首选)

Use the
search
tool (Rovo Search) to search across Confluence and Jira at once:
search(
  cloudId="...",
  query="[extracted search terms]"
)
When to use:
  • Default approach for most queries
  • When you don't know which system has the information
  • Fastest way to get results from multiple sources
Example:
search(
  cloudId="...",
  query="Stratus minions"
)
This returns results from both Confluence pages and Jira issues.
使用
search
工具(Rovo Search)同时搜索Confluence和Jira:
search(
  cloudId="...",
  query="[提取的搜索词]"
)
适用场景:
  • 大多数查询的默认方式
  • 不确定哪个系统包含所需信息时
  • 最快获取多来源结果的方式
示例:
search(
  cloudId="...",
  query="Stratus minions"
)
此调用会返回Confluence页面和Jira工单的结果。

Option B: Targeted Confluence Search

选项B:定向Confluence搜索

Use
searchConfluenceUsingCql
when specifically searching Confluence:
searchConfluenceUsingCql(
  cloudId="...",
  cql="text ~ 'search terms' OR title ~ 'search terms'"
)
When to use:
  • User specifically mentions "in Confluence" or "in our docs"
  • Cross-system search returns too many Jira results
  • Looking for documentation rather than tickets
Example CQL patterns:
text ~ "Stratus minions"
text ~ "authentication" AND type = page
title ~ "deployment guide"
当需要专门搜索Confluence时,使用
searchConfluenceUsingCql
searchConfluenceUsingCql(
  cloudId="...",
  cql="text ~ '搜索词' OR title ~ '搜索词'"
)
适用场景:
  • 用户明确提到“在Confluence中”或“在我方文档中”
  • 跨系统搜索返回过多Jira结果时
  • 查找文档而非工单时
示例CQL模式:
text ~ "Stratus minions"
text ~ "authentication" AND type = page
title ~ "deployment guide"

Option C: Targeted Jira Search

选项C:定向Jira搜索

Use
searchJiraIssuesUsingJql
when specifically searching Jira:
searchJiraIssuesUsingJql(
  cloudId="...",
  jql="text ~ 'search terms' OR summary ~ 'search terms'"
)
When to use:
  • User mentions "tickets", "issues", or "bugs"
  • Looking for historical problems or implementation details
  • Cross-system search returns mostly documentation
Example JQL patterns:
text ~ "Stratus minions"
summary ~ "authentication" AND type = Bug
text ~ "deployment" AND created >= -90d
当需要专门搜索Jira时,使用
searchJiraIssuesUsingJql
searchJiraIssuesUsingJql(
  cloudId="...",
  jql="text ~ '搜索词' OR summary ~ '搜索词'"
)
适用场景:
  • 用户提到“工单”、“问题”或“缺陷”时
  • 查找历史问题或实现细节时
  • 跨系统搜索主要返回文档时
示例JQL模式:
text ~ "Stratus minions"
summary ~ "authentication" AND type = Bug
text ~ "deployment" AND created >= -90d

Search Strategy

搜索策略

For most queries, use this sequence:
  1. Start with
    search
    (cross-system) - always try this first
  2. If results are unclear, follow up with targeted searches
  3. If results mention specific pages/tickets, fetch them for details

对于大多数查询,遵循以下顺序:
  1. 先使用
    search
    (跨系统)- 始终优先尝试此方式
  2. 如果结果不清晰,再进行定向搜索
  3. 如果结果提到特定页面/工单,获取其详细内容

Step 3: Fetch Detailed Content

步骤3:获取详细内容

After identifying relevant sources, fetch full content for comprehensive answers.
识别相关来源后,获取完整内容以形成全面答案。

For Confluence Pages

Confluence页面

When search results reference Confluence pages:
getConfluencePage(
  cloudId="...",
  pageId="[page ID from search results]",
  contentFormat="markdown"
)
Returns: Full page content in Markdown format
When to fetch:
  • Search result snippet is too brief
  • Need complete context
  • Page seems to be the primary documentation
当搜索结果指向Confluence页面时:
getConfluencePage(
  cloudId="...",
  pageId="[搜索结果中的页面ID]",
  contentFormat="markdown"
)
返回结果: Markdown格式的完整页面内容
获取时机:
  • 搜索结果片段过于简短时
  • 需要完整上下文时
  • 该页面似乎是主要文档时

For Jira Issues

Jira工单

When search results reference Jira issues:
getJiraIssue(
  cloudId="...",
  issueIdOrKey="PROJ-123"
)
Returns: Full issue details including description, comments, status
When to fetch:
  • Need to understand a reported bug or issue
  • Search result doesn't show full context
  • Issue contains important implementation notes
当搜索结果指向Jira工单时:
getJiraIssue(
  cloudId="...",
  issueIdOrKey="PROJ-123"
)
返回结果: 完整工单详情,包括描述、评论、状态
获取时机:
  • 需要理解已报告的缺陷或问题时
  • 搜索结果未展示完整上下文时
  • 工单包含重要实现说明时

Prioritization

优先级

Fetch in this order:
  1. Official documentation pages (Confluence pages with "guide", "documentation", "overview" in title)
  2. Recent/relevant issues (Jira tickets that are relevant and recent)
  3. Additional context (related pages mentioned in initial results)
Don't fetch everything - be selective based on relevance to user's question.

按以下顺序获取内容:
  1. 官方文档页面(标题包含“指南”、“文档”、“概述”的Confluence页面)
  2. 近期/相关工单(相关且较新的Jira工单)
  3. 额外上下文(初始结果中提到的相关页面)
不要全部获取 - 根据与用户问题的相关性选择性获取。

Step 4: Synthesize Results

步骤4:整合结果

Combine information from multiple sources into a coherent answer.
将多来源信息整合成连贯的答案。

Synthesis Guidelines

整合指南

Structure your answer:
  1. Direct Answer First
    • Start with a clear, concise answer to the question
    • "Stratus minions are..."
  2. Detailed Explanation
    • Provide comprehensive details from all sources
    • Organize by topic, not by source
  3. Source Attribution
    • Note where each piece of information comes from
    • Format: "According to [source], ..."
  4. Highlight Discrepancies
    • If sources conflict, note it explicitly
    • Example: "The Confluence documentation states X, however Jira ticket PROJ-123 indicates that due to bug Y, the behavior is actually Z"
  5. Provide Context
    • Mention if information is outdated
    • Note if a feature is deprecated or in development
答案结构:
  1. 直接给出答案
    • 以清晰、简洁的答案开头
    • 例如:"Stratus minions是..."
  2. 详细解释
    • 提供来自所有来源的全面细节
    • 按主题组织内容,而非按来源
  3. 来源归因
    • 注明每条信息的来源
    • 格式:"根据[来源],..."
  4. 突出矛盾点
    • 如果来源信息冲突,明确注明
    • 示例:"Confluence文档说明X,但Jira工单PROJ-123显示,由于缺陷Y,实际行为是Z"
  5. 提供上下文
    • 注明信息是否过时
    • 说明功能是否已弃用或处于开发中

Synthesis Patterns

整合模式

Pattern 1: Multiple sources agree
Stratus minions are background worker processes that handle async tasks.

According to the Confluence documentation, they process jobs from the queue and 
can be scaled horizontally. This is confirmed by several Jira tickets (PROJ-145, 
PROJ-203) which discuss minion configuration and scaling strategies.
Pattern 2: Sources provide different aspects
The billing system has two main components:

**Payment Processing** (from Confluence "Billing Architecture" page)
- Handles credit card transactions
- Integrates with Stripe API
- Runs nightly reconciliation

**Invoice Generation** (from Jira PROJ-189)
- Creates monthly invoices
- Note: Currently has a bug where tax calculation fails for EU customers
- Fix planned for Q1 2024
Pattern 3: Conflicting information
There is conflicting information about the authentication timeout:

- **Official Documentation** (Confluence) states: 30-minute session timeout
- **Implementation Reality** (Jira PROJ-456, filed Oct 2023): Actual timeout is 
  15 minutes due to load balancer configuration
- **Status:** Engineering team aware, fix planned but no timeline yet

Current behavior: Expect 15-minute timeout despite docs saying 30 minutes.
Pattern 4: Incomplete information
Based on available documentation:

[What we know about deployment process from Confluence and Jira]

However, I couldn't find information about:
- Rollback procedures
- Database migration handling

You may want to check with the DevOps team or search for additional documentation.

模式1:多来源信息一致
Stratus minions是处理异步任务的后台工作进程。

根据Confluence文档,它们从队列中处理任务,且可水平扩展。多个Jira工单(PROJ-145、PROJ-203)也讨论了minion的配置和扩展策略,证实了这一点。
模式2:来源提供不同维度信息
计费系统包含两个主要组件:

**支付处理**(来自Confluence“计费架构”页面)
- 处理信用卡交易
- 与Stripe API集成
- 每日夜间执行对账

**发票生成**(来自Jira PROJ-189)
- 生成月度发票
- 注意:当前存在欧盟客户税计算失败的缺陷
- 修复计划于2024年第一季度进行
模式3:信息冲突
关于认证超时的信息存在冲突:

- **官方文档**(Confluence)说明:会话超时为30分钟
- **实际实现**(Jira PROJ-456,2023年10月提交):由于负载均衡器配置,实际超时为15分钟
- **状态**:工程团队已知晓此问题,修复计划已制定但暂无时间表

当前行为:尽管文档说明为30分钟,但实际超时为15分钟。
模式4:信息不完整
根据现有文档:

[来自Confluence和Jira的部署流程相关信息]

不过,我未找到以下信息:
- 回滚流程
- 数据库迁移处理方式

你可咨询DevOps团队或搜索更多文档。

Step 5: Provide Citations

步骤5:提供引用

Always include links to source materials so users can explore further.
始终包含源材料链接,方便用户进一步探索。

Citation Format

引用格式

For Confluence pages:
**Source:** [Page Title](https://yoursite.atlassian.net/wiki/spaces/SPACE/pages/123456)
For Jira issues:
**Related Tickets:**
- [PROJ-123](https://yoursite.atlassian.net/browse/PROJ-123) - Brief description
- [PROJ-456](https://yoursite.atlassian.net/browse/PROJ-456) - Brief description
Complete citation section:
undefined
Confluence页面:
**来源:** [页面标题](https://yoursite.atlassian.net/wiki/spaces/SPACE/pages/123456)
Jira工单:
**相关工单:**
- [PROJ-123](https://yoursite.atlassian.net/browse/PROJ-123) - 简要描述
- [PROJ-456](https://yoursite.atlassian.net/browse/PROJ-456) - 简要描述
完整引用部分:
undefined

Sources

来源

Confluence Documentation:
Jira Issues:
Additional Resources:
  • [Internal architecture doc link if found]

---
Confluence文档:
Jira工单:
额外资源:
  • [若找到的内部架构文档链接]

---

Search Best Practices

搜索最佳实践

Effective Search Terms

有效搜索词

Do:
  • ✅ Use specific technical terms: "OAuth authentication flow"
  • ✅ Include system names: "Stratus minions"
  • ✅ Use acronyms if they're common: "API rate limiting"
  • ✅ Try variations if first search fails: "deploy process" → "deployment pipeline"
Don't:
  • ❌ Be too generic: "how things work"
  • ❌ Use full sentences: Use key terms instead
  • ❌ Include filler words: "the", "our", "about"
建议:
  • ✅ 使用具体技术术语:"OAuth authentication flow"
  • ✅ 包含系统名称:"Stratus minions"
  • ✅ 使用通用缩写:"API rate limiting"
  • ✅ 首次搜索失败时尝试变体:"deploy process" → "deployment pipeline"
避免:
  • ❌ 过于宽泛:"事物如何运作"
  • ❌ 使用完整句子:改用关键词
  • ❌ 包含填充词:"the"、"our"、"about"

Search Result Quality

搜索结果质量

Good results:
  • Recent documentation (< 1 year old)
  • Official/canonical pages (titled "Guide", "Documentation", "Overview")
  • Multiple sources confirming same information
  • Detailed implementation notes
Questionable results:
  • Very old tickets (> 2 years, may be outdated)
  • Duplicate or conflicting information
  • Draft pages or work-in-progress docs
  • Personal pages (may not be official)
When results are poor:
  • Try different search terms
  • Expand search to include related concepts
  • Search for specific error messages or codes
  • Ask user for more context

优质结果:
  • 近期文档(1年内)
  • 官方/标准页面(标题含“指南”、“文档”、“概述”)
  • 多来源确认同一信息
  • 详细实现说明
存疑结果:
  • 非常旧的工单(超过2年,可能过时)
  • 重复或冲突信息
  • 草稿页面或进行中的文档
  • 个人页面(可能非官方)
结果质量不佳时:
  • 尝试不同搜索词
  • 扩展搜索至相关概念
  • 搜索特定错误信息或代码
  • 请求用户提供更多上下文

Handling Common Scenarios

常见场景处理

Scenario 1: No Results Found

场景1:未找到结果

If searches return no results:
I searched across Confluence and Jira but couldn't find information about "[topic]".

This could mean:
- The concept hasn't been documented yet
- It might be called something else (can you provide alternative names?)
- Documentation might be in a different system I don't have access to

Would you like me to:
1. Try searching with different terms?
2. Search for related concepts?
3. Look for mentions in recent Jira tickets?
如果搜索无结果:
我在Confluence和Jira中搜索了“[主题]”但未找到相关信息。

可能的原因:
- 该概念尚未文档化
- 可能有其他名称(你能提供替代名称吗?)
- 文档可能在我无权访问的其他系统中

你希望我:
1. 尝试使用不同关键词搜索?
2. 搜索相关概念?
3. 查找近期Jira工单中的提及内容?

Scenario 2: Too Many Results

场景2:结果过多

If search returns 50+ results:
  • Focus on most recent and most relevant (top 10-15)
  • Prioritize official documentation over random tickets
  • Group similar results: "I found 15 tickets related to authentication bugs..."
  • Offer to narrow search: "Would you like me to focus on [specific aspect]?"
如果搜索返回50+结果:
  • 聚焦最新且最相关的结果(前10-15条)
  • 优先选择官方文档而非随机工单
  • 对相似结果分组:“我找到15条与认证缺陷相关的工单...”
  • 提供缩小搜索范围的选项:“你希望我聚焦[特定方面]吗?”

Scenario 3: Ambiguous Query

场景3:查询模糊

If the user's question is vague:
I found information about several topics related to "[term]":
1. [Topic A] - from Confluence page X
2. [Topic B] - from Jira tickets Y, Z
3. [Topic C] - from documentation W

Which aspect are you most interested in?
如果用户问题模糊:
我找到多个与“[术语]”相关的主题:
1. [主题A] - 来自Confluence页面X
2. [主题B] - 来自Jira工单Y、Z
3. [主题C] - 来自文档W

你最关注哪个方面?

Scenario 4: Outdated Information

场景4:信息过时

If you find information is old:
I found documentation about [topic], but note that it's from [date] and may be outdated.

[Provide the information anyway]

You may want to verify this is still current, especially if it's from more than 
a year ago.
如果发现信息过时:
我找到关于[主题]的文档,但注意到该文档创建于[日期],可能已过时。

[仍提供该信息]

你可能需要验证此信息是否仍有效,尤其是如果文档已超过1年。

Scenario 5: Restricted/Private Content

场景5:受限/私有内容

If search returns inaccessible content:
Search results mention [topic] in the following locations, but I don't have 
access to view the full content:
- Confluence page: [title] (Space: [SPACE])
- Jira issue: PROJ-123

You may need to access these directly or check your permissions.

如果搜索返回不可访问的内容:
搜索结果提及[主题]存在于以下位置,但我无权查看完整内容:
- Confluence页面:[标题](空间:[SPACE])
- Jira工单:PROJ-123

你可能需要直接访问这些内容或检查权限。

Examples

示例

Example 1: Clear Documentation Available

示例1:有明确文档可用

User: "What are Stratus minions?"
Process:
  1. Search:
    search(cloudId="...", query="Stratus minions")
  2. Find: Confluence page "Stratus Architecture" + 3 Jira tickets
  3. Fetch: Get full Confluence page content
  4. Synthesize: Combine architectural overview with implementation details from tickets
  5. Cite: Provide links to all sources
Answer:
Stratus minions are background worker processes that handle asynchronous task 
processing in the Stratus system.

**Key Characteristics:**
- Run independently from web servers
- Process jobs from a Redis queue
- Can be scaled horizontally for increased throughput
- Handle tasks like email sending, report generation, and data processing

**Architecture:**
According to the Stratus Architecture documentation, minions follow a 
worker-queue pattern where:
1. Web application enqueues tasks
2. Minions poll the queue for work
3. Tasks are processed asynchronously
4. Results are stored in the database

**Implementation Notes:**
From Jira ticket PROJ-203, the current deployment runs 5 minion instances, 
with plans to scale to 10 for handling increased load.
用户: "什么是Stratus minions?"
流程:
  1. 搜索:
    search(cloudId="...", query="Stratus minions")
  2. 找到:Confluence页面“Stratus架构” + 3条Jira工单
  3. 获取:完整Confluence页面内容
  4. 整合:将架构概述与工单中的实现细节结合
  5. 引用:提供所有来源的链接
答案:
Stratus minions是Stratus系统中处理异步任务的后台工作进程。

**核心特性:**
- 独立于Web服务器运行
- 从Redis队列中处理任务
- 可水平扩展以提升吞吐量
- 处理任务如邮件发送、报表生成和数据处理

**架构:**
根据Stratus架构文档,minions遵循工作队列模式:
1. Web应用将任务加入队列
2. Minions轮询队列获取工作
3. 异步处理任务
4. 结果存储至数据库

**实现说明:**
从Jira工单PROJ-203可知,当前部署运行5个minion实例,计划扩展至10个以应对增长的负载。

Sources

来源

  • Stratus Architecture Guide
  • PROJ-203 - Minion scaling implementation
undefined
  • Stratus架构指南
  • PROJ-203 - Minion扩展实现
undefined

Example 2: Conflicting Information

示例2:信息冲突

User: "How long is our session timeout?"
Process:
  1. Search across Confluence and Jira
  2. Find: Docs say 30 min, but ticket reports actual timeout is 15 min
  3. Fetch both sources for complete context
  4. Clearly note the discrepancy
Answer:
There is a discrepancy between documented and actual behavior:

**Official Documentation** (Security Guidelines):
Session timeout is configured for 30 minutes of inactivity.

**Actual Behavior** (PROJ-456, reported Oct 2023):
Users are being logged out after 15 minutes due to a load balancer configuration 
that overrides the application setting.

**Current Status:**
The engineering team is aware of this issue. The load balancer timeout needs to 
be adjusted to match the application setting. No fix timeline has been set.

**Recommendation:** Plan for 15-minute timeout until this is resolved.
用户: "我们的会话超时时间是多久?"
流程:
  1. 跨Confluence和Jira搜索
  2. 发现:文档说明30分钟,但工单显示实际超时为15分钟
  3. 获取两个来源的完整上下文
  4. 明确注明差异
答案:
文档记录与实际行为存在差异:

**官方文档**(安全指南):
会话超时配置为无活动30分钟。

**实际行为**(PROJ-456,2023年10月提交):
由于负载均衡器配置覆盖了应用设置,用户会在15分钟后被登出。

**当前状态:**
工程团队已知晓此问题。负载均衡器超时需调整至与应用设置匹配。暂无修复时间表。

**建议:** 在问题解决前,按15分钟超时规划。

Sources

来源

  • Security Guidelines - Official documentation
  • PROJ-456 - Timeout discrepancy bug report
undefined
  • 安全指南 - 官方文档
  • PROJ-456 - 超时差异缺陷报告
undefined

Example 3: Partial Information

示例3:信息不完整

User: "Explain our deployment process"
Process:
  1. Search finds some information but not complete
  2. Synthesize what is available
  3. Note gaps in documentation
Answer:
Based on available documentation, here's what I found about the deployment process:

**Build Phase** (from Confluence "CI/CD Guide"):
1. Code pushed to main branch triggers GitHub Actions
2. Automated tests run (unit, integration)
3. Docker image built and pushed to registry

**Deployment Phase** (from Jira PROJ-789):
4. Staging deployment happens automatically
5. Manual approval required for production
6. Blue-green deployment strategy used

**Gaps in Documentation:**
I couldn't find documented information about:
- Rollback procedures
- Database migration handling
- Post-deployment verification steps

These details may exist in tribal knowledge or need to be documented.
用户: "解释我们的部署流程"
流程:
  1. 搜索找到部分信息但不完整
  2. 整合现有信息
  3. 注明文档中的空白
答案:
根据现有文档,以下是关于部署流程的信息:

**构建阶段**(来自Confluence“CI/CD指南”)
1. 代码推送到主分支触发GitHub Actions
2. 运行自动化测试(单元测试、集成测试)
3. 构建Docker镜像并推送至镜像仓库

**部署阶段**(来自Jira PROJ-789)
4. 自动部署到预发布环境
5. 生产环境部署需手动审批
6. 使用蓝绿部署策略

**文档空白:**
我未找到以下方面的文档信息:
- 回滚流程
- 数据库迁移处理
- 部署后验证步骤

这些细节可能存在于团队经验中或需要文档化。

Sources

来源

  • CI/CD Guide
  • PROJ-789 - Deployment pipeline implementation
Would you like me to search for more specific aspects of deployment?

---
  • CI/CD指南
  • PROJ-789 - 部署流水线实现
你希望我搜索部署流程的更具体方面吗?

---

Tips for High-Quality Answers

高质量答案技巧

Do:

建议:

✅ Always search before answering (don't rely on general knowledge) ✅ Cite all sources with links ✅ Note discrepancies explicitly ✅ Mention when information is old ✅ Provide context and examples ✅ Structure answers clearly with headers ✅ Link to related documentation
✅ 始终先搜索再回答(不要依赖通用知识) ✅ 为所有来源添加链接引用 ✅ 明确注明差异 ✅ 注明信息是否过时 ✅ 提供上下文和示例 ✅ 使用标题清晰组织答案 ✅ 链接到相关文档

Don't:

避免:

❌ Assume general knowledge applies to this company ❌ Make up information if search returns nothing ❌ Ignore conflicting information ❌ Quote entire documents (summarize instead) ❌ Overwhelm with too many sources (curate top 5-10) ❌ Forget to fetch details when snippets are insufficient

❌ 假设通用知识适用于本公司 ❌ 搜索无结果时编造信息 ❌ 忽略冲突信息 ❌ 引用整篇文档(改用摘要) ❌ 提供过多来源(精选前5-10条) ❌ 片段不足时忘记获取详细内容

When NOT to Use This Skill

不适用此技能的场景

This skill is for internal company knowledge only. Do NOT use for:
❌ General technology questions (use your training knowledge) ❌ External documentation (use web_search) ❌ Company-agnostic questions ❌ Questions about other companies ❌ Current events or news
Examples of what NOT to use this skill for:
  • "What is machine learning?" (general knowledge)
  • "How does React work?" (external documentation)
  • "What's the weather?" (not knowledge search)
  • "Find a restaurant" (not work-related)

此技能仅适用于公司内部知识。请勿用于:
❌ 通用技术问题(使用训练知识) ❌ 外部文档(使用web_search) ❌ 与公司无关的问题 ❌ 关于其他公司的问题 ❌ 当前事件或新闻
不适用此技能的示例:
  • "什么是机器学习?"(通用知识)
  • "React如何工作?"(外部文档)
  • "天气如何?"(非知识搜索)
  • "找一家餐厅"(与工作无关)

Quick Reference

快速参考

Primary tool:
search(cloudId, query)
- Use this first, always
Follow-up tools:
  • getConfluencePage(cloudId, pageId, contentFormat)
    - Get full page content
  • getJiraIssue(cloudId, issueIdOrKey)
    - Get full issue details
  • searchConfluenceUsingCql(cloudId, cql)
    - Targeted Confluence search
  • searchJiraIssuesUsingJql(cloudId, jql)
    - Targeted Jira search
Answer structure:
  1. Direct answer
  2. Detailed explanation
  3. Source attribution
  4. Discrepancies (if any)
  5. Citations with links
Remember:
  • Parallel search > Sequential search
  • Synthesize, don't just list
  • Always cite sources
  • Note conflicts explicitly
  • Be clear about gaps in documentation
主要工具:
search(cloudId, query)
- 始终优先使用
后续工具:
  • getConfluencePage(cloudId, pageId, contentFormat)
    - 获取完整页面内容
  • getJiraIssue(cloudId, issueIdOrKey)
    - 获取完整工单详情
  • searchConfluenceUsingCql(cloudId, cql)
    - 定向Confluence搜索
  • searchJiraIssuesUsingJql(cloudId, jql)
    - 定向Jira搜索
答案结构:
  1. 直接答案
  2. 详细解释
  3. 来源归因
  4. 差异点(如有)
  5. 带链接的引用
记住:
  • 并行搜索 > 顺序搜索
  • 整合信息,而非简单罗列
  • 始终引用来源
  • 明确注明冲突
  • 清晰说明文档空白