updating-knowledge

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Updating Knowledge

更新知识

Core Principles

核心原则

  • Systematic > ad-hoc - Follow research methodology, don't scatter searches randomly
  • Cross-validate - Verify claims across multiple independent sources
  • Confidence tracking - Explicitly flag single-source claims and gaps
  • Concise output - Present findings efficiently, introspection in thinking blocks
  • 系统性 > 临时性 - 遵循研究方法论,避免随机零散搜索
  • 交叉验证 - 跨多个独立来源验证主张
  • 置信度追踪 - 明确标记单一来源的主张和信息缺口
  • 简洁输出 - 高效呈现研究结果,将思考过程放在思维块中

Preflight Check

事前检查

CRITICAL: This skill requires web_search tool access.
Before proceeding:
  1. Verify web_search tool is available in tool set
  2. If NOT available:
    • Immediately inform user: "I need web search enabled for research tasks. Please toggle on 'Web search' in the feature menu."
    • DO NOT attempt research without web_search
    • DO NOT proceed with workflow
If web_search is unavailable, fail fast—don't waste context attempting workarounds.
关键提示:该技能需要web_search工具权限。
开始前:
  1. 确认工具集中是否有web_search工具
  2. 如果没有:
    • 立即告知用户:“我需要启用网页搜索才能完成研究任务。请在功能菜单中开启‘Web search’功能。”
    • 禁止在无web_search工具的情况下尝试研究
    • 禁止继续执行工作流程
如果web_search不可用,立即终止操作——不要浪费时间尝试替代方案。

Imperative Triggers

强制触发条件

Use this skill when:
  • User says "Research", "Investigate", "What's current on", "Latest info on", "Find out about"
  • Query requires synthesizing multiple authoritative sources
  • Topic likely changed since training cutoff
  • Technical/product questions where documentation is essential
  • Contradictory information needs resolution
  • Building comprehensive understanding for ongoing work
Note: Avoid triggering on generic action verbs like "update" (which could mean file/code changes). Focus on explicit knowledge-gathering requests.
在以下场景中使用该技能:
  • 用户说出“Research”“Investigate”“What's current on”“Latest info on”“Find out about”
  • 查询需要整合多个权威来源的信息
  • 主题自训练截止日期后可能发生变化
  • 技术/产品问题需要参考官方文档
  • 需要解决相互矛盾的信息
  • 为后续工作构建全面的认知
注意: 避免因通用动作动词(如“update”,可能指文件/代码修改)触发该技能。专注于明确的知识收集请求。

Research Workflow

研究工作流程

1. Scope Definition (internal)

1. 范围定义(内部)

Identify in thinking block:
  • What specifically needs investigation
  • Current knowledge baseline
  • Known gaps
  • Required depth (overview vs comprehensive)
在思维块中明确:
  • 具体需要调查的内容
  • 当前的知识基线
  • 已知的信息缺口
  • 所需的研究深度(概述 vs 全面研究)

2. Source Gathering (2-10 tool calls)

2. 来源收集(2-10次工具调用)

Source priority:
  1. Official documentation, project repos, company announcements
  2. Academic papers, technical blogs with clear expertise
  3. Community discussions (for ecosystem context only)
Tool selection:
  • web_search
    - Find authoritative sources
  • web_fetch
    - Extract complete content from any URL (no prior search required)
  • Internal tools (GitHub, Drive, etc.) - Company/personal context
  • Multiple tool types as needed
Gather 3-5 diverse sources minimum for cross-validation.
来源优先级:
  1. 官方文档、项目仓库、企业公告
  2. 学术论文、具备明确专业背景的技术博客
  3. 社区讨论(仅用于了解生态环境)
工具选择:
  • web_search
    - 查找权威来源
  • web_fetch
    - 从任意URL提取完整内容(无需预先搜索)
  • 内部工具(GitHub、Drive等) - 企业/个人专属信息
  • 根据需要组合使用多种工具
至少收集3-5个不同来源用于交叉验证。

3. Synthesis (internal)

3. 信息整合(内部)

In thinking block:
  • Cross-validate major claims across sources
  • Note contradictions explicitly
  • Track publication dates
  • Assess source credibility
  • Identify remaining gaps
在思维块中:
  • 跨来源交叉验证主要主张
  • 明确标记矛盾点
  • 记录发布日期
  • 评估来源可信度
  • 识别剩余的信息缺口

4. Output (concise)

4. 输出(简洁)

Present findings concisely:
markdown
undefined
简洁呈现研究结果:
markdown
undefined

[Topic]

[主题]

Key findings: [2-3 sentence summary with most important updates]
Current state: [Concise description of what's true now]
Changes since cutoff: [Only if relevant - what's different]
Gaps: [Only if user needs to know - what wasn't found]
Sources: [URLs]

**Confidence indicators:**
- State explicitly when claims are single-source
- Note contradictions between sources
- Flag unverified information
- Quantify confidence (high/medium/low) when uncertain
关键发现: [2-3句话总结最重要的更新内容]
当前状态: [简洁描述当前的实际情况]
自训练截止日期后的变化: [仅在相关时列出 - 有哪些不同之处]
信息缺口: [仅在用户需要时列出 - 未找到的内容]
来源:[URL列表]

**置信度标识:**
- 明确说明主张是否仅来自单一来源
- 标记来源之间的矛盾点
- 标记未经验证的信息
- 不确定时量化置信度(高/中/低)

Quality Standards

质量标准

Minimum requirements:
  • 3+ independent sources consulted
  • Major claims cross-validated
  • Explicit confidence assessment
  • Remaining gaps identified when relevant
Avoid:
  • Single-source claims presented as definitive
  • Ignoring publication dates
  • Marketing language as fact
  • Verbose deliberation in final output (use thinking blocks)
  • Over-explaining research process to user
最低要求:
  • 参考3个以上独立来源
  • 主要主张经过交叉验证
  • 明确的置信度评估
  • 相关时识别剩余的信息缺口
需避免:
  • 将单一来源的主张作为定论呈现
  • 忽略发布日期
  • 将营销话术视为事实
  • 在最终输出中加入冗长的思考过程(使用思维块)
  • 向用户过度解释研究流程

Tool Usage Notes

工具使用说明

web_fetch capabilities:
  • Can fetch ANY URL directly - doesn't require prior search results
  • Use for complete documentation pages, technical articles
  • Effective for deep content extraction after search identifies sources
web_search patterns:
  • Start specific, broaden if needed
  • Never repeat similar queries - make each unique
  • Use current date context when relevant (November 2025)
Internal tools:
  • Prioritize for company/personal data
  • Combine with web tools for comparative analysis
web_fetch功能:
  • 可直接获取任意URL的内容 - 无需预先搜索结果
  • 用于获取完整的文档页面、技术文章
  • 在搜索确定来源后,可有效进行深度内容提取
web_search模式:
  • 从具体查询开始,必要时再扩大范围
  • 切勿重复相似查询 - 确保每个查询都独一无二
  • 相关时使用当前日期上下文(2025年11月)
内部工具:
  • 优先用于企业/个人数据
  • 结合网页工具进行对比分析

Output Efficiency

输出效率

DO:
  • Present findings concisely
  • Use thinking blocks for deliberation
  • Lead with key takeaways
  • State confidence explicitly when low
  • Cite sources inline
DON'T:
  • Narrate research process unless asked
  • Include verbose phase descriptions
  • Over-explain methodology
  • Repeat information across sections
  • Document internal reasoning in output
需要做:
  • 简洁呈现研究结果
  • 使用思维块进行思考
  • 优先展示关键结论
  • 置信度低时明确说明
  • 内联标注来源
不要做:
  • 除非被询问,否则不要叙述研究流程
  • 不要加入冗长的阶段描述
  • 不要过度解释方法论
  • 不要在各部分重复信息
  • 不要在输出中记录内部推理过程

Example Outputs

示例输出

Technical documentation inquiry:
TypeScript 5.3 (Nov 2023) added import attributes for JSON modules. The syntax uses `with` instead of deprecated `assert`. Runtime performance unchanged—validation happens at parse time.

Gap: No official benchmarks comparing validation overhead across bundlers.

Sources: [TS release notes, GitHub issue #54242, esbuild docs]
Conflicting information:
React Server Components ship in Next.js 13.4+ (stable) and Remix 2.0 (experimental). 

Contradiction: Meta's blog claims "production-ready" while Remix docs flag "breaking changes expected." Cross-validation shows Meta refers to Next.js implementation only.

Confidence: High on Next.js status, medium on Remix timeline.

Sources: [Next.js changelog, Remix docs, React.dev]
Avoid narrating process:
❌ "After conducting extensive research and cross-validating multiple authoritative sources..."
✓ Just present findings with source attribution
技术文档查询:
TypeScript 5.3(2023年11月)为JSON模块新增了import attributes。语法使用`with`替代已弃用的`assert`。运行时性能无变化——验证在解析阶段完成。

信息缺口:暂无官方基准测试对比不同打包工具的验证开销。

来源:[TS发布说明, GitHub Issue #54242, esbuild文档]
矛盾信息处理:
React Server Components已在Next.js 13.4+(稳定版)和Remix 2.0(实验版)中推出。 

矛盾点:Meta博客称其“可用于生产环境”,而Remix文档标注“预计会有破坏性变更”。交叉验证显示Meta仅指代Next.js中的实现。

置信度:Next.js状态为高置信度,Remix时间线为中置信度。

来源:[Next.js更新日志, Remix文档, React.dev]
避免叙述流程:
❌ "在进行了广泛研究并交叉验证多个权威来源..."
✓ 直接呈现研究结果并标注来源