Token导航 LogoToken导航

Agent Skill · 研究检索

updating-knowledge(更新知识)

updating-knowledge 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

updating-knowledge 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为调用外部服务;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 61,880。

总安装 346周安装 14GitHub Stars 公开资料未说明下载 109核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:updating-knowledge(更新知识)
来源仓库:https://github.com/arielperez82/agents-and-skills
仓库路径:skills/updating-knowledge
安装命令:
npx skills add https://github.com/arielperez82/agents-and-skills --skill updating-knowledge
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/arielperez82/agents-and-skills --skill updating-knowledge

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

updating-knowledge 系统化更新领域知识,强调多源交叉验证与置信度标注。适用于保持技术栈与行业动态同步的场景。自动标记单一来源主张与知识缺口,避免错误传播。依赖 web_search 工具完成信息获取,不可离线运行。

适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/updating-knowledge

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/arielperez82/agents-and-skills --skill updatin…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要调用外部服务,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

updating-knowledge 怎么安装?

在终端执行 npx skills add https://github.com/arielperez82/agents-and-skills --skill updating-knowledg…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

updating-knowledge 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

updating-knowledge 需要什么权限?

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

updating-knowledge 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

updating-knowledge 用的人多吗?

公开数据是累计安装 346 次,近一周安装 14 次,下载 109 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

updating-knowledge 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
updating-knowledge

更新知识 · 本页

346—调用外部服务未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Updating Knowledge

Core Principles

  • 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

Preflight Check

CRITICAL: This skill requires web_search tool access.

Before proceeding:

  1. Verify WebSearch tool is available in tool set
  2. If NOT available:

- Immediately inform user: "I need web search enabled for research tasks." - DO NOT attempt research without web search - DO NOT proceed with workflow

If WebSearch is unavailable, fail fast—don't waste context attempting workarounds.

Imperative Triggers

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.

Research Workflow

1. Scope Definition (internal)

Identify in thinking block:

  • What specifically needs investigation
  • Current knowledge baseline
  • Known gaps
  • Required depth (overview vs comprehensive)

2. Source Gathering (2-10 tool calls)

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:

  • WebSearch - Find authoritative sources
  • mcp_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.

3. Synthesis (internal)

In thinking block:

  • Cross-validate major claims across sources
  • Note contradictions explicitly
  • Track publication dates
  • Assess source credibility
  • Identify remaining gaps

4. Output (concise)

Present findings concisely:

## [Topic]

**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

Quality Standards

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

Tool Usage Notes

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

Output Efficiency

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

Example Outputs

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

平台分布

Codex

33.82%
按下载量换算37

Claude

29.38%
按下载量换算32

Cursor

17.95%
按下载量换算20

Gemini CLI

9.6%
按下载量换算10

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

可疑

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills