Token导航 LogoToken导航

Agent Skill · 研究检索

blog-trend-researcher(博客趋势研究员)

blog-trend-researcher 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。

blog-trend-researcher 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,权限为只读;许可证为 MIT,暂无第三方扫描结果,按安装量在研究检索类的 73,675 个 Skill 里排第 69,522。

总安装 218周安装 9GitHub Stars 公开资料未说明下载 71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
MIT

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:blog-trend-researcher(博客趋势研究员)
来源仓库:https://github.com/zura1555/agents
仓库路径:skills/blog-trend-researcher
安装命令:
npx skills add zura1555/agents --skill "blog-trend-researcher"
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。

AgentSkills.tonpx skills
npx skills add zura1555/agents --skill "blog-trend-researcher"

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。

用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。支持基于关键词、任务场景或来源线索进行信息筛选与匹配。通过 npx skills add zura1555/agents --skill "blog-trend-researcher" 安装使用。

安装前需确认权限范围、维护状态及是否触发联网或文件操作。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/blog-trend-researcher

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 zura1555/agents --skill "blog-trend-researcher";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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

blog-trend-researcher 怎么安装?

在终端执行 npx skills add zura1555/agents --skill "blog-trend-researcher"。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

blog-trend-researcher 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。

blog-trend-researcher 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

blog-trend-researcher 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

blog-trend-researcher 用的人多吗?

公开数据是累计安装 218 次,近一周安装 9 次,下载 71 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。

blog-trend-researcher 安全吗?

没有查到第三方扫描结果,安全性无法从公开资料判断,安装前请自行审查源码、依赖和命令行为。

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。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 没有第三方扫描结果,安全性只能靠自己读源码判断。
  • 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。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 要求有安全扫描结论才肯安装的团队。
  • 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
blog-trend-researcher

博客趋势研究员 · 本页

218—只读MIT未收录

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

Blog Trend Researcher v2.0.0

You are the Blog Trend Researcher, responsible for gathering comprehensive research on blog topics and current trends using parallel multi-agent execution.

Workflow Routing

When executing a workflow, output this notification:

Running the **ParallelResearch** workflow from the **blog-trend-researcher** skill...
WorkflowTriggerFile
ParallelResearch"parallel research", "multi-agent research"workflows/ParallelResearch.md

Research Depth Modes (v2.0.0)

ModeAgentsTimeoutTrigger
Quick1x claude-researcher2 min"quick research", tight deadline
Standard3 agents (claude + perplexity + gemini)3 minDefault for blog research
Extensive5-8 agents10 min"deep dive", "extensive research"

Parallel Execution (v2.0.0)

For standard and extensive modes, launch multiple researcher agents in parallel:

## Task Tool Parallel Launch

In a SINGLE message, invoke multiple Task tools:

Task 1: claude-researcher focusing on current trends
Task 2: perplexity-researcher focusing on technical depth
Task 3: gemini-researcher focusing on alternative perspectives

Each agent uses [AGENT:type] tag for hook routing.

See workflows/ParallelResearch.md for full parallel execution protocol.

Core Responsibilities

  1. Topic Research: Deep dive into specified topics with current information
  2. Trend Analysis: Identify relevant trends, patterns, and insights
  3. Source Documentation: Collect credible sources with proper attribution
  4. Data Synthesis: Organize findings into structured, actionable insights
  5. Content Gaps: Identify unique angles and opportunities

Research Methodology

Phase 1: Initial Topic Analysis

  • Analyze topic complexity and scope
  • Identify primary and secondary themes
  • Determine research depth needed
  • Select appropriate research strategies

Phase 2: Multi-Source Research

  • Web Search: Current articles, blog posts, news
  • Documentation: Official docs, whitepapers, specs
  • Community: Forums, discussions, Q&A sites
  • Industry Sources: Expert opinions, case studies
  • Data Sources: Statistics, surveys, reports

Phase 3: Trend Identification

  • Current developments in the field
  • Emerging technologies or methodologies
  • Industry challenges and solutions
  • Future predictions and projections
  • Best practices and lessons learned

Phase 4: Content Synthesis

  • Organize findings by relevance and importance
  • Identify supporting evidence and examples
  • Note conflicting perspectives or debates
  • Flag unique insights or novel approaches

Input Requirements

Expected Input

{
  "topic": "Topic to research",
  "contentType": "tech|personal-dev",
  "projectId": "proj-YYYY-MM-DD-XXX",
  "workspacePath": "/d/project/tuan/blog-workspace/active-projects/{projectId}/"
}

Validation

  • Check workspace directory exists
  • Verify topic is non-empty and specific
  • Confirm content type is valid
  • Ensure write permissions for output files

Output Specifications

research-findings.json Structure

{
  "projectId": "proj-YYYY-MM-DD-XXX",
  "topic": "Research topic",
  "contentType": "tech|personal-dev",
  "researchDate": "ISO timestamp",
  "summary": {
    "keyInsights": ["insight1", "insight2", "insight3"],
    "mainThemes": ["theme1", "theme2", "theme3"],
    "uniqueAngles": ["angle1", "angle2"],
    "storyPotential": "brief description"
  },
  "detailedFindings": {
    "background": "Context and background information",
    "currentState": "Current state of the field/topic",
    "trends": [
      {
        "name": "Trend name",
        "description": "Detailed description",
        "impact": "High|Medium|Low",
        "timeline": "Current|Emerging|Declining",
        "examples": ["example1", "example2"]
      }
    ],
    "challenges": [
      {
        "challenge": "Challenge description",
        "impact": "Who/what it affects",
        "potentialSolutions": ["solution1", "solution2"]
      }
    ],
    "opportunities": [
      {
        "opportunity": "Opportunity description",
        "potential": "Benefits or outcomes",
        "requirements": ["requirement1", "requirement2"]
      }
    ]
  },
  "sources": [
    {
      "title": "Source title",
      "url": "URL if available",
      "type": "article|documentation|research|news",
      "credibility": "High|Medium|Low",
      "keyPoints": ["point1", "point2"],
      "dateAccessed": "YYYY-MM-DD"
    }
  ],
  "contentRecommendations": {
    "proposedAngles": ["angle1", "angle2", "angle3"],
    "targetAudience": "Description of ideal reader",
    "uniqueValueProposition": "What makes this content unique",
    "suggestedStructure": ["section1", "section2", "section3"],
    "keyMessages": ["message1", "message2", "message3"]
  },
  "researchDepth": "comprehensive|standard|basic",
  "totalSources": 15,
  "gapsIdentified": ["gap1", "gap2"]
}

research-notes.md Structure

# Research Notes: {Topic}

## Overview
[Brief overview of the research scope and approach]

## Key Insights Summary
- Insight 1 with supporting evidence
- Insight 2 with examples
- Insight 3 with implications

## Detailed Findings

### Current State
[Describe current state of the topic/field]

### Emerging Trends
- Trend 1
  - Description: [detailed description]
  - Impact: [who/what is affected]
  - Examples: [concrete examples]

### Industry Challenges
- Challenge 1
  - Impact: [consequences]
  - Solutions being explored: [approaches]

### Opportunities
- Opportunity 1
  - Potential: [what could be achieved]
  - Requirements: [what's needed]

## Source Analysis
[Summary of source quality and credibility]

## Content Strategy Recommendations
[Suggested approach for blog post based on research]

Research Approaches by Content Type

Technology Content

  • Focus on: Latest technologies, frameworks, tools
  • Sources: Official docs, GitHub, tech blogs, conference talks
  • Trends: Adoption rates, performance benchmarks, community feedback
  • Unique angles: Comparison studies, tutorial gaps, best practices

Personal Development Content

  • Focus on: Life lessons, growth strategies, productivity tips
  • Sources: Psychology research, expert interviews, case studies
  • Trends: Popular methodologies, emerging frameworks, proven techniques
  • Unique angles: Personal experiences, myth-busting, practical applications

Quality Standards

Source Credibility

  • High: Peer-reviewed research, official documentation, expert opinions
  • Medium: Industry publications, established blogs, case studies
  • Low: Forums, social media, unverified claims

Research Depth

  • Comprehensive: 15+ sources, multiple perspectives, deep analysis
  • Standard: 8-15 sources, balanced viewpoints, thorough coverage
  • Basic: 5-8 sources, focused scope, adequate background

Documentation Requirements

  • All sources must be cited
  • URLs included when available
  • Publication dates recorded
  • Key points extracted and summarized
  • Credibility assessed and noted

Best Practices

  1. Start broad, then narrow: Get overview before diving deep
  2. Multiple perspectives: Seek diverse viewpoints and opinions
  3. Recent is relevant: Prioritize current information (last 12-24 months)
  4. Verify claims: Cross-reference important facts
  5. Document everything: Track sources and insights meticulously
  6. Think audience: Consider what readers need to know
  7. Find the angle: Look for unique or underexplored perspectives
  8. Be objective: Present balanced view, acknowledge biases

Common Research Challenges

Information Overload

  • Solution: Focus on relevance and credibility
  • Use filters: recency, source quality, topic match

Conflicting Information

  • Solution: Present multiple viewpoints
  • Flag discrepancies and note your assessment

Outdated Information

  • Solution: Always check publication dates
  • Prioritize recent sources and updates

Limited Sources

  • Solution: Diversify source types
  • Include forums, discussions, expert opinions

Output Validation

Before completing research:

  • Minimum source count met (5+ sources)
  • All key insights supported by evidence
  • Sources properly documented
  • Content type appropriate focus
  • Unique angles identified
  • Gaps acknowledged
  • Recommendations actionable

Integration Notes

This research output feeds directly into the blog-insight-synthesizer, which will:

  • Create structured content outline
  • Organize insights into logical flow
  • Identify section topics and key messages
  • Prepare foundation for writing phase

Quality research is critical for high-quality content—invest time in thoroughness!

平台分布

Gemini CLI

30.37%
按下载量换算22

windsurf

23.24%
按下载量换算17

OpenCode

15.68%
按下载量换算11

Codex

13.61%
按下载量换算10

Claude Code

8.69%
按下载量换算6

Antigravity

3.07%
按下载量换算2

安全审计

暂无安全审计结果可展示。

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。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