Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计提醒

research-methodology研究方法

Agent Skill

research-methodology 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。

总安装

927

周安装

39

GitHub Stars

15

下载量

324
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:research-methodology(研究方法)
来源仓库:https://github.com/nickcrew/claude-ctx-plugin
仓库路径:skills/research-methodology
安装命令:
npx skills add https://github.com/nickcrew/claude-ctx-plugin --skill research-methodology
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/nickcrew/claude-ctx-plugin --skill research-methodology

简介

research-methodology 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。

  • 适用于学术研究、市场调研和技术调研等需要系统性信息收集的场合。
  • 通过关键词匹配和来源仓库查询提供相关候选结果。
  • 安装命令为 npx skills add https://github.com/nickcrew/claude-ctx-plugin --skill research-methodology。
  • 使用前需确认权限范围、维护状态,以及是否会触发联网或文件读写操作。

SKILL.md

Research Methodology

Structured approach to finding, vetting, and synthesizing information from diverse sources. Turns research questions into trustworthy, actionable findings through systematic query design, source evaluation, and cross-referencing.

When to Use This Skill

  • Conducting competitive analysis or market scans
  • Investigating historical events, trends, or technical evolution
  • Fact-checking claims across multiple sources
  • Synthesizing research into structured deliverables (reports, tables, timelines)
  • Any research task that requires more than a single search query

Quick Reference

ResourcePurposeLoad when
references/search-strategies.mdQuery design, source vetting, fact verification, synthesis techniquesStarting any research task

Workflow

Phase 1: Scope       → Define research objective, key questions, constraints
Phase 2: Explore     → Design queries, search broadly, capture sources
Phase 3: Verify      → Vet sources, cross-reference claims, assess credibility
Phase 4: Synthesize  → Organize findings into structured deliverables

Phase 1: Scope the Research

Before searching, clarify the research objective:

  1. State the question -- what exactly are we trying to learn?
  2. Define success criteria -- what does a complete answer look like?
  3. Set constraints -- time period, geography, domains, source types
  4. List hypotheses -- what do we expect to find? (helps detect bias)
  5. Identify key terms -- domain vocabulary, synonyms, related concepts

Scoping Template

**Research Question**: [precise question]
**Success Criteria**: [what constitutes a complete answer]
**Constraints**: [time period, scope, source types]
**Key Terms**: [domain vocabulary and synonyms]
**Initial Hypotheses**: [what we expect, to check against later]

Phase 2: Explore

Design multiple query variations and search broadly before narrowing:

  1. Create 3-5 query variations per research question
  2. Search broadly first -- cast a wide net with general terms
  3. Refine iteratively -- narrow based on initial results
  4. Track what you searched -- record every query for reproducibility

Query Design Principles

  • Use exact-match phrases in quotes for precision
  • Exclude noise with negative keywords
  • Target specific timeframes for recency or historical depth
  • Vary terminology across queries to avoid vocabulary bias
  • Use domain-specific operators when available (site:, filetype:, etc.)

Source Capture

For each promising source, record:

  • URL and access date
  • Key claims with direct quotes
  • Author/publisher and their domain authority
  • Any noted biases or limitations

Phase 3: Verify

Vet sources and cross-reference claims before trusting them:

  1. Assess source authority -- who wrote it, what are their credentials?
  2. Check recency -- is the information current enough for the question?
  3. Detect bias -- does the source have a commercial, political, or ideological interest?
  4. Triangulate -- require 2+ independent sources for any key claim
  5. Seek primary sources -- follow citation chains to the original data

Confidence Rating

LevelCriteria
Confirmed3+ independent, authoritative sources agree
Likely2 sources agree, no contradictions found
UncertainSingle source or sources disagree
ContestedCredible sources directly contradict each other

Phase 4: Synthesize

Organize findings into a structured deliverable:

Standard Research Report Structure

## Research Summary
[1-2 paragraph overview of findings]

## Key Findings
- [Finding 1] — [confidence level]
- [Finding 2] — [confidence level]

## Detailed Analysis
[Organized by theme or question]

## Source Credibility Assessment
| Source | Authority | Recency | Bias Risk | Rating |
|--------|-----------|---------|-----------|--------|

## Gaps and Limitations
[What we couldn't determine and why]

## Recommendations
[Next steps or actions based on findings]

Anti-Patterns

  • Do not rely on a single source for any key claim
  • Do not present uncertain findings as confirmed facts
  • Do not skip source vetting for convenience
  • Do not omit contradictory evidence -- always surface disagreements
  • Do not let initial hypotheses bias which findings you report

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

37.74%
按下载量换算122

Claude

28.95%
按下载量换算94

Cursor

19.8%
按下载量换算64

Gemini CLI

10.3%
按下载量换算33

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills