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

research-strategy研究策略

Agent Skill

research-strategy 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

1,717

周安装

73

GitHub Stars

4

下载量

602
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-strategy(研究策略)
来源仓库:https://github.com/autumnsgrove/groveengine
仓库路径:skills/research-strategy
安装命令:
npx skills add https://github.com/autumnsgrove/groveengine --skill research-strategy
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/autumnsgrove/groveengine --skill research-strategy

简介

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。

  • 适用于需要根据关键词或任务场景进行信息检索的研究类 Agent 工作流。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装使用。
  • 建议确认权限范围和维护状态,注意可能触发联网或文件读写操作。
  • research-strategy 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Research Strategy Skill

When to Activate

Activate this skill when:

  • Researching technology options
  • Evaluating libraries or frameworks
  • Investigating best practices
  • Analyzing security concerns
  • Making architectural decisions
  • Performing codebase analysis

Core Principles

  • Research and report, don't implement
  • Multiple sources beat single sources
  • Document confidence levels for all findings
  • Acknowledge knowledge gaps openly
  • Present alternatives objectively

7-Step Research Methodology

  1. Define Research Questions - What exactly needs answering?
  2. Identify Information Sources - Where to look?
  3. Gather Raw Information - Collect systematically
  4. Cross-Reference Findings - Verify across sources
  5. Validate Accuracy - Check dates, authority, consensus
  6. Identify Gaps - What's still unknown?
  7. Synthesize Insights - Connect into actionable knowledge

Source Prioritization

  1. Primary Sources (Highest priority)

- Official documentation - Technical specifications - API references

  1. Authoritative Sources

- Well-maintained libraries - Industry standards (OWASP, NIST) - Academic papers

  1. Community Sources

- Stack Overflow discussions - GitHub issues/PRs - Technical blogs

  1. Experimental Sources (Use with caution)

- Beta features - Draft proposals

Confidence Scoring

Assign to ALL findings:

LevelRangeCriteria
HIGH90-100%Multiple authoritative sources agree, widely adopted
MEDIUM60-89%Good documentation, some adoption, minor disagreements
LOW30-59%Limited sources, conflicting information
SPECULATIVE<30%Educated guess, no direct sources

Research Report Structure

# Research Report: [Topic]

## Executive Summary
[2-3 paragraphs: key findings, recommendation, confidence]

## Research Questions
1. [Question 1]
2. [Question 2]

## Key Findings

### Finding 1: [Title]
**Confidence**: HIGH/MEDIUM/LOW
**Sources**: [List with links]
[Detailed explanation]
**Implications**: [How this affects decisions]

## Comparative Analysis

| Aspect | Option A | Option B |
|--------|----------|----------|
| Performance | Details | Details |
| Learning Curve | Details | Details |

## Best Practices
1. **[Practice]**: Why, Source, Adoption level

## Risks and Concerns
- **Risk**: Severity, Likelihood, Mitigation

## Knowledge Gaps
- **Gap**: Impact, How to address

## Recommendations
[Clear, actionable recommendations with confidence levels]

Library/Framework Research Template

## Overview
- Purpose: [One sentence]
- Maturity: Stable/Beta/Experimental
- Last commit: [Date]
- License: [Type]

## Technical Assessment
- Performance: [Benchmarks]
- Bundle Size: [KB]
- Dependencies: [Count, quality]

## Developer Experience
- Documentation: Excellent/Good/Fair/Poor
- TypeScript: Built-in/DefinitelyTyped/None
- Learning Curve: Steep/Moderate/Gentle

## Verdict
**Recommendation**: Use/Don't Use/Conditional
**Confidence**: HIGH/MEDIUM/LOW
**When to Use**: [Scenarios]
**When to Avoid**: [Scenarios]

Analysis Framework

For each topic, answer:

Current State

  • What exists today?
  • What patterns are established?

Best Practices

  • What do experts recommend?
  • What anti-patterns to avoid?

Trade-offs

  • What are alternatives?
  • Pros/cons of each option?

Risks

  • What could go wrong?
  • Common pitfalls?

Anti-Patterns to Avoid

Single Source Syndrome

  • "According to this one article..."
  • ✅ "Multiple sources agree (A, B, C)..."

Premature Implementation

  • "Here's the code..."
  • ✅ "Implementation would follow this approach..."

Missing Confidence Levels

  • "This is the way."
  • ✅ "HIGH confidence: Recommended by [sources]..."

Outdated Information

  • Using 2020 practices without checking updates
  • ✅ Verify current practices, note recent changes

Research Quality Checklist

Completeness

  • All questions answered
  • Multiple sources consulted (minimum 2-3)
  • Advantages AND disadvantages investigated
  • Edge cases considered

Accuracy

  • Sources are authoritative and current
  • Publication dates checked
  • Conflicting info acknowledged
  • Assumptions stated

Actionability

  • Findings translate to next steps
  • Risks quantified
  • Alternatives provided
  • Decision criteria clear

Related Resources

See AgentUsage/research_workflow.md for complete documentation including:

  • Security research template
  • Detailed report examples
  • Research mission template
  • Quality checklists

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

37.47%
按下载量换算226

Claude

29.94%
按下载量换算180

Cursor

17.58%
按下载量换算106

Gemini CLI

8.51%
按下载量换算51

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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