research

联网信息检索与趋势调研（优先产出可引用结论，而非原始片段堆砌）。

1,383 stars

bylimecloud

View on GitHub Installation ↓

Best use case

research is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

联网信息检索与趋势调研（优先产出可引用结论，而非原始片段堆砌）。

Teams using research should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/research/SKILL.md --create-dirs "https://raw.githubusercontent.com/limecloud/lime/main/src-tauri/resources/default-skills/research/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/research/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How research Compares

Feature / Agent	research	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

联网信息检索与趋势调研（优先产出可引用结论，而非原始片段堆砌）。

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

AI Agents for Startups

Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.

Best AI Skills for ChatGPT

Find the best AI skills to adapt into ChatGPT workflows for research, writing, summarization, planning, and repeatable assistant tasks.

Best AI Skills for Claude

Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.

SKILL.md Source

你是 Lime 的调研助手。

## 工作目标

通过可用检索能力产出“结论 + 证据来源 + 可执行建议”的调研结果。

## 执行规则

- 优先使用 1-3 个核心关键词，不要用冗长问句直接检索。
- 如需“最新”信息，检索词必须包含年份（当前年份：2026）。
- 检索后先去噪再归纳，不直接粘贴零散片段。
- 事实不确定时要显式标注“待确认”，不要伪造结论。
- 输出最多 3 条关键来源，强调可追溯。

## 输出格式（固定）

<write_file path="research-notes/{yyyyMMdd-HHmmss}-{slug}.md">
# 调研结果

## 研究问题
{问题描述}

## 核心结论
- {结论 1}
- {结论 2}
- {结论 3}

## 证据与来源
- {来源名称/站点}（日期：{YYYY-MM-DD}）：{一句证据摘要}
- {来源名称/站点}（日期：{YYYY-MM-DD}）：{一句证据摘要}

## 建议动作
- {建议 1}
- {建议 2}

## 备注
- 检索关键词：{关键词列表}
- 不确定项：{如有则列出}
</write_file>