R
rrrrrredy/research-toolkit
Research methods, workflow tools, and independent review for AI agents, packaged as a Skill, plugin, and local MCP server.
无 SECURITY.md
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · HTTP 200 · 打开的是厂商自己的官网
我们没有从该仓库取到可核对的安装命令,也没有公开的远端端点。这两样都没有时,我们不出配置——编一条出来比不给更糟。 各客户端的接法 →
- ★ 数取值
- 314 ★ · rrrrrredy/research-toolkit · 取自 GitHub 搜索 API · (2026-11-13 20:00:50 核对)
- 来源明细
- 收录自 punkpeye/awesome-mcp-servers 榜单(我们从中收集的条目之一) · 条目类型:MCP 服务
- 收录与活跃
- 收录于 2026-10-23 · 最近见到 2026-11-14 · 共见到 26 次 · 被 33 个来源列出
- 评分构成
- 综合分 3,300 · 314 ★ · 33 个来源 · mcp
常见问题(答案都来自我们的记录)
它适合谁 / 用来做什么?
我们把它归在这些标签下: MCP 服务。标签来自条目自身,不是我们强加的分类。
谁维护它、还在更新吗?
仓库
rrrrrredy/research-toolkit;我们收录于 2026-10-23;最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。# Research Toolkit
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
English · 简体中文
Turn a research question or existing material into a report with concrete judgments and traceable sources.
Use it for industry research, product comparisons, company analysis and technical research. Start a new study, revise an existing report against its sources, or update conclusions when new material arrives. Your agent researches and writes; Toolkit supplies the methods and optional workflow tools.
Start here · See a research case · Agent setup · Documentation
## Quick start
Send this request to an agent that can read the repository and your sources. No installation is needed to use the methods directly.
text
Use Research Toolkit: https://github.com/rrrrrredy/research-toolkit
Read SKILL.md and follow the methods needed for this task.
Question or revision request: [Include the audience and intended use.]
Scope and length: [Include the information cutoff and counting unit.]
Material: [Attach sources, links or an existing report, if available.]
Use the complete research methods as needed to develop evidence, comparisons, explanations and judgments.
Deliver the complete report with usable citations; include a short change note
when revising. Maintain working records yourself and state the checks performed.
Start research: one usage guide
One method set supports long-form and in-depth research, revisions and updates. The request determines scope, length and depth; the agent loads methods, maintains records and completes agreed checks as needed.
Only need to review an existing report? Use the standalone Research Review Skill. Toolkit already includes these review capabilities; existing users do not need a second installation.
Have a draft or new material? Revise or update existing research, reusing completed research and its sources.
## Research case
APIs or browsers for AI agents. An English report drawing on 11 primary sources to compare API calls, DOM automation and visual interaction through completion, recovery and cost.
Read the report · Initial draft · Sources · Reviews and revisions
A revision that changes the decision
Before:
> There is no benefit in preserving this split if the API later covers document generation with adequate permissions and result checking.
After:
> If the API later covers document generation with adequate permissions and result checking, the original coverage gap disappears. Retiring the browser step then depends on whether the expected maintenance and recovery savings justify migration and revalidation costs.
The review identified a missing counterexample: replacing a working browser step may cost more than the expected savings. The revision makes that trade-off part of the recommendation.
Explore the revision
Public-source analysis dated 10 October 2026, not a deployment test. Also read the Chinese office-agent comparison and its source and revision archive.
## Agent setup
| How you want to use it | Entry |
| Read the methods directly | Send the request above; for files or text-only chats, see agent setup. |
Turn a research question or existing material into a report with concrete judgments and traceable sources.
Use it for industry research, product comparisons, company analysis and technical research. Start a new study, revise an existing report against its sources, or update conclusions when new material arrives. Your agent researches and writes; Toolkit supplies the methods and optional workflow tools.
Start here · See a research case · Agent setup · Documentation
## Quick start
Send this request to an agent that can read the repository and your sources. No installation is needed to use the methods directly.
text
Use Research Toolkit: https://github.com/rrrrrredy/research-toolkit
Read SKILL.md and follow the methods needed for this task.
Question or revision request: [Include the audience and intended use.]
Scope and length: [Include the information cutoff and counting unit.]
Material: [Attach sources, links or an existing report, if available.]
Use the complete research methods as needed to develop evidence, comparisons, explanations and judgments.
Deliver the complete report with usable citations; include a short change note
when revising. Maintain working records yourself and state the checks performed.
Start research: one usage guide
One method set supports long-form and in-depth research, revisions and updates. The request determines scope, length and depth; the agent loads methods, maintains records and completes agreed checks as needed.
Only need to review an existing report? Use the standalone Research Review Skill. Toolkit already includes these review capabilities; existing users do not need a second installation.
Have a draft or new material? Revise or update existing research, reusing completed research and its sources.
## Research case
APIs or browsers for AI agents. An English report drawing on 11 primary sources to compare API calls, DOM automation and visual interaction through completion, recovery and cost.
Read the report · Initial draft · Sources · Reviews and revisions
A revision that changes the decision
Before:
> There is no benefit in preserving this split if the API later covers document generation with adequate permissions and result checking.
After:
> If the API later covers document generation with adequate permissions and result checking, the original coverage gap disappears. Retiring the browser step then depends on whether the expected maintenance and recovery savings justify migration and revalidation costs.
The review identified a missing counterexample: replacing a working browser step may cost more than the expected savings. The revision makes that trade-off part of the recommendation.
Explore the revision
Public-source analysis dated 10 October 2026, not a deployment test. Also read the Chinese office-agent comparison and its source and revision archive.
## Agent setup
| How you want to use it | Entry |
| Read the methods directly | Send the request above; for files or text-only chats, see agent setup. |
收录徽章(可选)
想把收录标记放进 README 就复制这行,可选,不影响收录。
[](https://anclum.com/zh/s/rrrrrredy-research-toolkit/)
- 来源
- awesome · https://github.com/rrrrrredy/research-toolkit
- 按领域浏览
- MCP 服务
- Traction
- 314 ★
- 收录来源
- 33 个独立来源
- 收录于
- 今天
- 安全策略
- 我们没在该仓库根目录找到
SECURITY.md(这不代表不安全)
同类推荐
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。