research-toolkit

# Research Toolkit

> Complete research methods for in-depth analysis and long-form reports. 一套完整研究方法，支持深度分析与长文写作。

Use the methods through repository access, files, attachments, or pasted instructions. Native Skill installation is optional for reading methods. In Codex, Claude Code and OpenCode, the agent reuses existing local usage configuration and configures it with the bundled Python 3.10+ script when needed; reload an open Codex session only when its configuration changed. Research continues while recording awaits activation. See usage-data.md for setup and controls. Plugin and local MCP integrations provide executable workflow tools; their shared context, handoff and independent-agent review are described in the usage guide. The agent tool runs independent production and assessment agents without separate API setup.

The four connected responsibilities are task/context, evidence/analysis, writing/revision and review/delivery. Content perspectives, domain review, audit and final acceptance use separate independent agent contexts.

## Research methods


- [Research instructions](https://raw.githubusercontent.com/rrrrrredy/research-toolkit/main/SKILL.md): The entry point, with links to methods for each research stage.
- [中文研究指令](https://raw.githubusercontent.com/rrrrrredy/research-toolkit/main/SKILL.zh-CN.md): Chinese reading version.
- [Research guide](https://raw.githubusercontent.com/rrrrrredy/research-toolkit/main/docs/research-guide.md): Research scope, evidence, writing, and review.

## Usage

- [Project overview](https://raw.githubusercontent.com/rrrrrredy/research-toolkit/main/README.md): Capabilities, a complete research request, and the case study.
- [中文项目介绍](https://raw.githubusercontent.com/rrrrrredy/research-toolkit/main/README.zh-CN.md): Chinese overview and research request.
- [Agent setup](https://raw.githubusercontent.com/rrrrrredy/research-toolkit/main/agents/README.md): Repository, file, attachment, and text input methods.
- [Tools and configuration](https://raw.githubusercontent.com/rrrrrredy/research-toolkit/main/docs/usage-modes.md): Optional plugin/MCP setup, common task context, native-agent assignments and current delivery contract.
- [工具与配置](https://raw.githubusercontent.com/rrrrrredy/research-toolkit/main/docs/usage-modes.zh-CN.md): Chinese usage guide.

## Research case

- [Current English report](https://rrrrrredy.github.io/research-toolkit/case-study/long-research-2026-11/test-time-compute.en.html): Test-time compute for reasoning models and agents, through 9 November 2026; mechanisms, evidence, comparisons and design choices.
- [当前中文报告](https://rrrrrredy.github.io/research-toolkit/case-study/long-research-2026-11/microdrama.zh-CN.html): 中国微短剧市场的增长、竞争与产业链价值分配，资料截至2026年11月9日。
- [Bilingual research archive](https://rrrrrredy.github.io/research-toolkit/case-study/long-research-2026-11/): Independent English and Chinese reports, original manuscripts and review records.
- [Long-research benchmark](https://raw.githubusercontent.com/rrrrrredy/research-toolkit/main/evals/README.md): Thirteen independent questions and fifteen report assignments across research fields, with reusable execution and judgment arrangements.

- [Updating an existing research report](https://rrrrrredy.github.io/research-toolkit/case-study/coding-benchmark-update/): old report, changed evidence, concrete revisions and preserved originals.
- [已有研究报告的实际更新](https://rrrrrredy.github.io/research-toolkit/case-study/coding-benchmark-update/index.zh-CN.html): 中文场景说明，链接旧稿、新材料、具体修订及实验限制。

- [APIs or browsers for AI agents](https://raw.githubusercontent.com/rrrrrredy/research-toolkit/main/docs/case-study/api-or-browser/report.md): original English research from primary documentation on action coverage, completion, recovery, and cost; no comparative performance experiment.
- [English case archive](https://raw.githubusercontent.com/rrrrrredy/research-toolkit/main/docs/case-study/api-or-browser/README.md): the retained first draft, sources, claims, complete reviews, and revision decision.
- [国内办公 Agent 调研](https://raw.githubusercontent.com/rrrrrredy/research-toolkit/main/docs/case-study/report.zh-CN.md): Chinese report.
- [Chinese case archive](https://raw.githubusercontent.com/rrrrrredy/research-toolkit/main/docs/case-study/office-agents/README.md): Initial and final manuscripts, sources, and review decisions. The revisions are not a controlled test of toolkit effectiveness.

## Optional

- [Documentation index](https://raw.githubusercontent.com/rrrrrredy/research-toolkit/main/docs/README.md): Detailed methods and development documentation.
- [Evaluation status](https://raw.githubusercontent.com/rrrrrredy/research-toolkit/main/docs/evaluation-status.md): Available evaluation evidence and its limits.

- [Start research](https://raw.githubusercontent.com/rrrrrredy/research-toolkit/main/docs/quickstart.md): one complete research entry.
- [开始研究](https://raw.githubusercontent.com/rrrrrredy/research-toolkit/main/docs/quickstart.zh-CN.md): 完整研究入口。