Skip to content
Back to search

deep-research-skills

Structured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/weizhena--deep-research-skills/badge.svg)](/listings/weizhena--deep-research-skills)

HTML

<a href="/listings/weizhena--deep-research-skills"><img src="/api/listings/weizhena--deep-research-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

git clone https://github.com/Weizhena/deep-research-skills.git
cd deep-research-skills

Claude Code

# English version
cp -r skills/research-en/* ~/.claude/skills/

# Chinese version
cp -r skills/research-zh/* ~/.claude/skills/

# Required: Install agent and modules
cp agents/web-search-agent.md ~/.claude/agents/
cp -r agents/web-search-modules ~/.claude/agents/

# Required: Install Python dependency
pip install pyyaml

OpenCode (default: gpt-5.4)

# Skills (same as Claude Code)
cp -r skills/research-en/* ~/.claude/skills/   # or research-zh for Chinese

# Required: Enable web search for current shell
export OPENCODE_ENABLE_EXA=1

# Optional: make it permanent
echo 'export OPENCODE_ENABLE_EXA=1' >> ~/.bashrc
source ~/.bashrc

# Required: Install agent and modules
cp agents/web-search-opencode.md ~/.config/opencode/agents/web-search.md
cp -r agents/web-search-modules ~/.config/opencode/agents/

# Required: Install Python dependency
pip install pyyaml

> **Important**: In OpenCode, ANY model's websearch requires `OPENCODE_ENABLE_EXA=1`. A plain `export` only affects the current shell; writing it to `~/.bashrc` makes it persistent. Without it, you only get `web fetch`, which is weaker for the deep research phase.

Codex

# English version
mkdir -p ~/.codex/skills ~/.codex/agents
cp -r skills/research-codex-en/* ~/.codex/skills/

# Chinese version
mkdir -p ~/.codex/skills ~/.codex/agents
cp -r skills/research-codex-zh/* ~/.codex/skills/

# Required: Install web researcher agent and modules
cp agents-codex/web-researcher.toml ~/.codex/agents/
cp -r agents-codex/web-search-modules ~/.codex/agents/

# Required: Install Python dependency
pip install pyyaml

Add or update `~/.codex/config.toml` using either method below:

**Option A: Automatic script**

cd deep-research-skills
bash scripts/install-codex.sh

**Option B: Manual edit**

suppress_unstable_features_warning = true

[features]
multi_agent = true
default_mode_request_user_input = true

[agents.web_researcher]
description = "Use this agent when you need to research information on the internet, particularly for debugging issues, finding solutions to technical problems, or gathering comprehensive information from multiple sources. This agent excels at finding relevant discussions. Use when you need creative search strategies, thorough investigation, or compilation of findings from multiple sources."
config_file = "agents/web-researcher.toml"

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 170 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Deep Research Skill for Claude Code / OpenCode / Codex
  2. [English](README.md) | [中文](README.zh.md)
  3. > If you find this project helpful, please give it a star! :star:
  4. > Inspired by [RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Context](https://arxiv.org/abs/2511.18743)
  5. A structured research workflow skill for Claude Code, OpenCode, and Codex, supporting two-phase research: outline generation (extensible) and deep investigation. Human-in-the-loop design ensures precise control at every stage.
  6. ![Deep Research Skills Workflow](workflow.png)
  7. ## Use Cases
  8. - **Academic Research**: Paper surveys, benchmark reviews, literature analysis
  9. - **Technical Research**: Technology comparison, framework evaluation, tool selection
  10. - **Market Research**: Competitor analysis, industry trends, product comparison
  11. - **Due Diligence**: Company research, investment analysis, risk assessment
  12. ## Installation
  13. ```bash
  14. git clone https://github.com/Weizhena/deep-research-skills.git
  15. cd deep-research-skills
  16. ```
  17. ### Claude Code
  18. ```bash
  19. # English version
  20. cp -r skills/research-en/* ~/.claude/skills/
  21. # Chinese version
  22. cp -r skills/research-zh/* ~/.claude/skills/
  23. # Required: Install agent and modules
  24. cp agents/web-search-agent.md ~/.claude/agents/
  25. cp -r agents/web-search-modules ~/.claude/agents/
  26. # Required: Install Python dependency
  27. pip install pyyaml
  28. ```
  29. ### OpenCode (default: gpt-5.4)
  30. ```bash
  31. # Skills (same as Claude Code)
  32. cp -r skills/research-en/* ~/.claude/skills/ # or research-zh for Chinese
  33. # Required: Enable web search for current shell
  34. export OPENCODE_ENABLE_EXA=1
  35. # Optional: make it permanent
  36. echo 'export OPENCODE_ENABLE_EXA=1' >> ~/.bashrc
  37. source ~/.bashrc
  38. # Required: Install agent and modules
  39. cp agents/web-search-opencode.md ~/.config/opencode/agents/web-search.md
  40. cp -r agents/web-search-modules ~/.config/opencode/agents/
  41. # Required: Install Python dependency
  42. pip install pyyaml
  43. ```
  44. > **Important**: In OpenCode, ANY model's websearch requires `OPENCODE_ENABLE_EXA=1`. A plain `export` only affects the current shell; writing it to `~/.bashrc` makes it persistent. Without it, you only get `web fetch`, which is weaker for the deep research phase.
  45. ### Codex
  46. ```bash
  47. # English version
  48. mkdir -p ~/.codex/skills ~/.codex/agents
  49. cp -r skills/research-codex-en/* ~/.codex/skills/
  50. # Chinese version
  51. mkdir -p ~/.codex/skills ~/.codex/agents
  52. cp -r skills/research-codex-zh/* ~/.codex/skills/
  53. # Required: Install web researcher agent and modules
  54. cp agents-codex/web-researcher.toml ~/.codex/agents/
  55. cp -r agents-codex/web-search-modules ~/.codex/agents/
  56. # Required: Install Python dependency
  57. pip install pyyaml
  58. ```
  59. Add or update `~/.codex/config.toml` using either method below:
  60. **Option A: Automatic script**
  61. ```bash
  62. cd deep-research-skills
  63. bash scripts/install-codex.sh
  64. ```
  65. **Option B: Manual edit**
  66. ```toml
  67. suppress_unstable_features_warning = true
  68. [features]
  69. multi_agent = true
  70. default_mode_request_user_input = true
  71. [agents.web_researcher]
  72. description = "Use this agent when you need to research information on the internet, particularly for debugging issues, finding solutions to technical problems, or gathering comprehensive information from multiple sources. This agent excels at finding relevant discussions. Use when you need creative search strategies, thorough investigation, or compilation of findings from multiple sources."
  73. config_file = "agents/web-researcher.toml"
  74. ```
  75. ## Commands
  76. > **Claude Code 2.1.0+**: Direct `/skill-name` trigger is now supported!
  77. >
  78. > **Older versions**: Use `run /skill-name` format instead.
  79. >
  80. > **Codex**: You can trigger these skills from `/skills` -> `List Skills`, or ask naturally, for example `Use the research skill to build an outline for AI Agent Demo 2025`.
  81. | Command (2.1.0+) | Description |
  82. |------------------|-------------|
  83. | `/research` | Generate research outline with items and fields |
  84. | `/research-add-items` | Add more research items to existing outline |
  85. | `/research-add-fields` | Add more field definitions to existing outline |
  86. | `/research-deep` | Deep research each item with parallel agents |
  87. | `/research-report` | Generate markdown report from JSON results |
  88. ## Workflow & Example
  89. > **Example**: Researching "AI Agent Demo 2025"
  90. ### Phase 1: Generate Outline
  91. ```
  92. /research AI Agent Demo 2025
  93. ```
  94. 💡 **What will happen**: Tell it your topic → It creates a research list for you
  95. **You get**: A list of 17 AI Agents to research (ChatGPT Agent, Claude Computer Use, Cursor, etc.) + what info to collect for each
  96. ### (Optional) Not satisfied? Add more
  97. ```
  98. /research-add-items
  99. /research-add-fields
  100. ```
  101. 💡 **What will happen**: Add more research items or field definitions
  102. ### Phase 2: Deep Research
  103. ```
  104. /research-deep
  105. ```
  106. 💡 **What will happen**: AI automatically searches the web for each item, one by one
  107. **You get**: Detailed info for each Agent (company, release date, pricing, tech specs, reviews...)
  108. ### Phase 3: Generate Report
  109. ```
  110. /research-report
  111. ```
  112. 💡 **What will happen**: All data → One organized report
  113. **You get**: `report.md` - A complete markdown report with table of contents, ready to read or share
  114. ## Need Help?
  115. If you have questions, ask Claude Code, OpenCode, or Codex to explain this project:
  116. ```
  117. Help me understand this project: https://github.com/Weizhena/deep-research-skills
  118. ```
  119. ## References
  120. - RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Context
  121. ## License
  122. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.