Deep Research

by feiskyer

Deep Research is an AI Engineering skill for Claude Code, published by feiskyer in codex-settings.

237 stars33 forkson feiskyer/codex-settingsAdded 2026/09/03Repository updated 2026/08/13

View source on GitHub Download repo ZIP

agent-skillsagentic-aiagentsaiai-codingcodexcodex-clicodex-profilescodex-skillscopilotlitellmmcpopenaivibe-coding

Install in seconds

Install Deep Research

Copy Deep Research into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/feiskyer/codex-settings/tree/main/skills/deep-research ~/.claude/skills/deep-research

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/feiskyer/codex-settings.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/deep-research/SKILL.md in feiskyer/codex-settings
Installs to: ~/.claude/skills/deep-research
Collection: One of 11 skills cataloged from this repository
Category: AI Engineering — 2793 skills

What Deep Research does

Deep Research orchestrates a multi-agent workflow that splits a research goal into parallel sub-tasks, gathers evidence with Codex CLI subprocesses, and merges the results into a verified report. Use it for systematic web or document research, competitor analysis, and long-form evidence synthesis.

Deep Research is cataloged under AI Engineering on DirSkills. Deep Research comes from a repository tagged agent-skills, agentic-ai, agents, ai and ai-coding.

Documentation

README

Excerpt

Deep Research

把深度调研作为可重复、可审计的生产流程执行。主控负责目标澄清、样本摸底、子任务设计、结果核验和最终综合；子进程负责边界清晰的采集或局部分析。

核心约束

保持用户当前模型和推理配置，不传 --model，不覆盖无关配置。
子进程默认使用 workspace-write；只有确实需要 shell 网络访问时才启用 runner 的 --network。
先检查当前会话可用的 Skills、连接器和 MCP，再按来源适配能力；不要假设固定服务或工具名存在。
不使用 --dangerously-bypass-approvals-and-sandbox。
所有运行产物写入独立的 .research/<name>/ 目录。
在开始批量执行前向用户展示拆分方案；需要明显成本、长时间运行或外部系统访问时，等待明确同意。

Bundled scripts

先解析当前 Skill 的绝对目录并记为 <skill-dir>。

scripts/run_children.py：跨平台并行执行 codex exec，负责超时、重试、日志和结果状态。
scripts/aggregate.py：按 manifest 顺序聚合成功的子报告，缺失或空结果时失败。

两个脚本都使用 Python 标准库，不生成临时 shell 脚本。

Frequently asked about Deep Research

What else does feiskyer publish alongside Deep Research?
Deep Research is one of 11 skills that DirSkills catalogs from feiskyer/codex-settings, the repository it ships in. Its siblings there include Brainstorming, Claude Code Headless Mode and GPT Image. Each one is a separate skill with its own page in this directory, installs the same way Deep Research does, and is maintained by feiskyer in that same repository. The rest of the collection is listed on the feiskyer/codex-settings page.
How does Deep Research compare to other AI Engineering skills?
Deep Research ranks #2437 by stars among the 2793 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Deep Research against them. Open each page to compare what they document and how they install.