GitHub Deep Research
bytedance/deer-flow
Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.
Multi-agent research orchestration: split a research goal into parallel sub-goals, run each via headless claude -p subprocesses, aggregate results into a polished report file.
$ npx skills add feiskyer/claude-code-settings --skill deep-research -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install feiskyer/claude-code-settings deep-research --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/feiskyer/claude-code-settings.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/deep-research .claude/skills/deep-research && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "deep-research" agent skill from https://github.com/feiskyer/claude-code-settings/tree/main/skills/deep-research into .claude/skills/deep-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-research", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/feiskyer/claude-code-settings/tree/main/skills/deep-researchType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add feiskyer/claude-code-settings --skill deep-research -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install feiskyer/claude-code-settings deep-research --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/feiskyer/claude-code-settings.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/deep-research .agents/skills/deep-research && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "deep-research" agent skill from https://github.com/feiskyer/claude-code-settings/tree/main/skills/deep-research into .agents/skills/deep-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-research", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add feiskyer/claude-code-settings --skill deep-research -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install feiskyer/claude-code-settings deep-research --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/feiskyer/claude-code-settings.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/deep-research .cursor/skills/deep-research && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "deep-research" agent skill from https://github.com/feiskyer/claude-code-settings/tree/main/skills/deep-research into .cursor/skills/deep-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-research", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/feiskyer/claude-code-settings.git --path skills/deep-research--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add feiskyer/claude-code-settings --skill deep-research -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install feiskyer/claude-code-settings deep-research --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/feiskyer/claude-code-settings.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/deep-research .gemini/skills/deep-research && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "deep-research" agent skill from https://github.com/feiskyer/claude-code-settings/tree/main/skills/deep-research into .gemini/skills/deep-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-research", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install feiskyer/claude-code-settings deep-researchInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add feiskyer/claude-code-settings --skill deep-research -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/feiskyer/claude-code-settings.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/deep-research .github/skills/deep-research && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "deep-research" agent skill from https://github.com/feiskyer/claude-code-settings/tree/main/skills/deep-research into .github/skills/deep-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-research", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add feiskyer/claude-code-settings --skill deep-research -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install feiskyer/claude-code-settings deep-research --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/feiskyer/claude-code-settings.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/deep-research .opencode/skills/deep-research && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "deep-research" agent skill from https://github.com/feiskyer/claude-code-settings/tree/main/skills/deep-research into .opencode/skills/deep-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-research", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
deep-researchMulti-agent research orchestration: split a research goal into parallel sub-goals, run each via headless claude -p subprocesses, aggregate results into a polished report file.
Deep Research is an agent skill from feiskyer/claude-code-settings. Multi-agent research orchestration: split a research goal into parallel sub-goals, run each via headless claude -p subprocesses, aggregate results into a polished report file. Use for systematic web/document research, competitive or industry analysis, batch link/dataset processing, and long-form evidence synthesis. Triggers: "深度调研", "deep research", "wide research", "多 Agent 调研", "系统调研".
Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Research & Science, covering Deep research. The repository describes itself as: Curated skills, sub-agents, and config templates that supercharge Claude Code — research, image gen, GitHub automation & more. The licence is MIT.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 95dab59. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteEditBashGlobGrepWebFetchWebSearchTodoWritemcp__firecrawl__firecrawl_scrape…and 7 more on the same allowed-tools line.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
claudeFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Deep Research loads about 2.6k tokens when it runs. Until then it costs about 102 tokens; SKILL.md has 421 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Read, Write, Edit, Bash, Glob, Grep, WebFetch, WebSearch, TodoWrite, mcp__firecrawl__firecrawl_scrapAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from feiskyer/claude-code-settings at commit 95dab59, republished under its MIT licence (© feiskyer). 421 words, ~2,647 tokens.
.claude/skills/deep-research/SKILL.md (or your agent's skills folder).把"深度调研"当作一个可复用、可并行的生产流程来执行:主控负责澄清目标、拆解子目标、调度子进程、聚合与精修;子进程负责采集/抽取/局部分析并输出结构化 Markdown 素材;最终交付物必须是独立成品文件而不是聊天贴文。
关键约束(必须遵守)
--allowedTools 控制可用工具;仅在必要时启用网络等权限。firecrawl,其次 exa;确实无法满足时再考虑 WebFetch/WebSearch。claude -p 子进程;<3 个子目标时可由主进程直接执行,但仍需记录完整目录结构和原始数据。claude -p 子进程,并为其分配合适权限(通过 --allowedTools 参数)。.research/<name>/aggregated_raw.md),在成品中仅吸收关键洞察/证据。根据子目标数量选择执行路径:
| 规模 | 子目标数 | 执行方式 | 目录要求 |
|---|---|---|---|
| 微型 | 1-2 | 主进程直接执行 | 仍需 raw/、logs/、final_report.md |
| 小型 | 3-5 | 启动子进程,串行或少量并行 | 完整目录结构 |
| 中型 | 6-15 | 并行子进程(默认 8 并发) | 完整目录结构 + 调度脚本 |
| 大型 | >15 | GNU Parallel + 分批调度 | 完整目录结构 + 多阶段调度 |
注意:即使是微型任务,也必须:
raw/ 目录logs/dispatcher.log预执行规划与摸底(必做;主控亲自完成)
firecrawl,其次 exa;若都不可用,记录原因并选择替代方案(必要时再降级到 WebFetch/WebSearch)。初始化与总体规划
name(建议:<YYYYMMDD>-<短题>-<随机后缀>,全小写、短横线分隔、无空格)。.research/<name>/,并把所有产物都保存到该目录下(子目录如 prompts/、logs/、child_outputs/、raw/、cache/、tmp/)。子目标识别
生成调度脚本
.research/<name>/run_children.sh),要求:claude -p 调用,推荐要点:claude -p "prompt" --allowedTools "Read,Write,Edit,Bash,WebFetch,WebSearch,mcp__firecrawl__*"(以 claude --help 为准)。firecrawl,其次 exa;确实没办法才用 WebFetch/WebSearch;不使用 plan 工具与"人工交互等待"。.research/<name>/child_outputs/<id>.md)。timeout 600 claude -p "$(cat "$prompt_file")" \
--allowedTools "Read,Write,Edit,Bash,Glob,Grep,WebFetch,WebSearch,mcp__firecrawl__firecrawl_scrape,mcp__firecrawl__firecrawl_search" \
--output-format json \
> "$output_file" 2>&1--allowedTools 中追加对应工具名。timeout 300),较大任务可放宽到最多 15 分钟(timeout 900),通过外部 timeout 命令兜底。首次命中 5 分钟超时时,结合任务实际判断是否拆分/改参数再重试;15 分钟仍未完成则视为 prompt 或流程需要排查。xargs/GNU Parallel,但必须先用小规模验证参数展开。默认并行 8 个,可按硬件或配额调整。stdbuf -oL -eL claude -p … 2>&1 | tee .research/<name>/logs/<id>.log 等方式保证实时刷新,便于 tail -f 观察进度。设计子进程 Prompt
firecrawl → exa)→ WebFetch/WebSearch。printf/逐行写入注入变量,避免 Bash 3.2 在多字节字符场景下 cat <<EOF 截断变量的已知问题。.research/<name>/child_prompt_template.md)以便审计与复用。cat .research/<name>/prompts/<id>.md),确认变量替换正确、指令完整后再派发任务。并行执行与监控
tail -f .research/<name>/logs/<id>.log 追踪实时输出。程序化聚合(生成基础稿)
.research/<name>/aggregate.py)读取 .research/<name>/child_outputs/ 下所有 Markdown,按预设顺序聚合为初版主文档(例如 .research/<name>/final_report.md)。解读聚合结果并设计结构
.research/<name>/final_report.md 与关键子输出。.research/<name>/polish_outline.md),明确目标受众、章节顺序与每章核心论点。分章精修与出稿
.research/<name>/polished_report.md),按大纲逐章撰写;每写完一章立刻自查事实、引用与语言要求,必要时回溯子稿核实。落地交付
.research/<name>/);通过提供文件路径与必要摘要向用户回报,禁止在聊天中贴出完整成稿。.research/<name>/,避免覆盖旧文件。.research/<name>/raw/ 等缓存目录,后续处理优先读取本地缓存以减少重复请求。.research/<name>/tmp/、.research/<name>/raw/、.research/<name>/cache/ 等子目录,必要时在流程结束后按需清理。firecrawl,其次 exa;缺少 MCP 时再退回 WebFetch/WebSearch。# 基本非交互调用
claude -p "Your prompt here"
# 指定允许的工具(无需人工确认)
claude -p "Your prompt" --allowedTools "Read,Write,Edit,Bash"
# JSON 格式输出(便于脚本解析)
claude -p "Your prompt" --output-format json
# 流式 JSON 输出
claude -p "Your prompt" --output-format stream-json
# 继续上一次对话
claude -p "Follow up question" --continue
# 继续指定会话
claude -p "Follow up" --resume <session_id>#!/bin/bash
# 子进程调度示例
prompt_file="$1"
output_file="$2"
log_file="$3"
# 读取 prompt 并执行
timeout 600 claude -p "$(cat "$prompt_file")" \
--allowedTools "Read,Write,Edit,Bash,Glob,Grep,WebFetch,WebSearch,mcp__firecrawl__firecrawl_scrape,mcp__firecrawl__firecrawl_search,mcp__firecrawl__firecrawl_map" \
--output-format json \
2>&1 | tee "$log_file" > "$output_file"
exit_code=${PIPESTATUS[0]}
echo "Exit code: $exit_code" >> "$log_file"#!/bin/bash
# 并行执行多个子任务
max_parallel=8
research_dir=".research/$name"
# 使用 GNU Parallel(推荐)
cat "$research_dir/tasks.txt" | parallel -j $max_parallel \
"timeout 600 claude -p \"\$(cat $research_dir/prompts/{}.md)\" \
--allowedTools 'Read,Write,Edit,Bash,WebFetch,WebSearch' \
--output-format json > $research_dir/child_outputs/{}.json 2>&1"
# 或使用后台任务
for task_id in $(cat "$research_dir/task_ids.txt"); do
(
timeout 600 claude -p "$(cat "$research_dir/prompts/$task_id.md")" \
--allowedTools "Read,Write,Edit,Bash,WebFetch,WebSearch" \
--output-format json \
> "$research_dir/child_outputs/$task_id.json" 2>&1
) &
# 控制并行数量
while [ $(jobs -r | wc -l) -ge $max_parallel ]; do
sleep 1
done
done
wait # 等待所有后台任务完成realpath/test -d 等确认关键路径(如 venv、资源目录)存在;必要时用 dirname "$0" 推导仓库根路径并通过参数传入,避免硬编码。.research/<name>/dispatcher.log;子任务单独写 .research/<name>/logs/<id>.log,失败时直接 tail 对应日志定位 MCP/调用细节。failed_ids 列表并在收尾阶段统一提示后续建议。.research/<name>/child_outputs/<id>.md 是否已合法存在;存在则跳过,减少配额消耗与重复访问。[来源](https://example.com)),避免把链接集中到段尾,便于即时查证。追求有深度、有独立判断的洞见:揣摩用户为什么会问这个问题、背后的假设是什么、有没有更本质的问法;同时明确你的答案应满足的成功标准,再围绕标准组织内容。
保持协作:你的目标不是机械执行指令、也不是在信息不足时强行给出确定答案;而是与用户共同推进,逐步逼近更好的问题与更可靠的结论。
写作风格要求:
执行本技能时,在每一步输出清晰的决策与进度日志。
在提交最终报告前,必须核对以下清单:
.research/<name>/ 目录已创建logs/dispatcher.log 包含完整执行记录(非事后补写)raw/ 目录包含原始搜索/抓取结果prompts/、child_outputs/ 目录存在且有内容claude -p 子进程如有以下情况,应在报告中明确说明:
© feiskyer, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/deep-research of feiskyer/claude-code-settings.
Open the folder on GitHubat commit 95dab59
Deep Research next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Deep Research this skillfeiskyer/claude-code-settings | 1.7k | — | ~2.6k | Automated safety check: Notes | MIT | |
| GitHub Deep Researchbytedance/deer-flow | 84k | 4 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Deep Research WorkflowTokenRhythm/opensquilla | 7.1k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Deep Researchsanjay3290/ai-skills | 431 | 9 repos | ~683 | Automated safety check: Notes | Apache-2.0 | |
| Horizontal-Vertical Deep ResearchKKKKhazix/khazix-skills | 21k | — | ~2.1k | Automated safety check: Pass | MIT | |
| Academic Research PipelineImbad0202/academic-research-skills | 51k | — | ~15k | Automated safety check: Pass | Custom licence |
bytedance/deer-flow
Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.
TokenRhythm/opensquilla
Runs multi-round research in three stages with a persisted state file, evidence tracking and a long-form report with per-claim citations.
sanjay3290/ai-skills
Execute autonomous multi-step research using Google Gemini Deep Research Agent.
KKKKhazix/khazix-skills
Runs a two-axis deep research method on a product, company, concept or person: its full history over time, compared with peers today, delivered as a typeset PDF report.
Imbad0202/academic-research-skills
Orchestrates a ten-stage academic workflow from research to finished manuscript, including integrity checks, two rounds of peer review and revision.
Imbad0202/academic-research-skills-codex
A router skill that sends academic work such as literature reviews, drafting, citation checks, peer review and revision to the right workflow in the ARS suite.
feiskyer/claude-code-settings
Create, refine, and benchmark agent skills. An agent skill from feiskyer/claude-code-settings.
feiskyer/claude-code-settings
Explore user intent, requirements, and design options through collaborative dialogue before implementation.
feiskyer/claude-code-settings
Leverage OpenAI Codex/GPT models for autonomous code implementation, code review, and plan review.
feiskyer/claude-code-settings
Fix GitHub issues end-to-end — analysis, branch creation, implementation, testing, and PR submission.
feiskyer/claude-code-settings
Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents.
feiskyer/claude-code-settings
Generate or edit images using OpenAI GPT Image API (gpt-image-2, gpt-image-1, etc).
Categories
Multi-agent research orchestration: split a research goal into parallel sub-goals, run each via headless claude -p subprocesses, aggregate results into a polished report file. Deep Research is an agent skill from feiskyer/claude-code-settings. Multi-agent research orchestration: split a research goal into parallel sub-goals, run each via headless claude -p subprocesses, aggregate results into a polished report file.
Deep Research fits situations like: systematic web/document research; industry analysis; batch link/dataset processing; long-form evidence synthesis.
Run `npx skills add feiskyer/claude-code-settings --skill deep-research -a claude-code`. Or copy the skill folder (skills/deep-research in feiskyer/claude-code-settings) into .claude/skills/deep-research in your project. Claude Code loads it when a task matches its description.
Run `npx skills add feiskyer/claude-code-settings --skill deep-research -a codex`. Or copy the skill folder (skills/deep-research in feiskyer/claude-code-settings) into .agents/skills/deep-research in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add feiskyer/claude-code-settings --skill deep-research -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deep-research, .gemini/skills/deep-research, .github/skills/deep-research and .opencode/skills/deep-research in your project.
Going by SKILL.md and its folder, Deep Research needs the command-line tools its instructions call (claude). Its frontmatter pre-approves these tools: Read, Write, Edit, Bash, Glob, Grep, WebFetch, WebSearch, TodoWrite, mcp__firecrawl__firecrawl_scrape, mcp__firecrawl__firecrawl_search, mcp__firecrawl__firecrawl_map, mcp__firecrawl__firecrawl_crawl, mcp__firecrawl__firecrawl_extract, mcp__firecrawl__firecrawl_agent, mcp__exa__web_search_exa, mcp__exa__web_fetch_exa.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Deep Research is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.6k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Deep Research: GitHub Deep Research (bytedance/deer-flow, 84k stars), Deep Research Workflow (TokenRhythm/opensquilla, 7.1k stars), Deep Research (sanjay3290/ai-skills, 431 stars) and Horizontal-Vertical Deep Research (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
feiskyer (a GitHub user) maintains it in feiskyer/claude-code-settings, which has 1,658 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on September 27, 2026.
Source: feiskyer/claude-code-settings on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.