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.
Conduct multi-round web research on a question and produce a structured, cited report.
Install Deep Research
$ npx skills add rongxinzy/RongxinAI --skill deep-research -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install rongxinzy/RongxinAI 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/rongxinzy/RongxinAI.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/rongxinzy/RongxinAI/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/rongxinzy/RongxinAI/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 rongxinzy/RongxinAI --skill deep-research -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install rongxinzy/RongxinAI deep-research --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.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/rongxinzy/RongxinAI/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 rongxinzy/RongxinAI --skill deep-research -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install rongxinzy/RongxinAI deep-research --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.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/rongxinzy/RongxinAI/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/rongxinzy/RongxinAI.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 rongxinzy/RongxinAI --skill deep-research -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install rongxinzy/RongxinAI deep-research --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.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/rongxinzy/RongxinAI/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 rongxinzy/RongxinAI 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 rongxinzy/RongxinAI --skill deep-research -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.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/rongxinzy/RongxinAI/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 rongxinzy/RongxinAI --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 rongxinzy/RongxinAI deep-research --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.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/rongxinzy/RongxinAI/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.
Facts
- Skill name
deep-research- GitHub stars
- 154
- Token cost
- ~1.8k tokens
- SKILL.md length
- 832 words
- Files
- 3
- Skills in repo
- 94
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Conduct multi-round web research on a question and produce a structured, cited report.
- Works in 5 steps: Clarify the Research Question → Plan Angles, Then Fan Out in Parallel → Cross-Validate the Returns → …
- The user asks for in-depth research
- SKILL.md covers When to Use This Skill, Composition with Retrieval Tools, Delegation Protocol (mandatory) and Quality Bar
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Deep Research is an agent skill from rongxinzy/RongxinAI. Conduct multi-round web research on a question and produce a structured, cited report. Use when the user asks for in-depth research, a deep dive, a landscape/survey of a topic, fact-checked analysis, or a report with sources. Triggers: deep research, 深度调研, 深度研究, research report, 调研报告, investigate, due diligence.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `zhiyuan/metadata.yaml`).
It sits in Research & Science, covering Deep research. The repository describes itself as: An all-in-one local AI Agent workspace with a fully self-developed stack. The licence is Apache-2.0.
When your agent uses it
- The user asks for in-depth research
- A landscape/survey of a topic
- Fact-checked analysis
- A report with sources
Example prompts
- “/deep-research”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 9c64865. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Deep Research loads about 1.8k tokens when it runs. Until then it costs about 82 tokens; SKILL.md has 832 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.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated 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.
SKILL.md
The full file from rongxinzy/RongxinAI at commit 9c64865, republished under its Apache-2.0 licence (© rongxinzy). 832 words, ~1,794 tokens.
Download SKILL.mdSave it as
.claude/skills/deep-research/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- deep-research
- description
- Conduct multi-round web research on a question and produce a structured, cited report. Use when the user asks for in-depth research, a deep dive, a landscape/survey of a topic, fact-checked analysis, or a report with sources. Triggers: deep research, 深度调研, 深度研究, research report, 调研报告, investigate, due diligence.
- license
- Apache-2.0
- metadata.version
- 1.1
- metadata.category
- research
- metadata.sources
- https://github.com/ComposioHQ/awesome-claude-skills/tree/master/content-research-writer
<!-- Adapted from content-research-writer (Apache-2.0), original source: https://github.com/ComposioHQ/awesome-claude-skills/tree/master/content-research-writer. Rewritten as a deep-research workflow: question clarification, parallel subagent fan-out, loop-driven gap filling, cross-source validation, and cited report synthesis. Pure-prompt skill: no scripts, no external dependencies. -->Deep Research
This skill turns a single question into a rigorous, multi-round research process and a structured report with citations. It orchestrates searching, reading, and validation — it does not provide its own search implementation.
When to Use This Skill
- The user asks for in-depth research, a deep dive, or a 深度调研 on a topic
- The question needs current information from multiple sources, not a one-shot answer
- The user wants a report with verifiable citations, not an off-the-cuff summary
- Comparing options, surveying a landscape, or doing due diligence
Do not use this skill for simple fact lookups — a single web search is faster and enough.
Composition with Retrieval Tools
This skill contains no search scripts. Use whatever retrieval tools are available in the current environment, in this order of preference:
- The
web-searchskill (if available) for query-based discovery. - Built-in web search / web fetch tools exposed by the runtime.
- The
browsertool for login-gated or heavily dynamic pages that plain fetching cannot handle.
Never claim to have searched or read a page unless a retrieval tool was actually invoked. If no retrieval tool is available in the current mode, say so plainly and produce the best report you can from prior knowledge, clearly marked as unverified.
Delegation Protocol (mandatory)
Deep research is not a solo 2–3 round search. When the subagent tool is available, you MUST fan the work out and drive it in loops. Stopping after a couple of quick search rounds is a protocol violation.
1. Clarify the Research Question
Pin down what a good answer looks like:
- Core question: restate it in one sentence. If the request is genuinely ambiguous, ask 1–3 targeted clarifying questions; otherwise proceed with a stated interpretation.
- Scope: time range, geography, industry, depth (brief vs. exhaustive survey).
- Deliverable: report length and required sections.
State your interpretation at the top of the work so the user can correct course early.
2. Plan Angles, Then Fan Out in Parallel
Decompose the question into 3–5 meaningfully different angles (definitions/background, current landscape and key players, recent developments, primary data and statistics, contrarian views and limitations). Then launch one researcher subagent per angle in a single subagent parallel call — do not research the angles one by one yourself.
Each delegation task must be self-contained: the angle, the core question for context, the time range, the languages to search in, and the required output — a list of findings where each finding carries a source URL, publisher, date, and a one-line takeaway.
When the controlled Deep Research shortcut is active, persist the 3–5 angles
with workflow_state action plan, and record each source with action
source. Those URLs are fetched by the runtime before they count.
3. Cross-Validate the Returns
When the parallel researchers return:
- Merge their source inventories; deduplicate by URL.
- Require at least two independent sources for any load-bearing claim. Mark single-source claims.
- Prefer primary sources over aggregators; check publication dates on fast-moving topics.
- When sources conflict, report the conflict and the credibility of each side — never silently pick one.
- Read the few most load-bearing pages yourself; do not relay snippet-level claims as verified.
Show full SKILL.md (316 more words)Show less
4. Loop on the Gaps
Draft the report outline and audit it for gaps: unsupported claims, missing sub-questions, contradictions left unresolved. If material gaps remain, start an agent_loop (goal mode, goal = "all load-bearing claims in the outline are supported by 2+ independent sources") and use each iteration to attack the remaining gaps — with fresh subagent delegations where the gap needs new retrieval. Declare done only when the goal holds or the iterations stop changing the picture. Respect the loop's iteration cap; if it trips, deliver the report with the gaps explicitly listed. In the controlled shortcut, done is only a completion request: it remains active until the recorded angles, researcher delegations, and reachable sources clear the runtime gate.
5. Synthesize the Report
Write the report in the user's language. Recommended structure (adapt to the question):
# [研究主题 / Topic]: Research Report
## 摘要 / Executive Summary
[3–5 sentences: the question, the headline findings, the confidence level]
## 背景 / Background
[Context needed to understand the findings]
## 主要发现 / Key Findings
### Finding 1: [title]
[Evidence and analysis, with inline citations like [1], [2]]
### Finding 2: [title]
...
## 争议与分歧 / Disagreements and Open Questions
[Where sources conflict, what remains unknown]
## 结论 / Conclusions
[Direct answer to the research question; caveats and confidence]
## 来源 / Sources
[1] Publisher — "Title" (date). URL
[2] ...Citation rules:
- Every non-obvious factual claim carries an inline
[n]citation. - The source list contains full URLs; each source was actually opened/read, not just seen in a results snippet.
- If a section relies on prior knowledge rather than retrieved sources, label it as such.
Quality Bar
Before delivering, check:
- The research was fanned out to parallel
researchersubagents (or, if the tool is unavailable, the report says so and explains the degraded process) - Material gaps were attacked in
agent_loopiterations, not abandoned after one round - The report answers the question actually asked, in the user's language
- Load-bearing claims have 2+ independent sources or are flagged as single-source
- Every citation maps to a real, retrieved URL
- Conflicts and uncertainty are surfaced, not hidden
- No fabricated quotes, numbers, or links
- In the controlled shortcut, save the completed report as a
.mdfile inside the selected workspace and record it withworkflow_stateroledeliverable. - Save a readable
.md,.txt, or.jsonvalidation report that audits citations, source conflicts, scope, and remaining uncertainty; record it with rolevalidation. Research evidence alone never completes the shortcut.
© rongxinzy, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files in SKILLs/deep-research of rongxinzy/RongxinAI.
- SKILL.md
- zhiyuan/icon.svg
- zhiyuan/metadata.yaml
Open the folder on GitHubat commit 9c64865
Compare with similar skills
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 skillrongxinzy/RongxinAI | 154 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| 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 | 432 | 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 |
Similar skills
Deep Research Workflow
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.
Deep Research
sanjay3290/ai-skills
Execute autonomous multi-step research using Google Gemini Deep Research Agent.
Horizontal-Vertical Deep Research
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.
Academic Research Pipeline
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.
Academic Research Suite for Codex
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.
More from rongxinzy/RongxinAI
All 94 skills in this repoSaaS Metrics Coach
rongxinzy/RongxinAI
SaaS financial health advisor. An agent skill from rongxinzy/RongxinAI.
Churn Prevention
rongxinzy/RongxinAI
Reduce voluntary and involuntary churn through cancel flow design, save offers, exit surveys, and dunning sequences.
Presentation Studio
rongxinzy/RongxinAI
The only skill for creating a new PowerPoint deck. An agent skill from rongxinzy/RongxinAI.
Zhiyuan Expert Manager
rongxinzy/RongxinAI
ZhiYuan Agent expert package lifecycle manager for the pi engine.
Ziwei Doushu
rongxinzy/RongxinAI
Professional Ziwei Doushu consultation skill with an offline calculation engine.
Lark Mail
rongxinzy/RongxinAI
飞书邮箱：Use when user mentions 起草邮件、写邮件、草稿、发送/回复/转发邮件、查阅邮件、看邮件、搜索邮件、邮件文件夹、邮件标签、邮件联系人、监听新邮件、邮件收信规则等；use for mail/email intent only.
Related
Categories
Questions about Deep Research
What does Deep Research do?
Conduct multi-round web research on a question and produce a structured, cited report. Deep Research is an agent skill from rongxinzy/RongxinAI. Conduct multi-round web research on a question and produce a structured, cited report.
When should I use Deep Research?
Deep Research fits situations like: the user asks for in-depth research; A landscape/survey of a topic; fact-checked analysis; A report with sources.
How do I install Deep Research in Claude Code?
Run `npx skills add rongxinzy/RongxinAI --skill deep-research -a claude-code`. Or copy the skill folder (SKILLs/deep-research in rongxinzy/RongxinAI) into .claude/skills/deep-research in your project. Claude Code loads it when a task matches its description.
How do I install Deep Research in Codex?
Run `npx skills add rongxinzy/RongxinAI --skill deep-research -a codex`. Or copy the skill folder (SKILLs/deep-research in rongxinzy/RongxinAI) into .agents/skills/deep-research in your project. Codex loads it when a task matches its description.
Can I use Deep Research in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rongxinzy/RongxinAI --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.
What does Deep Research need to run?
SKILL.md names no scripts, command-line tools or credentials: Deep Research is instructions for the agent only.
Does Deep Research access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Deep Research safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Deep Research use?
Deep Research is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Deep Research use?
About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Deep Research?
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, 432 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.
Who maintains Deep Research?
rongxinzy (a GitHub organization) maintains it in rongxinzy/RongxinAI, which has 154 GitHub stars. The repository holds 94 skills in this directory. The repository was last updated on October 10, 2026.
Source: rongxinzy/RongxinAI on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.