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.
Research current topics with multiple sources and produce a structured brief, comparison, recommendation, or fact-check.
Install Researcher
$ npx skills add understudy-ai/understudy --skill researcher -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install understudy-ai/understudy researcher --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/understudy-ai/understudy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/researcher .claude/skills/researcher && 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 "researcher" agent skill from https://github.com/understudy-ai/understudy/tree/main/skills/researcher into .claude/skills/researcher/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "researcher", 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/understudy-ai/understudy/tree/main/skills/researcherType 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 understudy-ai/understudy --skill researcher -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install understudy-ai/understudy researcher --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/understudy-ai/understudy.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/researcher .agents/skills/researcher && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "researcher" agent skill from https://github.com/understudy-ai/understudy/tree/main/skills/researcher into .agents/skills/researcher/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "researcher", 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 understudy-ai/understudy --skill researcher -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install understudy-ai/understudy researcher --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/understudy-ai/understudy.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/researcher .cursor/skills/researcher && 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 "researcher" agent skill from https://github.com/understudy-ai/understudy/tree/main/skills/researcher into .cursor/skills/researcher/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "researcher", 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/understudy-ai/understudy.git --path skills/researcher--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 understudy-ai/understudy --skill researcher -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install understudy-ai/understudy researcher --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/understudy-ai/understudy.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/researcher .gemini/skills/researcher && 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 "researcher" agent skill from https://github.com/understudy-ai/understudy/tree/main/skills/researcher into .gemini/skills/researcher/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "researcher", 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 understudy-ai/understudy researcherInstalls 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 understudy-ai/understudy --skill researcher -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/understudy-ai/understudy.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/researcher .github/skills/researcher && 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 "researcher" agent skill from https://github.com/understudy-ai/understudy/tree/main/skills/researcher into .github/skills/researcher/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "researcher", 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 understudy-ai/understudy --skill researcher -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install understudy-ai/understudy researcher --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/understudy-ai/understudy.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/researcher .opencode/skills/researcher && 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 "researcher" agent skill from https://github.com/understudy-ai/understudy/tree/main/skills/researcher into .opencode/skills/researcher/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "researcher", 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
researcher- GitHub stars
- 462
- Token cost
- ~1.2k tokens
- SKILL.md length
- 621 words
- Files
- 1
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- MIT
At a glance
Research current topics with multiple sources and produce a structured brief, comparison, recommendation, or fact-check.
- Works in 6 steps: Frame the question → Make a research plan → Use a bounded search budget → …
- The user asks for investigation
- SKILL.md covers When to use, Working style, Workflow and Output templates, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Researcher is an agent skill from understudy-ai/understudy. Research current topics with multiple sources and produce a structured brief, comparison, recommendation, or fact-check. Use when the user asks for investigation, market/product landscape scans, option evaluation, due diligence, source-backed validation, or a research report. Do not use for summarizing a single provided URL/document, or for GitHub issue/PR operations.
Its SKILL.md is about 1.2k 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 Fact-checking and source verification, Deep research and Fundraising and pitch decks. It works with GitHub. The repository describes itself as: An understudy watches. Then performs. The licence is MIT.
When your agent uses it
- The user asks for investigation
- Market/product landscape scans
- Option evaluation
- Source-backed validation
Example prompts
- “/researcher”
Workflow steps
6 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 820cac1. 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.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Researcher loads about 1.2k tokens when it runs. Until then it costs about 95 tokens; SKILL.md has 621 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 understudy-ai/understudy at commit 820cac1, republished under its MIT licence (© understudy-ai). 621 words, ~1,218 tokens.
Download SKILL.mdSave it as
.claude/skills/researcher/SKILL.md (or your agent's skills folder).- name
- researcher
- description
- Research current topics with multiple sources and produce a structured brief, comparison, recommendation, or fact-check. Use when the user asks for investigation, market/product landscape scans, option evaluation, due diligence, source-backed validation, or a research report. Do not use for summarizing a single provided URL/document, or for GitHub issue/PR operations.
Researcher
Use this skill for bounded, source-backed research.
Default goal: turn an open-ended question into a concise research output with explicit evidence, tradeoffs, and uncertainty.
When to use
Use this skill when the user wants any of:
- a comparison of products, vendors, tools, APIs, papers, or approaches
- a market or ecosystem landscape scan
- due diligence on a company, category, or technical option
- fact-checking or claim validation with citations
- a structured research brief, memo, or recommendation
Do not use this skill for:
- summarizing one URL, one article, one video, or one local file; use the more specific summarize flow instead
- GitHub issue, PR, release, or CI workflows; use the GitHub-specific skills instead
- purely internal codebase exploration with no web research component
Working style
Prefer current sources over memory. Use a small search budget first, then expand only if the evidence is weak or conflicting.
Unless the user already gave a narrow format, produce:
- Research goal
- Short answer or recommendation
- Comparison or findings
- Risks, caveats, and unknowns
- Sources
If the user asks for a persistent artifact, write a Markdown report under research/ with a short kebab-case filename that matches the topic.
Workflow
Follow these phases in order.
1. Frame the question
Before searching, extract or infer:
- the decision to be made
- the comparison axes or success criteria
- any hard constraints such as budget, platform, geography, or timeline
If one missing detail would materially change the answer, ask a short clarifying question. Otherwise proceed with a stated assumption.
2. Make a research plan
Break the work into 3-7 subquestions. Keep them concrete and decision-relevant.
Examples:
- What options belong in scope?
- What are the meaningful differences?
- What evidence is primary vs secondary?
- What risks or hidden costs matter?
3. Use a bounded search budget
Start with a tight first pass:
- 2-4 targeted searches to map the space
- fetch the strongest candidate sources
- expand only if the first pass is incomplete, outdated, or contradictory
Avoid aimless searching. Stop when additional searches are no longer changing the answer.
4. Prefer stronger evidence
When possible, prioritize:
- official product or vendor documentation
- original papers, specs, standards, or release notes
- first-party pricing or policy pages
- reputable primary reporting or direct statements
Use secondary summaries only to discover leads, not as the sole basis for important conclusions.
Show full SKILL.md (239 more words)Show less
5. Compare and validate
For each important claim:
- note which source supports it
- look for disagreement or missing context
- cross-check high-impact claims with at least two independent sources when feasible
Call out any inference you are making from the evidence instead of presenting it as a confirmed fact.
6. Produce a decision-ready output
Keep the final answer structured and useful. Include:
- the answer up front
- a short comparison table or bullets when multiple options are involved
- the strongest evidence and why it matters
- explicit uncertainty, recency limits, and open questions
- source links or source identifiers
Output templates
Comparison / recommendation
Use this shape by default:
- Recommendation
- Why it wins
- Alternatives considered
- Key risks or tradeoffs
- Sources
Fact-check / validation
Use this shape:
- Verdict: supported / mixed / unsupported / unclear
- What the evidence says
- What remains uncertain
- Sources
Landscape scan
Use this shape:
- Category snapshot
- Main players or approaches
- How they differ
- Notable gaps, risks, or trends
- Recommendation or next step
- Sources
Tool guidance
Prefer web_search to discover candidates, web_fetch to read exact page contents, and pdf when a primary source is a PDF.
Use the browser only when a relevant source requires interactive navigation, login, or a page state that the normal web tools cannot reach.
Quality bar
Do not end with a pile of links. Synthesize.
Do not present stale or weakly supported claims as settled.
Do not hide uncertainty. If the evidence is thin, say so clearly and narrow the recommendation.
© understudy-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/researcher of understudy-ai/understudy.
Open the folder on GitHubat commit 820cac1
Compare with similar skills
Researcher 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 |
|---|---|---|---|---|---|---|
| Researcher this skillunderstudy-ai/understudy | 462 | — | ~1.2k | Automated safety check: Pass | MIT | |
| GitHub Deep Researchbytedance/deer-flow | 84k | 4 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Deep Researchsanjay3290/ai-skills | 431 | 9 repos | ~683 | Automated safety check: Notes | Apache-2.0 | |
| Deep Research Agent TeamImbad0202/academic-research-skills | 51k | — | ~13k | Automated safety check: Pass | Custom licence | |
| Workflow PatternsQuintinShaw/pi-dynamic-workflows | 555 | — | ~827 | Automated safety check: Pass | MIT | |
| Rival Search MCPdamionrashford/RivalSearchMCP | 132 | — | ~796 | Automated safety check: Pass | MIT |
Similar skills
Deep Research
sanjay3290/ai-skills
Execute autonomous multi-step research using Google Gemini Deep Research Agent.
Deep Research Agent Team
Imbad0202/academic-research-skills
Runs a 13-agent pipeline for rigorous academic research, from forming the question through systematic search, synthesis, bias checks and an APA 7.0 report.
Workflow Patterns
QuintinShaw/pi-dynamic-workflows
Argument shapes for the 5 built-in workflow patterns — deep-research, adversarial-review, code-review, multi-perspective, codebase-audit — runnable via the workflow tool's name input, without…
Rival Search MCP
damionrashford/RivalSearchMCP
Deterministic deep research via RivalSearchMCP. An agent skill from damionrashford/RivalSearchMCP.
Net Deep Research
h4444433333/net-deep-research
Runs cross-source web research to verify whether an online claim is true, distinguishing confirmed facts from rumor, marketing claims or stale information.
More from understudy-ai/understudy
Discord
understudy-ai/understudy
Discord messaging via messagesend (channel=discord). An agent skill from understudy-ai/understudy.
Xquik
understudy-ai/understudy
Use Xquik REST and MCP APIs for X data workflows: search public posts, inspect users, export datasets, download media, monitor accounts or keywords, and send webhook events.
Healthcheck
understudy-ai/understudy
Host security hardening and risk-tolerance guidance for Understudy deployments.
Related
Works with
Categories
Questions about Researcher
What does Researcher do?
Research current topics with multiple sources and produce a structured brief, comparison, recommendation, or fact-check. Researcher is an agent skill from understudy-ai/understudy. Research current topics with multiple sources and produce a structured brief, comparison, recommendation, or fact-check.
When should I use Researcher?
Researcher fits situations like: the user asks for investigation; market/product landscape scans; option evaluation; source-backed validation.
How do I install Researcher in Claude Code?
Run `npx skills add understudy-ai/understudy --skill researcher -a claude-code`. Or copy the skill folder (skills/researcher in understudy-ai/understudy) into .claude/skills/researcher in your project. Claude Code loads it when a task matches its description.
How do I install Researcher in Codex?
Run `npx skills add understudy-ai/understudy --skill researcher -a codex`. Or copy the skill folder (skills/researcher in understudy-ai/understudy) into .agents/skills/researcher in your project. Codex loads it when a task matches its description.
Can I use Researcher 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 understudy-ai/understudy --skill researcher -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/researcher, .gemini/skills/researcher, .github/skills/researcher and .opencode/skills/researcher in your project.
What does Researcher need to run?
SKILL.md names no scripts, command-line tools or credentials: Researcher is instructions for the agent only.
Does Researcher access the network?
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.
Is Researcher 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 Researcher use?
Researcher is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Researcher use?
About 1.2k tokens (SKILL.md is roughly 4.9k 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 Researcher?
Skills that share tags, products or a category with Researcher: GitHub Deep Research (bytedance/deer-flow, 84k stars), Deep Research (sanjay3290/ai-skills, 431 stars), Deep Research Agent Team (Imbad0202/academic-research-skills, 51k stars) and Workflow Patterns (QuintinShaw/pi-dynamic-workflows, 555 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Researcher?
understudy-ai (a GitHub organization) maintains it in understudy-ai/understudy, which has 462 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on June 19, 2026.
Source: understudy-ai/understudy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.