Exploratory Data Analysis
spacering-net/codeg
Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats.
A skill your agent uses to orchestrate a multi-domain research team for literature/evidence research and data analysis.
Install Science Research Team
$ npx skills add openJiuwen-ai/sciencediscovery --skill science-research-team -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install openJiuwen-ai/sciencediscovery science-research-team --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/openJiuwen-ai/sciencediscovery.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/science-research-team .claude/skills/science-research-team && 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 "science-research-team" agent skill from https://github.com/openJiuwen-ai/sciencediscovery/tree/main/skills/science-research-team into .claude/skills/science-research-team/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "science-research-team", 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/openJiuwen-ai/sciencediscovery/tree/main/skills/science-research-teamType 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 openJiuwen-ai/sciencediscovery --skill science-research-team -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install openJiuwen-ai/sciencediscovery science-research-team --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openJiuwen-ai/sciencediscovery.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/science-research-team .agents/skills/science-research-team && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "science-research-team" agent skill from https://github.com/openJiuwen-ai/sciencediscovery/tree/main/skills/science-research-team into .agents/skills/science-research-team/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "science-research-team", 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 openJiuwen-ai/sciencediscovery --skill science-research-team -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install openJiuwen-ai/sciencediscovery science-research-team --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openJiuwen-ai/sciencediscovery.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/science-research-team .cursor/skills/science-research-team && 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 "science-research-team" agent skill from https://github.com/openJiuwen-ai/sciencediscovery/tree/main/skills/science-research-team into .cursor/skills/science-research-team/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "science-research-team", 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/openJiuwen-ai/sciencediscovery.git --path skills/science-research-team--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 openJiuwen-ai/sciencediscovery --skill science-research-team -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install openJiuwen-ai/sciencediscovery science-research-team --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openJiuwen-ai/sciencediscovery.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/science-research-team .gemini/skills/science-research-team && 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 "science-research-team" agent skill from https://github.com/openJiuwen-ai/sciencediscovery/tree/main/skills/science-research-team into .gemini/skills/science-research-team/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "science-research-team", 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 openJiuwen-ai/sciencediscovery science-research-teamInstalls 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 openJiuwen-ai/sciencediscovery --skill science-research-team -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/openJiuwen-ai/sciencediscovery.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/science-research-team .github/skills/science-research-team && 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 "science-research-team" agent skill from https://github.com/openJiuwen-ai/sciencediscovery/tree/main/skills/science-research-team into .github/skills/science-research-team/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "science-research-team", 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 openJiuwen-ai/sciencediscovery --skill science-research-team -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install openJiuwen-ai/sciencediscovery science-research-team --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openJiuwen-ai/sciencediscovery.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/science-research-team .opencode/skills/science-research-team && 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 "science-research-team" agent skill from https://github.com/openJiuwen-ai/sciencediscovery/tree/main/skills/science-research-team into .opencode/skills/science-research-team/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "science-research-team", 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
science-research-team- GitHub stars
- 162
- Token cost
- ~1.3k tokens
- SKILL.md length
- 600 words
- Files
- 3 (incl. references)
- Skills in repo
- 23
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
A skill your agent uses to orchestrate a multi-domain research team for literature/evidence research and data analysis.
- Works in 3 steps: User-centric — remember the user's… → Workflow adherence — follow the… → Domain separation — each sub-agent stays…
- Orchestrate a multi-domain research team for literature/evidence research and data analysis
- SKILL.md covers Overview, When to Use This Skill, Core Principle and Python Package Installation, plus 4 more sections
- Calls pip; reaches pypi.tuna.tsinghua.edu.cn
What it does
Science Research Team is an agent skill from openJiuwen-ai/sciencediscovery. Use this skill to orchestrate a multi-domain research team for literature/evidence research and data analysis. Dispatches the right domain(s) based on the user's request, runs each domain to completion with its own loop, then synthesizes into reports. Load when the user needs rigorous research with knowledge or data analysis.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/analysis-principles.md` and `references/workflow.md`).
It sits in Data & Analytics, covering Data analysis. The repository describes itself as: ScienceDiscovery is an all‑in‑one agentic workbench built specifically for scientific research. The licence is Apache-2.0.
When your agent uses it
- Orchestrate a multi-domain research team for literature/evidence research and data analysis
- Needs rigorous research with knowledge
Example prompts
- “/science-research-team”
Requirements
- Python 3
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- User-centric — remember the user's requirements and execute tasks centered on them. Do NOT add scope, change the assignment, or substitute…
- Workflow adherence — follow the specified workflow. Do NOT plan independently, re-design the topology, or skip steps.
- Domain separation — each sub-agent stays in its lane. Knowledge sub-agents do NOT run code analysis; code-engineer does NOT do literature…
What it can do on your machine
Read from SKILL.md and the folder at commit cc95884. 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
Shell commands in SKILL.md call:
pip
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
pypi.tuna.tsinghua.edu.cn
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
Science Research Team loads about 1.3k tokens when it runs, and up to ~6.2k if it reads all its reference files. Until then it costs about 87 tokens; SKILL.md has 600 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 openJiuwen-ai/sciencediscovery at commit cc95884, republished under its Apache-2.0 licence (© openJiuwen-ai). 600 words, ~1,259 tokens.
Download SKILL.mdSave it as
.claude/skills/science-research-team/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- science-research-team
- description
- Use this skill to orchestrate a multi-domain research team for literature/evidence research and data analysis. Dispatches the right domain(s) based on the user's request, runs each domain to completion with its own loop, then synthesizes into reports. Load when the user needs rigorous research with knowledge or data analysis.
Science Research Team Skill
Overview
A research-and-analysis orchestrator: takes a research question, runs the right combination of literature search, evidence extraction, code-based analysis, and report synthesis, then delivers reports. The skill handles sub-task decomposition, sub-agent dispatch, iteration with revision, file persistence, and reports assembly end-to-end — the user provide the research question, the skill runs the workflow.
When to Use This Skill
Use this skill when:
- The user asks a research question that benefits from rigorous literature / evidence work — knowledge domain activated.
- The user asks for data analysis, statistical testing, modeling, or visualization — data domain activated.
- The user wants both knowledge and data combined, with the knowledge findings informing the analysis — both domains activated, knowledge runs first.
Do NOT use this skill for:
- Pure single-turn Q&A, planning, or reasoning that doesn't need execution or evidence gathering.
- Tasks where the user just wants raw code run with no verification
Core Principle
Three principles govern the team:
- User-centric — remember the user's requirements and execute tasks centered on them. Do NOT add scope, change the assignment, or substitute your own preferences for what the user asked.
- Workflow adherence — follow the specified workflow. Do NOT plan independently, re-design the topology, or skip steps.
- Domain separation — each sub-agent stays in its lane. Knowledge sub-agents do NOT run code analysis; code-engineer does NOT do literature search; report-writer does NOT re-run analysis.
Python Package Installation
If you need to install new Python packages, install them through the Tsinghua PyPI mirror for reliability:
pip install [python package] -i https://pypi.tuna.tsinghua.edu.cn/simpleMethodology
The team runs in 5 high-level steps. You MUST read references/workflow.md in full before executing any step — it owns each step's detailed execution flow, input formats, validation rules, and iteration rules, and the overview below is not a substitute.
- Coarse-grained intent parsing — identify active domains (knowledge, data, report), capture scope constraints, and verify sub-agents + skills are present (pause and ask the user for any missing). Knowledge runs first when both data and knowledge are activated.
- Knowledge domain (if activated) — you plan sub-tasks → dispatches
literature-searcher/evidence-extractor→ integrates outputs and applies the schema + content rules as integration principles in one step. - Data domain (if activated) — you dispatches
code-engineer↔result-evaluatoriteration loop withmax_engineer_evaluator_iterationscap. Revision guidance flows verbatim between rounds. - Report writing — you dispatch
report-writerwith Domain Summaries;report-writerproduces the user's required outputs (or default outputs if none specified). You do NOT write the report. - Final delivery — deliver whatever the report-writer produced, with execution summaries.
Show full SKILL.md (193 more words)Show less
Quality Bar
The team run is sound when:
- Coarse intent parsing correctly identified which domains to activate and in what order.
- Data iteration stopped at
ACCEPT_AND_PROCEEDormax_engineer_evaluator_iterations, whichever came first. - Analysis Summary carried no fabricated data, no off-scope analysis, no self-evaluation by code-engineer.
- Report: every finding traces to its source role; no new claims introduced; contradictions surfaced verbatim.
- No new scope was injected by you across iterations; only revision guidance changed between data rounds.
- report-writer did NOT re-run analysis, did NOT add claims, did NOT resolve contradictions on its own.
- You never wrote code, evaluated results, or produced user-required outputs — all were delegated to the respective sub-agents / report-writer.
Common Mistakes to Avoid
- ❌ Activating both knowledge and data when the user only needs one.
- ❌ Running knowledge and data in parallel — knowledge must complete first when used as feed-forward.
- ❌ Paraphrasing or summarizing revision guidance between data rounds.
- ❌ Raising
max_engineer_evaluator_iterationsmid-loop to keep iterating past the cap. - ❌ Modifying evaluation criteria between data rounds.
Output
You deliver whatever the report-writer produced to the user, with:
- Which domains ran and which round finalized each
- Any unresolved issues
- The iteration trail (
accepted/ iteration cap / format error / kick-back retry)
© openJiuwen-ai, 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 (references) in skills/science-research-team of openJiuwen-ai/sciencediscovery.
- SKILL.md
- references/analysis-principles.md
- references/workflow.md
Open the folder on GitHubat commit cc95884
Compare with similar skills
Science Research Team 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 |
|---|---|---|---|---|---|---|
| Science Research Team this skillopenJiuwen-ai/sciencediscovery | 162 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Exploratory Data Analysisspacering-net/codeg | 3.9k | 14 repos | ~3.6k | Automated safety check: Pass | MIT | |
| Excel and CSV Data Analysisbytedance/deer-flow | 84k | 4 repos | ~2.2k | Automated safety check: Pass | MIT | |
| Exploratory Data AnalysisOleafly/Oleafly | 212 | 2 repos | ~3.4k | Automated safety check: Notes | MIT | |
| Pandas ProJeffallan/claude-skills | 12k | 1 repos | ~1.5k | Automated safety check: Pass | MIT | |
| Python Executorcortega26/chile-hub | 113 | 2 repos | ~1.5k | Automated safety check: Pass | MIT |
Similar skills
Excel and CSV Data Analysis
bytedance/deer-flow
Analyzes uploaded Excel and CSV files with SQL through DuckDB, producing schema inspections, statistical summaries and exports to CSV, JSON or Markdown.
Exploratory Data Analysis
Oleafly/Oleafly
Perform bounded, local exploratory analysis of explicitly supported scientific files.
Pandas Pro
Jeffallan/claude-skills
Handles pandas DataFrame work: cleaning, merging, groupby aggregation, pivots, time-series resampling and memory tuning, with checks on dtypes, shapes and nulls.
Python Executor
cortega26/chile-hub
Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh).
Agentic Kaggle Workflow
FrankS-IntelLab/agentic-kaggle-skill
Takes a Kaggle competition from rules and validation design through baselines, ensembling and notebook architecture to a scored submission.
More from openJiuwen-ai/sciencediscovery
All 23 skills in this repoCode Engineer
openJiuwen-ai/sciencediscovery
A skill your agent uses when you need to write and execute Python/R code to process, transform, and analyze data, delivering reproducible computational results with complete code-level methodology…
Gitcode
openJiuwen-ai/sciencediscovery
Operate GitCode issues, PRs, wikis, code/MR refs, and cached org templates.
Structure Pocket Inspection
openJiuwen-ai/sciencediscovery
Inspect a local PDB structure, summarize chains and residue composition, and identify protein atoms near a user-specified ligand or pocket center.
Antibody Design
openJiuwen-ai/sciencediscovery
Prepare, launch, monitor, and summarize the real RFdiffusion to ProteinMPNN to Protenix antibody pipeline on a local or remote ScienceDiscovery Runner with sandboxed Ascend NPUs.
Literature Searcher
openJiuwen-ai/sciencediscovery
A skill your agent uses when a research workflow needs verified academic source retrieval through literature-search MCP interfaces available in the current session before evidence extraction.
Create GitHub PR
openJiuwen-ai/sciencediscovery
Open or update a pull request on GitHub's openJiuwen-ai/sciencediscovery: run the UT/ST/E2E layers locally, push the branch to the operator's own GitHub fork, write a body that says what was…
Related
Categories
Questions about Science Research Team
What does Science Research Team do?
A skill your agent uses to orchestrate a multi-domain research team for literature/evidence research and data analysis. Science Research Team is an agent skill from openJiuwen-ai/sciencediscovery. Use this skill to orchestrate a multi-domain research team for literature/evidence research and data analysis.
When should I use Science Research Team?
Science Research Team fits situations like: orchestrate a multi-domain research team for literature/evidence research and data analysis; needs rigorous research with knowledge.
How do I install Science Research Team in Claude Code?
Run `npx skills add openJiuwen-ai/sciencediscovery --skill science-research-team -a claude-code`. Or copy the skill folder (skills/science-research-team in openJiuwen-ai/sciencediscovery) into .claude/skills/science-research-team in your project. Claude Code loads it when a task matches its description.
How do I install Science Research Team in Codex?
Run `npx skills add openJiuwen-ai/sciencediscovery --skill science-research-team -a codex`. Or copy the skill folder (skills/science-research-team in openJiuwen-ai/sciencediscovery) into .agents/skills/science-research-team in your project. Codex loads it when a task matches its description.
Can I use Science Research Team 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 openJiuwen-ai/sciencediscovery --skill science-research-team -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/science-research-team, .gemini/skills/science-research-team, .github/skills/science-research-team and .opencode/skills/science-research-team in your project.
What does Science Research Team need to run?
Going by SKILL.md and its folder, Science Research Team needs the command-line tools its instructions call (pip). Our summary lists: Python 3.
Does Science Research Team access the network?
SKILL.md names 1 domain. In commands or code: pypi.tuna.tsinghua.edu.cn; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Science Research Team 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 Science Research Team use?
Science Research Team is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Science Research Team use?
About 1.3k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5k tokens, read only when the agent opens those files.
What are the alternatives to Science Research Team?
Skills that share tags, products or a category with Science Research Team: Exploratory Data Analysis (spacering-net/codeg, 3.9k stars), Excel and CSV Data Analysis (bytedance/deer-flow, 84k stars), Exploratory Data Analysis (Oleafly/Oleafly, 212 stars) and Pandas Pro (Jeffallan/claude-skills, 12k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Science Research Team?
openJiuwen-ai (a GitHub organization) maintains it in openJiuwen-ai/sciencediscovery, which has 162 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 11, 2026.
Source: openJiuwen-ai/sciencediscovery on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.