A skill your agent uses when the user needs academic paper retrieval — searching scientific literature by author/year/journal, finding paper chunks for RAG-style citations, or expanding original…

Custom licenceAuto-check passedAI & LLM Engineering

Install Sciverse

skills CLI
$ npx skills add opendatalab/Sciverse-Agent-Tools --skill sciverse -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install opendatalab/Sciverse-Agent-Tools sciverse --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/opendatalab/Sciverse-Agent-Tools.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skill-claude-code .claude/skills/sciverse && rm -rf skills-src

Use ~/.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/

Facts

Skill name
sciverse
GitHub stars
119
Token cost
~3k tokens
SKILL.md length
1,161 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
Custom licence

At a glance

A skill your agent uses when the user needs academic paper retrieval — searching scientific literature by author/year/journal, finding paper chunks for RAG-style citations, or expanding original…

  • Works in 2 steps: Install the MCP server → Obtain an API token from…
  • The user needs academic paper retrieval — searching scientific literature by author/year/journal
  • SKILL.md covers When to use, Prerequisites, Tools and Bootstrap: learn the schema…, plus 2 more sections
  • Calls npm; reaches orcid.org; needs SCIVERSE_API_TOKEN

What it does

Sciverse is an agent skill from opendatalab/Sciverse-Agent-Tools. Use when the user needs academic paper retrieval — searching scientific literature by author/year/journal, finding paper chunks for RAG-style citations, or expanding original text around a known paper offset. Provides six Sciverse tools (searchpapers, semanticsearch, listcatalog, listpaperrelations, readcontent, getresource) via the sciverse-mcp-server MCP server.

Its SKILL.md is about 3k 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 AI & LLM Engineering, covering Citation management, Retrieval-augmented generation and MCP servers. It works with Model Context Protocol. The repository describes itself as: Standardized tool schemas and SDKs that expose Sciverse Open Platform retrieval capabilities to LLM agents.

When your agent uses it

  • The user needs academic paper retrieval — searching scientific literature by author/year/journal
  • Finding paper chunks for RAG-style citations
  • Expanding original text around a known paper offset

Example prompts

  • “/sciverse”

Requirements

  • Python 3
  • Node.js
  • A credential in SCIVERSE_API_TOKEN

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. Install the MCP server
  2. Obtain an API token from https://sciverse.space and export it

What it can do on your machine

Read from SKILL.md and the folder at commit 5246a81. 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:

    • npm

    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:

    • orcid.org

    Also links to:

    • sciverse.space

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • SCIVERSE_API_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sciverse loads about 3k tokens when it runs. Until then it costs about 96 tokens; SKILL.md has 1,161 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~96
When it runs · the whole SKILL.md, loaded when a task matches
~3k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,161 words (~3,049 tokens).

“Retrieval skill for the Sciverse open platform. Exposes six tools for working with scientific literature: field introspection, structured metadata search, semantic chunk retrieval for RAG, citation / reference pagination, character-range content reading, and figure / table image fetching.”

— opening of SKILL.md by opendatalab, Custom licence
name
sciverse

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skill-claude-code of opendatalab/Sciverse-Agent-Tools.

Open the folder on GitHubat commit 5246a81

Compare with similar skills

Sciverse 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.

Sciverse compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sciverse this skillopendatalab/Sciverse-Agent-Tools119—~3kAutomated safety check: PassCustom licence
Tw Legal RAGaa0101181514/tw-legal-rag327—~580Automated safety check: PassCustom licence
AutoRAG Setup and RepairMarker-Inc-Korea/AutoRAG5.1k—~5.3kAutomated safety check: PassMIT
Local RAG Searchnkapila6/mcp-local-rag1341 repos~1.6kAutomated safety check: PassMIT
Neurolink Guidejuspay/neurolink143—~1.4kAutomated safety check: PassMIT
RAG Cite Sourceslyonzin/knowledge-rag290—~1.4kAutomated safety check: PassMIT

Similar skills

  • Tw Legal RAG

    aa0101181514/tw-legal-rag

    Retrieve real Taiwan court judgments with verifiable citations before answering any question about Taiwan law or case law.

    327 GitHub stars~580 tokensUpdated 3 days ago
    Legal & ComplianceAuto-check passed
  • AutoRAG Setup and Repair

    Marker-Inc-Korea/AutoRAG

    Installs, configures, and repairs AutoRAG's search model, approved folders, indexes, and datasources, and registers its Lite MCP server.

    5.1k GitHub stars~5.3k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Local RAG Search

    nkapila6/mcp-local-rag

    Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking.

    134 GitHub starsUsed in 1 repo~1.6k tokens
    AI & LLM EngineeringAuto-check passed
  • Neurolink Guide

    juspay/neurolink

    Guide for using the NeuroLink SDK and CLI. An agent skill from juspay/neurolink.

    143 GitHub stars~1.4k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • RAG Cite Sources

    lyonzin/knowledge-rag

    Every technical claim drawn from the local corpus must ship with a source citation formatted as path:line or path:section.

    290 GitHub stars~1.4k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed
  • Setup Medsci

    Aperivue/medsci-skills

    A skill your agent uses when a skill fails for a missing tool or the environment needs checking.

    329 GitHub stars~960 tokensUpdated 2 days ago
    Research & ScienceAuto-check passed

More from opendatalab/Sciverse-Agent-Tools

  • Sciverse Academic Retrieval

    opendatalab/Sciverse-Agent-Tools

    Sciverse academic paper retrieval: structured metadata search, semantic chunk retrieval for RAG, and character-range content reading (offsets in Unicode code points).

    119 GitHub stars~2.3k tokensUpdated 18 days ago
    Auto-check passed

Questions about Sciverse

What does Sciverse do?

A skill your agent uses when the user needs academic paper retrieval — searching scientific literature by author/year/journal, finding paper chunks for RAG-style citations, or expanding original…. Sciverse is an agent skill from opendatalab/Sciverse-Agent-Tools. Use when the user needs academic paper retrieval — searching scientific literature by author/year/journal, finding paper chunks for RAG-style citations, or expanding original text around a known paper offset.

When should I use Sciverse?

Sciverse fits situations like: the user needs academic paper retrieval — searching scientific literature by author/year/journal; finding paper chunks for RAG-style citations; expanding original text around a known paper offset.

How do I install Sciverse in Claude Code?

Run `npx skills add opendatalab/Sciverse-Agent-Tools --skill sciverse -a claude-code`. Or copy the skill folder (skill-claude-code in opendatalab/Sciverse-Agent-Tools) into .claude/skills/sciverse in your project. Claude Code loads it when a task matches its description.

How do I install Sciverse in Codex?

Run `npx skills add opendatalab/Sciverse-Agent-Tools --skill sciverse -a codex`. Or copy the skill folder (skill-claude-code in opendatalab/Sciverse-Agent-Tools) into .agents/skills/sciverse in your project. Codex loads it when a task matches its description.

Can I use Sciverse 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 opendatalab/Sciverse-Agent-Tools --skill sciverse -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sciverse, .gemini/skills/sciverse, .github/skills/sciverse and .opencode/skills/sciverse in your project.

What does Sciverse need to run?

Going by SKILL.md and its folder, Sciverse needs the command-line tools its instructions call (npm) and credentials named SCIVERSE_API_TOKEN. Our summary lists: Python 3; Node.js; A credential in SCIVERSE_API_TOKEN.

Does Sciverse access the network?

SKILL.md names 2 domains. In commands or code: orcid.org; the agent is likely to contact it when it follows the instructions. As links in the text: sciverse.space. This is read from the text; nothing was executed.

Is Sciverse 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 Sciverse use?

Sciverse has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Sciverse use?

About 3k tokens (SKILL.md is roughly 12k 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 Sciverse?

Skills that share tags, products or a category with Sciverse: Tw Legal RAG (aa0101181514/tw-legal-rag, 327 stars), AutoRAG Setup and Repair (Marker-Inc-Korea/AutoRAG, 5.1k stars), Local RAG Search (nkapila6/mcp-local-rag, 134 stars) and Neurolink Guide (juspay/neurolink, 143 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sciverse?

opendatalab (a GitHub organization) maintains it in opendatalab/Sciverse-Agent-Tools, which has 119 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 20, 2026.

Source: opendatalab/Sciverse-Agent-Tools on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.