sciverse
Retrieve citation-grade academic literature from Sciverse. Use when an agent needs structured paper metadata search, semantic paper chunk retrieval for RAG, source text expansion around a paper offset, or figure/table image fetching from scientific papers. Prefer this skill for peer-reviewed and preprint literature tasks that require docid/title citations and reproducible retrieval steps.
- Installs
- 499
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://sciverse.space --skill sciverse- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads sciverse automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Sciverse
Use Sciverse for scientific literature retrieval. This skill is agent-neutral:
it works through bundled Node.js scripts and does not require a host-specific
tool protocol. Keep answers grounded in returned doc_id, title, and excerpts.
Choose The Path
- Need setup, environment variables, script invocation rules, or exit codes: read references/runtime.md.
- Need author/year/journal/DOI/field filtering, schema discovery, metadata
search, or author / journal (source) entity search via
collection: read references/search-tools.md. - Need RAG chunks, source text expansion, or paper figures/tables: read references/rag-and-content.md.
- Need a workflow decision tree for combining tools: read references/workflows.md.
Default Workflow
- For ambiguous field names or enum values, call
list_catalogfirst. - For natural-language research questions, start with
semantic_search. - For structured discovery, use
search_papers. - For promising chunks, expand context with
read_content. - For figures or tables referenced by Markdown image placeholders, use
get_resource.
Guardrails
- Do not use Sciverse for general web search, news, or non-scientific content.
- Cite paper-based claims with
doc_idand title. - Prefer exact filters only after checking the catalog when field names are uncertain.
- Run bundled scripts from this skill directory, or use absolute paths to the scripts.
FAQ
What does the sciverse skill do?
Retrieve citation-grade academic literature from Sciverse. Use when an agent needs structured paper metadata search, semantic paper chunk retrieval for RAG, source text expansion around a paper offset, or figure/table image fetching from scientific papers. Prefer this skill for peer-reviewed and preprint literature tasks that require docid/title citations and reproducible retrieval steps.
How do I install sciverse?
Run npx skills add https://sciverse.space --skill sciverse in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/sciverse/ (personal) or .claude/skills/sciverse/ (project).
Which AI agents can use sciverse?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is sciverse safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains sciverse?
It is published by sciverse.space in sciverse.space. It has 499 recorded installs.
Popular education & science skills
teach
mattpocock/skills
Teach the user a new skill or concept, within this workspace.
scaffold-exercises
mattpocock/skills
Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.
paper-context-resolver
lllllllama/rigorpilot-skills
Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing README guidance by default.
caveman-learn
juliusbrussee/caveman
Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's token cost, what caveman has saved, to trim a heavy CLAUDE.md, or to offload re-pasted context into cavemem.
gsap-plugins
greensock/gsap-skills
Official GSAP skill for GSAP plugins — registration, ScrollToPlugin, ScrollSmoother, Flip, Draggable, Inertia, Observer, SplitText, ScrambleText, SVG and physics plugins, CustomEase, EasePack, CustomWiggle, CustomBounce, GSDevTools. Use when the user asks about a GSAP plugin, scroll-to, flip animations, draggable, SVG drawing, or plugin registration.
teach-impeccable
pbakaus/impeccable
DEPRECATED: Use /impeccable teach instead. This command has been folded into the impeccable skill.