By KRLabsOrg
Search and ask specialized document collections (ACL Anthology and more) — get verbatim cited answers via the Verbatim platform.
Search and query specialized document collections with verbatim, cited answers. Defaults to the **ACL Anthology** collection (90,000+ papers). Also includes a general-purpose **Verbatim Transform** that turns any question + context into a cited, verbatim answer.
Turn any question + context documents into a verbatim answer with exact citations. Collection-agnostic — works with any text you supply.
A Claude Code plugin for the Verbatim platform — specialized document collections with verbatim, citation-grounded answers. Defaults to the ACL Anthology collection (90,000+ NLP/CL papers).
Also includes a general-purpose Verbatim Transform — give it any question + context documents and get a verbatim, cited answer
First add the marketplace:
claude plugin marketplace add https://github.com/KRLabsOrg/verbatim-skill
Then install:
claude plugin install verbatim
Or test locally without installing:
claude --plugin-dir /path/to/verbatim-skill
export VERBATIM_API_KEY=vb_your_key_here
| Command | Description |
|---|---|
/verbatim:search | Search collection papers, ask research questions, browse authors/venues |
/verbatim:transform | Verbatim transform any question + context into a cited answer |
Collection search & research questions:
/verbatim:search papers about transformer efficiency from 2023/verbatim:search what does the research say about attention mechanisms?Verbatim Transform (collection-agnostic):
/verbatim:transform what are the main findings? (with context provided)Or just ask Claude naturally — it will use the API endpoints from the skill.
Verbatim is organized into collections. The launch collection is the ACL Anthology; more collections may be added. Every action endpoint accepts an optional collection_ids parameter:
["anthology"]?collection_ids=anthology (GET) or {"collection_ids": ["anthology"]} (POST)?collection_ids=anthology&collection_ids=biorxiv or {"collection_ids": ["anthology", "biorxiv"]}| Action | Endpoint | Quota |
|---|---|---|
| List collections | GET /api/v1/collections | Free |
| Verbatim Transform (any context) | POST /api/v1/transform/verbatim | Counts |
| Ask a research question (RAG) | POST /api/v1/query | Counts |
| Search papers | GET /api/v1/papers/search | Free |
| Get paper metadata | GET /api/v1/papers/{id} | Free |
| Get full paper content | GET /api/v1/papers/{id}/content | Free |
| Get BibTeX citation | GET /api/v1/papers/{id}/bibtex | Free |
| Browse authors/venues/years | GET /api/v1/facets | Free |
Apache 2.0
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub krlabsorg/verbatim-skill --plugin verbatimAnnotated research paper collection management — retrieve, read, extract, cross-reference scientific papers
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 three Sciverse tools (search_papers, semantic_search, read_content) via the sciverse-mcp-server MCP server.
Specialized research analysis agents for critical thinking, evidence verification, synthesis, and parallel paper analysis
A research infrastructure for AI agents. Search, read, and analyze papers from your local knowledge base while coding. Includes arXiv discovery, layered reading, ingestion, topic modeling, citation graphs, insights analytics, Office document inspection, scientific tool docs, and academic writing workflows. Requires Python 3.10+ and pip install.
Production-grade academic research pipeline for Claude Code: research → write → review → revise → finalize. 4 skills, 27 modes, 39-agent ensemble, v3.7.3 + v3.8 L3 claim-faithfulness gate, v3.9.0 cross-index triangulation, v3.10 triangulation policy layer, v3.11 deterministic citation verification gate (#182).
A plugin for studying research papers with automated material generation and code demos