AI-assisted computational research with license-aware MCP-first Wolfram execution, wiki knowledge base, LaTeX/Typst paper scaffolding, Wolfram paclet development and publishing, notebook generation, guided tours, Wolfram ecosystem search, pure-math project scaffolding with MathWorld/nLab/OEIS/DLMF/Wikipedia search, BibTeX from arXiv/DOI, Lean/Mathlib formalization bridge, multi-session work tracking (spec/tasks/progress), Conventional-Commits enforcement via scaffolded git hooks, optional prompt-provenance tracking for generated artifacts, an optional cited scientific journal (def/thm/rem) in LaTeX/Typst, a per-project one-sentence-per-line source-formatting toggle, and revision workflow.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Add a resource (paper, repo, notebook, tool, web page) to the wiki using the `add-resource` skill.
Build a Wolfram paclet archive and install locally using the `build-paclet` skill.
Run `${CLAUDE_PLUGIN_ROOT}/scripts/check-env.sh` using the Bash tool and display the full output.
Run a wiki health check using the `check-wiki` skill.
Produce a BibTeX entry from an arXiv ID or DOI using the `cite` skill.
Search external mathematics resources for a topic: MathWorld, nLab, OEIS, DLMF, and Wikipedia math articles. Returns ranked results, optionally hands them to add-resource. Use when the user says "search math", "find on MathWorld", "look up in nLab", "OEIS sequence", "DLMF formula", "search Wikipedia math", or during math-research project setup when external math sources are needed.
Search Wolfram ecosystem resources for a topic: documentation, Function Repository, Community forum, Stephen Wolfram's writings, and the Wolfram Physics Technical Introduction. Downloads notebooks, creates wiki articles, and logs findings. Use when the user says "search wolfram", "find wolfram resources", "wolfram community search", "what functions exist for X", "check the function repository", or during project setup when the user wants Wolfram-specific resource gathering.
Start, resume, or manage a guided tour of the project. Creates an interactive walkthrough with narrative and runnable code for each topic. Use when the user says "start tour", "give me a tour", "continue tour", "where were we", "tour status", or when presenting the project to someone.
Update the wiki after a substantial change. Creates or updates articles, maintains the index, status, log, and backlinks. Use after any significant step — code changes, new functionality, completed tasks, discoveries. Triggers on: "update wiki", "log this", or automatically after substantial work. Also invoke proactively after completing any multi-step task.
Create and manage work items in the top-level Work/ folder — each a multi-session effort with a Spec (what to build), a Tasks checklist (one task ≈ one session), and a Progress log. This is the project's execution state, separate from the Wiki knowledge base. Use for: "new work item", "start a work item", "spec out X", "plan for X", "break X into tasks", "track this across sessions", "add a task", "update the spec", or the /work command. Creates Work/Backlog/<Name>.md, bootstrapping the folder if missing. A work item's status is its folder (Active/Backlog/Done/Dropped), not a field. Specs follow the revise protocol. Do NOT trigger on casual uses of the word "work".
Matches all tools
Hooks run on every tool call, not just specific ones
A Wolfram-centric Claude plugin for AI-assisted computational research.
⚠️ Disclaimer. This repo grows on the fly out of my own thoughts and needs around AI assistance in computational research. It is a working draft, in need of human revision and selective improvement. Helpers and testers welcome!
The plugin is distributed through the WolframInstitute plugin marketplace.
Claude Code (CLI / VS Code extension) — the author's setup:
claude plugin marketplace add WolframInstitute/ClaudePluginMarketplace
claude plugin install computational-research@WolframInstitute
Claude Desktop app — install from the marketplace GUI.
Note: Operation in Cowork mode and Chat mode has not been tested.
The plugin works best with Wolfram Engine (or Mathematica).
MCP servers — the plugin draws on these:
| Server | Required | Purpose | Source |
|---|---|---|---|
| Wolfram (official) | yes | Evaluation, notebook I/O, docs search, tests | Wolfram/AgentTools |
| arxiv-latex-mcp | recommended | Download LaTeX source of arXiv papers | takashiishida/arxiv-latex-mcp |
| arxiv | recommended | Search and download arXiv papers | blazickjp/arxiv-mcp-server |
| wolfram (unofficial) | optional | Additionally supports Wolfram Language LSP, similar to Serena | sw1sh/WolframMCP |
Installing the official Wolfram server:
InstallMCPServer["ClaudeCode", "WolframLanguage"]
Note: On older Wolfram versions, the legacy Wolfram/MCPServer paclet still works as a fallback if that is what you have installed.
🔑 License seats. Each running kernel — every Wolfram MCP server, every open front-end, every
wolframscriptcall — consumes one of your license's$MaxLicenseProcessesseats. The plugin is MCP-first: it routes Wolfram work through the official server's single persistent kernel and treats the.wlsscripts as a fallback for when no MCP is attached (e.g. headless runs). Before spawningwolframscriptit checks headroom and warns rather than failing opaquely. Running both Wolfram MCP servers at once uses two seats —/check-envreports live headroom and flags this.
Skills share their name with the matching slash command (one name per feature), grouped by domain.
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 claimnpx claudepluginhub wolframinstitute/claudepluginmarketplace --plugin computational-researchResearch-team agents for Claude Code: supervisor, analysis-implementer, paper-writer, figure-descriptor, reviewer, literature-curator.
Academic research agents — hypothesis generation, experiment design, paper drafting, peer review simulation, and more.
Semi-automated research assistant for academic research and software development, with skills for literature review, experiments, analysis, writing, and project knowledge management
Oh My Paper research harness: memory system, Codex delegation, and pipeline commands for academic research projects.
LLM-maintained knowledge base skill — structured wiki with Obsidian, milestone-based source clustering, proactive write-back, and autonomous lint
LLM-compiled knowledge base. Topic-isolated wikis, parallel multi-agent research (topic + question auto-detect), thesis-driven investigation with verdicts, repo assessment, Obsidian dual-linking, retardmax mode, and --min-time sustained research.