mims-harvard avatar

Tooluniverse Literature Deep Research

This is a systematic literature review engine that disambiguates your query before searching, then pulls from PubMed, EuropePMC, bioRxiv, and citation networks to build structured reports with evidence grading. It handles biological targets, drugs, diseases, and general academic topics, running collision-aware searches when terms have naming conflicts. Every claim gets a T1-T4 evidence tier (mechanistic down to mention-only), and it delegates to specialized skills for deep entity profiling. The workflow is rigid: clarify, disambiguate, search, synthesize into a formal report with mandatory sections and full source attribution. It's overkill for quick lookups but solid when you need a defensible lit review with proper methodology baked in.

skills.sh installs
669
GitHub stars
1.8K
last updated
Aug 21, 2026

Install

$ npx -y skills add mims-harvard/tooluniverse --skill tooluniverse-literature-deep-research --agent claude-code

Installs into .claude/skills of the current project.

Files

Literature Deep Research

Systematic literature research: disambiguate, search with collision-aware queries, grade evidence, produce structured reports.

KEY PRINCIPLES: (1) Disambiguate first (2) Right-size deliverable (3) Grade every claim T1-T4 (4) All sections mandatory even if "limited evidence" (5) Source attribution for every claim (6) English-first queries, respond in user's language (7) Report = deliverable, not search log


LOOK UP, DON'T GUESS

Search PubMed/EuropePMC FIRST before reasoning. A published paper beats memory.

Factoid search strategy:

  1. Extract KEY TERMS (most specific nouns/verbs)
  2. EuropePMC_search_articles(query="term1 term2 term3", limit=5)
  3. No results -> BROADEN (remove most restrictive term)
  4. Too many -> NARROW (add specific terms)
  5. Answer usually in abstract of top results
  6. Failed query -> try DIFFERENT TERMS/synonyms, don't repeat

Sponsors

Details

Repository
github.com/mims-harvard/tooluniverse
Categories
Git & Pull Requests, Code Review & Quality, Data Science & ML
First seen
Jun 3, 2026

More from mims-harvard/tooluniverse

All 68
1alirezarezvani avatarcopy-editingalirezarezvani/claude-skillsWhen the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'p668skills.sh installs
2feiskyer avatarspec-kit-skillfeiskyer/claude-code-settingsGitHub Spec-Kit integration for constitution-based spec-driven development. 7-phase workflow. Triggers: "spec-kit", "speckit", "constitution", "specify", ".spec665skills.sh installs
3wanshuiyin avatarresearch-litwanshuiyin/auto-claude-code-research-in-sleepSearch and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does th651skills.sh installs
4alirezarezvani avatarterraform-patternsalirezarezvani/claude-skillsTerraform infrastructure-as-code agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Covers module design patterns, state management st647skills.sh installs
5alirezarezvani avatargoogle-workspace-clialirezarezvani/claude-skillsGoogle Workspace administration via the gws CLI (github.com/googleworkspace/cli). Install, authenticate, and automate Gmail, Drive, Sheets, Calendar, Docs, Chat645skills.sh installs
6basicmachines-co avatarmemory-defragbasicmachines-co/basic-memory-skillsDefragment and reorganize agent memory files: split bloated files, merge duplicates, remove stale information, and restructure the memory hierarchy. Use when me643skills.sh installs