Agent skill

Litbase

by aipoch in aipoch/medical-research-skills

Academic paper reading and research development system for biomedical researchers.

Install Litbase

skills CLI

$ npx skills add aipoch/medical-research-skills --skill litbase -a claude-code

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

GitHub CLI

$ gh skill install aipoch/medical-research-skills litbase --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/aipoch/medical-research-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/'awesome-med-research-skills/Evidence Insight/litbase' .claude/skills/litbase && 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/

Paste into Claude Code

Install the "litbase" agent skill from https://github.com/aipoch/medical-research-skills/tree/main/awesome-med-research-skills/Evidence%20Insight/litbase into .claude/skills/litbase/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "litbase", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/aipoch/medical-research-skills/tree/main/awesome-med-research-skills/Evidence%20Insight/litbase

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add aipoch/medical-research-skills --skill litbase -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install aipoch/medical-research-skills litbase --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/aipoch/medical-research-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/'awesome-med-research-skills/Evidence Insight/litbase' .agents/skills/litbase && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "litbase" agent skill from https://github.com/aipoch/medical-research-skills/tree/main/awesome-med-research-skills/Evidence%20Insight/litbase into .agents/skills/litbase/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "litbase", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add aipoch/medical-research-skills --skill litbase -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install aipoch/medical-research-skills litbase --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/aipoch/medical-research-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/'awesome-med-research-skills/Evidence Insight/litbase' .cursor/skills/litbase && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "litbase" agent skill from https://github.com/aipoch/medical-research-skills/tree/main/awesome-med-research-skills/Evidence%20Insight/litbase into .cursor/skills/litbase/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "litbase", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/aipoch/medical-research-skills.git --path 'awesome-med-research-skills/Evidence Insight/litbase'

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add aipoch/medical-research-skills --skill litbase -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install aipoch/medical-research-skills litbase --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/aipoch/medical-research-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/'awesome-med-research-skills/Evidence Insight/litbase' .gemini/skills/litbase && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "litbase" agent skill from https://github.com/aipoch/medical-research-skills/tree/main/awesome-med-research-skills/Evidence%20Insight/litbase into .gemini/skills/litbase/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "litbase", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install aipoch/medical-research-skills litbase

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add aipoch/medical-research-skills --skill litbase -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/aipoch/medical-research-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/'awesome-med-research-skills/Evidence Insight/litbase' .github/skills/litbase && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "litbase" agent skill from https://github.com/aipoch/medical-research-skills/tree/main/awesome-med-research-skills/Evidence%20Insight/litbase into .github/skills/litbase/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "litbase", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add aipoch/medical-research-skills --skill litbase -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install aipoch/medical-research-skills litbase --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/aipoch/medical-research-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/'awesome-med-research-skills/Evidence Insight/litbase' .opencode/skills/litbase && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "litbase" agent skill from https://github.com/aipoch/medical-research-skills/tree/main/awesome-med-research-skills/Evidence%20Insight/litbase into .opencode/skills/litbase/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "litbase", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: litbase
GitHub stars: 2k
Token cost: ~1.6k tokens
SKILL.md length: 513 words
Files: 55
Skills in repo: 567
Repo updated: Sep 17, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Academic paper reading and research development system for biomedical researchers.

Tasks that involve Academic paper search
SKILL.md covers Quick Start, Commands, Note Structure and Research Foundation Document…, plus 4 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Litbase is an agent skill from aipoch/medical-research-skills. Academic paper reading and research development system for biomedical researchers. Finds papers via Semantic Scholar, reads with structured notes, tracks discussion insights, and synthesizes literature into a Research Foundation Document (RFD) for downstream protocol design skills. 8 commands: /setup /feed /read /discuss /recap /update /sync /propose

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 56 other files (for example `CLAUDE.md`, `LITERATURE_HARD_RULES.md` and `README.md`).

It sits in Research & Science, covering Academic paper search. It works with Semantic Scholar. The repository describes itself as: Hundreds of agent skills for medical research, including protocol design, data analysis, evidence insights, and academic writing. The licence is MIT.

When your agent uses it

Tasks that involve Academic paper search

Example prompts

“/litbase”

Requirements

Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 686e09d. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are json).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
- semanticscholar.org
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Litbase loads about 1.6k tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 513 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~90
When it runs · the whole SKILL.md, loaded when a task matches: ~1.6k

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

The full file from aipoch/medical-research-skills at commit 686e09d, republished under its MIT licence (© aipoch). 513 words, ~1,617 tokens.

Download SKILL.mdSave it as .claude/skills/litbase/SKILL.md (or your agent's skills folder). This skill also uses 54 other files; get the full folder from GitHub.

name: litbase
description: Academic paper reading and research development system for biomedical researchers. Finds papers via Semantic Scholar, reads with structured notes, tracks discussion insights, and synthesizes literature into a Research Foundation Document (RFD) for downstream protocol design skills. 8 commands: /setup /feed /read /discuss /recap /update /sync /propose
license: MIT
author: AIPOCH

Source: https://github.com/aipoch/medical-research-skills

LitBase

An academic paper reading and research development system running inside Claude Code (or any compatible agent environment). Built for biomedical researchers who want to find papers, build structured reading notes, track discussion insights, and ultimately synthesize their literature base into a research proposal.

Paper source: Semantic Scholar — free, no login required, 200M+ papers across all disciplines.

Quick Start

Step 1 — Edit config.json with your research folder path:

json

{
  "data_dir": "/path/to/your/research/folder",
  "s2_api_key": "optional — leave empty to use free tier",
  "mode": "auto"
}

Step 2 — Open this folder in Claude Code, then type /setup.

The setup command configures everything automatically — no terminal commands needed.

Commands

Command	When to use	What it does
`/setup`	First use	Guided research profile setup; auto-configures environment
`/feed`	Daily	Updates search terms → searches Semantic Scholar → recommends papers
`/read`	Per paper	Submit a PDF path, DOI, or abstract → generates 4-section structured note
`/discuss [keyword]`	Deep dive	Locate a paper note by author/title/keyword and discuss; auto-records insights
`/recap`	Weekly review	Reading overview, framework completeness map, next-step recommendations
`/update`	Direction shift	Sync research direction changes to memory and search terms
`/sync`	Maintenance	Cross-document consistency check; literature integrity audit
`/propose`	Proposal stage	Synthesizes reading notes into a Research Foundation Document (RFD) for downstream protocol design

Note Structure

Each paper analysis is structured in four sections:

Section	Content
I. Paper Weight	Journal/conference rank, IF, database indexing (SSCI/Scopus/etc.), Q-rank; each author's institution, position, h-index; citation count and yearly average; overall assessment
II. Paper Highlights	Methodological innovation / critique of systemic problems / significance of the research object
III. Transferable Elements	Theory framework, method details, conceptual tools — each tagged to which part of the user's own paper it can support
IV. How to Use in Your Paper	Literature review positioning, suggested citation phrases (English), methodological precedent, research motivation

Show full SKILL.md (233 more words)Show less

Research Foundation Document (RFD)

The /propose command generates an RFD — a structured synthesis of the user's accumulated literature base. It serves as a standardized upstream input to any downstream protocol design skill.

RFD sections: Study Population & Clinical Context → Focused Research Question (P/E/C/O/D/T) → Theoretical Framework & Mechanistic Basis → Methodological Precedents → Identified Research Gaps → Literature Source Index.

All citations in the RFD are sourced exclusively from the user's confirmed reading list. No fabricated references.

Capability Tiers

LitBase adapts to its runtime environment automatically:

Tier	Environment	PDF reading	Paper search	Notes storage	State persistence
A	Web Claude, any LLM chat	Native upload	WebSearch / WebFetch	Artifact output	Session card (paste at session start)
B	Manus, file-capable agents	Claude Read tool	WebFetch → S2 API	File system	MEMORY.md
C	OpenClaw / Claude Code	Claude Read tool (+ optional pdftotext)	WebFetch → S2 API (+ optional Python)	File system	Claude persistent memory

Dependencies

Dependency	Purpose	Required?
Python (stdlib)	Runs paper search and metadata scripts	Optional — WebFetch fallback available
pdftotext (poppler)	PDF text extraction	Optional — Claude native PDF reading available
Claude Code	Executes skill commands	Required for Tier C

No API key required for Semantic Scholar. An optional free key raises rate limits.

Literature Integrity

All commands follow the rules in LITERATURE_HARD_RULES.md:

No fabricated PMIDs, DOIs, titles, authors, citation counts, or study data.
All citations in notes and proposals must be traceable to user-provided papers.
Unverifiable claims are labeled explicitly rather than omitted silently.

File Structure

litbase/
├── SKILL.md                        ← skill manifest (this file)
└── core/                           ← open this folder in Claude Code
    ├── CLAUDE.md                   ← project rules (auto-loaded)
    ├── README.md
    ├── config.json                 ← user config (data_dir, API key, mode)
    ├── search_config.json          ← search terms (maintained by Claude)
    ├── settings.local.json         ← Claude Code permissions template
    ├── install.sh                  ← optional manual setup script
    ├── commands/
    │   ├── setup.md
    │   ├── feed.md
    │   ├── read.md
    │   ├── discuss.md
    │   ├── recap.md
    │   ├── update.md
    │   ├── sync.md
    │   └── propose.md
    ├── references/
    │   ├── LITERATURE_HARD_RULES.md
    │   └── SESSION_CARD_TEMPLATE.md
    ├── scripts/
    │   ├── recommend.py            ← optional: Semantic Scholar search
    │   ├── lookup_paper.py         ← optional: paper metadata query
    │   └── rename_pdfs.py          ← optional: PDF batch rename
    ├── memory/
    │   └── MEMORY.md
    └── notes/
        └── WORKFLOW.md

data_dir/                           ← path set in config.json
  notes/
    reading_list.md
    YYYY-MM-DD/
      recommendations.md
      Author_Year_Keywords/
        Author_Year_Keywords.pdf
        Author_Year_Keywords.md
    recaps/
      YYYY-MM-DD_recap.md
    proposal/
      YYYY-MM-DD_RFD.md

Files

SKILL.md and 54 other files in awesome-med-research-skills/Evidence Insight/litbase of aipoch/medical-research-skills.

SKILL.md
.gitignore
CLAUDE.md
LITERATURE_HARD_RULES.md
README.md
SESSION_CARD_TEMPLATE.md
commands/discuss.md
commands/feed.md
commands/propose.md
commands/read.md
commands/recap.md
commands/setup.md
commands/sync.md
commands/update.md
config.json
core/.gitignore
core/CLAUDE.md
core/README.md
core/commands
… and 36 more

Open the folder on GitHubat commit 686e09d

Compare with similar skills

Litbase 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.

Litbase compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Litbase this skillaipoch/medical-research-skills	2k	—	~1.6k	Automated safety check: Pass	MIT	20 days ago
Literature Reviewneflibata-feng/MyArxiv-Agent	126	21 repos	~5.9k	Automated safety check: Notes	MIT	3 days ago
Paper Research on arXivXiaomiMiMo/MiMo-Code	14k	1 repos	~1.5k	Automated safety check: Pass	MIT	4 days ago
Literature Review AgentAr9av/PaperOrchestra	676	2 repos	~5.2k	Automated safety check: Pass	Custom licence	16 days ago
Paper Searchopenags/paper-search-mcp	2.8k	—	~1.2k	Automated safety check: Notes	MIT	5 days ago
Conference Paper Recommenderjuliye2025/evil-read-arxiv	1.7k	—	~2.5k	Automated safety check: Pass	None	22 days ago

Similar skills

Literature Review
neflibata-feng/MyArxiv-Agent
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.).
126 GitHub starsUsed in 21 repos~5.9k tokens
Research & ScienceAuto-check: notes
Paper Research on arXiv
XiaomiMiMo/MiMo-Code
Searches arXiv, fetches metadata, generates BibTeX, downloads PDFs and finds citations and related papers using a bundled Python script.
14k GitHub starsUsed in 1 repo~1.5k tokens
Research & ScienceAuto-check passed
Literature Review Agent
Ar9av/PaperOrchestra
Step 3 of the PaperOrchestra pipeline (arXiv:2604.05018). An agent skill from Ar9av/PaperOrchestra.
676 GitHub starsUsed in 2 repos~5.2k tokens
Research & ScienceAuto-check passed
Paper Search
openags/paper-search-mcp
Search, download, and read academic papers from 20+ sources (arXiv, PubMed, Semantic Scholar, CrossRef, etc).
2.8k GitHub stars~1.2k tokensUpdated 5 days ago
Research & ScienceAuto-check: notes
Conference Paper Recommender
juliye2025/evil-read-arxiv
Searches DBLP for papers from top conferences such as CVPR, ICLR and NeurIPS, adds Semantic Scholar data, scores them and writes a yearly Obsidian note.
1.7k GitHub stars~2.5k tokensUpdated 22 days ago
Research & ScienceAuto-check passed
Paper Autoraters
Ar9av/PaperOrchestra
Run the four paper-quality autoraters from PaperOrchestra (arXiv:2604.05018, App.
676 GitHub starsUsed in 2 repos~1.6k tokens
Research & ScienceAuto-check passed

Questions about Litbase

What does Litbase do?

Academic paper reading and research development system for biomedical researchers. Litbase is an agent skill from aipoch/medical-research-skills. Academic paper reading and research development system for biomedical researchers.

When should I use Litbase?

Litbase fits situations like: tasks that involve Academic paper search.

How do I install Litbase in Claude Code?

Run `npx skills add aipoch/medical-research-skills --skill litbase -a claude-code`. Or copy the skill folder (awesome-med-research-skills/Evidence Insight/litbase in aipoch/medical-research-skills) into .claude/skills/litbase in your project. Claude Code loads it when a task matches its description.

How do I install Litbase in Codex?

Run `npx skills add aipoch/medical-research-skills --skill litbase -a codex`. Or copy the skill folder (awesome-med-research-skills/Evidence Insight/litbase in aipoch/medical-research-skills) into .agents/skills/litbase in your project. Codex loads it when a task matches its description.

Can I use Litbase 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 aipoch/medical-research-skills --skill litbase -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/litbase, .gemini/skills/litbase, .github/skills/litbase and .opencode/skills/litbase in your project.

What does Litbase need to run?

SKILL.md names no scripts, command-line tools or credentials: Litbase is instructions for the agent only. Our summary lists: Python 3.

Does Litbase access the network?

SKILL.md names 1 domain. As links in the text: semanticscholar.org. This is read from the text; nothing was executed.

Is Litbase 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 Litbase use?

Litbase is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Litbase use?

About 1.6k tokens (SKILL.md is roughly 6.5k 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 Litbase?

Skills that share tags, products or a category with Litbase: Literature Review (neflibata-feng/MyArxiv-Agent, 126 stars), Paper Research on arXiv (XiaomiMiMo/MiMo-Code, 14k stars), Literature Review Agent (Ar9av/PaperOrchestra, 676 stars) and Paper Search (openags/paper-search-mcp, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Litbase?

aipoch (a GitHub organization) maintains it in aipoch/medical-research-skills, which has 1,973 GitHub stars. The repository holds 567 skills in this directory. The repository was last updated on September 17, 2026.

Source: aipoch/medical-research-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Litbase

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

LitBase

Quick Start

Commands

Note Structure

Research Foundation Document (RFD)

Capability Tiers

Dependencies

Literature Integrity

File Structure

Files

Compare with similar skills

Similar skills

More from aipoch/medical-research-skills

Related

Questions about Litbase