Overview
Academic Research Skills packages the stages of a research project — search, read, draft, review, revise, finalise — as Claude Code skills rather than as one monolithic prompt. Each stage is its own skill with its own sub-agents, so the model that hunts for literature is not the same configuration as the one arguing with your methods section. The project's stated position is human-in-the-loop rather than end-to-end automation: it puts verification gates between stages so a claim cannot slide from a search result into a manuscript unchecked.
Four skills make up the suite. Deep Research runs a 13-agent research team across eight modes, including a PRISMA-style systematic review and a Socratic mode that interrogates your question before it starts collecting. Academic Paper is a 12-agent writing pipeline with eleven modes spanning drafting, revision and format conversion. Academic Paper Reviewer is a seven-agent peer-review pass that returns criterion-bound narrative judgements instead of a score. Academic Pipeline is the ten-stage orchestrator that chains the other three and enforces the integrity checks between them.
It installs as a Claude Code plugin marketplace, with a manual symlink path for people who want to read and edit the skill files themselves. Pandoc and tectonic are optional dependencies used for document conversion. The repository is written in Python and licensed CC-BY-NC 4.0 — attribution required, commercial use not permitted — which is worth checking against your institution's rules before adopting it for funded work.
What it does
- Deep Research: a 13-agent research team with 8 modes, including PRISMA systematic review and Socratic exploration
- Academic Paper: a 12-agent writing pipeline with 11 modes for drafting, revision and format conversion
- Academic Paper Reviewer: 7 agents producing criterion-bound narrative peer review rather than a numeric score
- Academic Pipeline: a 10-stage orchestrator that chains the other skills with integrity verification gates
- Human-in-the-loop by design — stages hand back for approval instead of running unattended
- Optional Pandoc and tectonic integration for converting manuscripts between formats
Getting started
Needs a current Claude Code and an ANTHROPIC_API_KEY. Pandoc and tectonic are optional and only used for document conversion.
Add the marketplace and install
Run both commands inside Claude Code. The first registers the repository as a plugin marketplace; the second installs the suite.
/plugin marketplace add Imbad0202/academic-research-skills
/plugin install academic-research-skillsStart with a single stage
The individual skills work on their own — Deep Research for a literature pass, Academic Paper Reviewer for a critique of a draft you already have — before you commit to the full pipeline.
Run the orchestrated pipeline
Academic Pipeline chains research → write → review → revise → finalise across ten stages, stopping at each integrity gate for your confirmation rather than pushing through.
Check the licence before funded work
The suite is CC-BY-NC 4.0: attribution is required and commercial use is not permitted, which is a stricter licence than most agent-skill repositories carry.
Commands and code are distilled from the project's own documentation — always check the official repo for the latest.
When to use it
- Run a structured literature review with an auditable trail instead of an unstructured chat
- Get an adversarial peer-review pass on a draft before you send it to a real reviewer
- Keep a long writing project organised across sessions, with each stage handed back for approval
- Study how a multi-agent research workflow is decomposed — the skill files are plain, readable markdown
How Academic Research Skills compares
Academic Research Skills alongside other open-source agent skills & plugins tools AI/TLDR tracks, ranked by GitHub stars.
| Tool | Stars | What it does |
|---|---|---|
| Superpowers | ★ 297k | A composable skills plugin that installs a spec-first, TDD, subagent-driven development methodology into Claude Code, Codex, Cursor, Gemini CLI and other coding harnesses. |
| Skills for Real Engineers | ★ 282k | Matt Pocock's everyday agent skills for coding agents, covering alignment grilling, planning, code review and research — small, composable and meant to be edited. |
| ECC | ★ 276k | An installable plugin that adds 68 agents, 286 skills, hooks, rules, memory and an agent-config security scanner to Claude Code, Codex and other coding harnesses. |
| Karpathy Coding Guidelines | ★ 218k | A Claude Code plugin and CLAUDE.md rule set built from Andrej Karpathy's observations on LLM coding pitfalls: think before coding, keep it simple, make surgical changes, and work to verifiable success criteria. |
| Ponytail | ★ 159k | A skill and plugin that makes a coding agent take the laziest correct route — a seven-rung ladder from "does this need to exist?" to "the minimum that works" — while keeping validation, security and accessibility off the chopping block. |
| Caveman | ★ 111k | A skill plus local proxy that shortens an AI coding agent's prose while leaving code, commands and paths untouched — the rule file cuts what the agent writes, the proxy compresses what it reads. |
| Addy’s Agent Skills | ★ 104k | A pack of production engineering skills for AI coding agents, with nine lifecycle slash commands — /spec, /plan, /build, /test, /review, /ship — installable into 70+ agents. |
| Academic Research Skills | ★ 51.1k | A Claude Code skill suite for the whole research pipeline |