reaper

Reaper

Reaper (REAd PapER) — an AI-native scientific research pipeline. A composable set of AI agent skills that takes a research goal — optionally with a research paper — and autonomously conducts rigorous, multi-step academic research. Runs on any agent that supports the SKILL.md convention (Cursor, Codex CLI, Cline, Continue, Gemini CLI, Copilot, Windsurf, Claude Code, and 40+ more).

What Reaper Does

Give Reaper a research question — with or without a PDF. It reads the paper (if provided), searches for related work, formalizes hypotheses, investigates them in parallel, critiques its own findings, and delivers a structured research report — all without manual prompting between steps.

# Without a paper — pure goal-driven research
/reaper "explore the feasibility of post-quantum threshold signatures"

# With a paper
/reaper "determine if the security proof in Section 4 holds under asynchrony" path/to/paper.pdf

How you invoke a skill depends on the host agent. The /<skill> form above is the canonical display convention used throughout these docs — it works directly on slash-command hosts (e.g. Claude Code), and on auto-discovery hosts (Cursor, Codex CLI, Cline, Continue, Gemini CLI, Copilot, Windsurf, …) you simply ask the agent to "run the /reaper skill on …" by its bare name.

Key capabilities:

• Autonomous multi-stage pipeline — goal clarification, paper analysis, literature review, hypothesis formalization, parallel investigation, critique, and synthesis all chain automatically
• Parallel investigation with keep-or-discard discipline — multiple hypotheses are investigated concurrently; only genuine progress advances the working state, while dead ends stay logged
• Built-in academic search — paper search, PDF download, citation graph tracing, and venue resolution across arXiv, IACR ePrint, Semantic Scholar, DBLP, and OpenAlex
• Domain-agnostic design — ships with cryptography and distributed systems references, but swap the reference files to adapt to any research domain
• Multi-model AI consultation — optionally consult Codex, Gemini, DeepSeek, or local models for a second opinion at every pipeline stage
• Composable skills — each pipeline stage is an independent skill you can run standalone
• Host-agnostic — distributed as plain SKILL.md folders that work across 45+ AI coding agents

How It Works

Reaper executes a multi-stage pipeline where investigation runs in parallel batches and critique provides feedback from multiple sources:

                     ┌── /analyze-paper (if paper) ──┐
/clarify-goal ─────> │                               ├─> /formalize-problem
                     └── /review-literature ─────────┘          │
                           │ (parallel)                         v
                           │                    ┌──────────> /brainstorm
                           └── calls            │                │
                               /analyze-paper   │                │
                               per downloaded   │    ┌─ /investigate ─────────────────┐
                               paper            │    │  plan batch                    │
                                                │    │    ├──> agent H1 ─┐            │
                                                │    │    ├──> agent H2 ─┼──> merge   │
                                                │    │    └──> agent H3 ─┘     │      │
                                                │    │          next batch or done    │
                                                │    └────────────────────────────────┘
                                                │                    │
                                                │    ┌─ /critique ────────────────────┐
                                                │    │  --self  --codex  "feedback"   │
                                                │    └────┬───────────────────┬───────┘
                                                │         │                   │
                                                │   deepen/explore    rewrite/done ──> /synthesize ──> report.md
                                                └─────────┘

Skills

Each skill can be used independently or composed by the orchestrator. Invoke by skill name using your host's native skill-loading mechanism.