Analyze Paper

Path Resolution Protocol

This skill references files in sibling skills. {{REAPER_SKILL_DIR}} below is a template placeholder — you MUST substitute it with the absolute install path of the /reaper skill before reading, or the read will fail. Common install locations:

• ~/.claude/skills/reaper/ (Claude Code)
• ~/.cursor/skills/reaper/ (Cursor)
• ~/.agents/skills/reaper/ (Codex CLI, Cline, Gemini CLI, Copilot, OpenCode, Warp, Goose, Replit — universal target)
• ~/.continue/skills/reaper/ (Continue)
• ~/.windsurf/skills/reaper/ (Windsurf)
• <repo-root>/skills/reaper/ (during repo development)

Sibling-skill dependency: This skill assumes the full /reaper package was installed together (npx skills add SebastianElvis/reaper). Single-skill installs will fail to resolve sibling references.

Instructions

1. Read the Paper

Read the paper at the provided path using your host's file-read primitive (works for PDFs and text files on hosts that support PDF reading; otherwise extract text first).

Follow the three-pass strategy from {{REAPER_SKILL_DIR}}/references/paper-analysis.md:

• Pass 1 (skeleton): Abstract, introduction, conclusion, theorem statements. Identify the main claims.
• Pass 2 (construction): Protocol details, proof sketches, figures. Understand the key technical idea.
• Pass 3 (proofs): Full formal proofs, appendices, security reductions. Verify logical steps.

When --goal is provided, calibrate depth by relevance to the goal: Pass 1 for all papers; Pass 2 for medium-relevance; all three passes for high-relevance papers.

2. Extract Information

For each section below, extract the relevant information. When extracting theorem statements or formal claims, copy them verbatim — do not paraphrase.

Critical: Distinguish what the paper claims (in the introduction, abstract) from what it actually proves (in the theorems, proofs). Note any discrepancies.

3. Write Output

Write the extracted information to reaper-workspace/notes/paper-summary.md (or the path specified by --output) with the following structure:

# Paper Summary: [Paper Title]

## Metadata
- **Title**:
- **Authors**:
- **Venue/Year**:
- **Paper ID**: (ePrint, arXiv, DOI)
- **Link**: (e.g., https://arxiv.org/abs/XXXX.XXXXX or https://eprint.iacr.org/YYYY/NNNN)

## Problem Statement
What problem does this paper solve? Why does it matter?

## System Model
[Extract all model dimensions relevant to the paper's domain. Consult `{{REAPER_SKILL_DIR}}/references/model.md` for the domain-appropriate dimensions to extract. Every applicable dimension must have a concrete answer.]

## Construction Overview
High-level protocol description. Key technical idea. Building blocks used.

## Key Results
List each theorem/claim verbatim:
1. **Theorem X.X**: [exact statement]
   - Model: [exact model under which this is proved]
   - Proof technique: [game-based / simulation / reduction]

## Proof Technique
Overall proof approach. Key lemmas. Reduction chain. Where the corruption threshold and network model are used.

## Complexity Claims
- Communication: 
- Rounds:
- Computation:

## Strengths
[Label each major/minor: novelty, methodology fit, proof rigor, evaluation quality, clarity.]

## Weaknesses
[Label each major/minor/fatal: broken methodology, missing proofs, unjustified claims, unfair comparisons, unclear writing, overclaimed results.]

## Key Definitions and Notation
Non-standard notation. Formal definitions referenced by the proofs.

## Red Flags
Any concerns identified during reading (see `{{REAPER_SKILL_DIR}}/references/paper-analysis.md` for common red flags).

## Relevance
[Present ONLY when --goal is provided. Tag one or more: *problem definition*, *formalization*, *solution technique*, *negative result*, *literature/context*, *writing model*. One sentence per tag explaining how this paper relates to the research goal.]

Sections should be proportional to what the paper warrants. If a paper has no complexity claims, omit that section. If the proof technique is trivial, keep it brief. The template is a guide, not a form to fill in mechanically.

Quality Criteria

• Every theorem statement is copied verbatim, not paraphrased
• The system model section is complete — no missing dimensions (network, adversary, trust, communication, crypto)
• Strengths and weaknesses are labeled with severity (major/minor/fatal) and are honest — if the paper looks solid, say so; if there are concerns, list them specifically
• Red flags section is honest — no concerns is a valid answer
• The summary is useful standalone — a reader who hasn't seen the paper should understand the key claims and approach
• When --goal is provided, relevance tags are specific to the goal, not generic ("related to our topic")
• If the PDF is unreadable, try page-by-page with the pages parameter. If it still fails, report the error — do not fabricate a summary