PrathamLearnsToCode/paper2code

Health v2 · maintenance only

Flags: no_releases young

Adoption not part of the score

1509 stars · 176 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

An agent skill for coding agents like Claude Code that converts an arXiv paper URL into a working Python implementation. It generates citation-anchored code where every line references the paper section it implements, and flags unspecified implementation choices instead of silently inventing them.

Use cases

• turn an arxiv paper into working code
• reproduce a machine learning paper implementation
• generate code from a research paper with citations
• audit which parts of a paper implementation are unspecified
• implement a paper's model and training loop automatically
• find hyperparameters buried in paper appendices

When to choose

• you need to reproduce an ML paper and want traceable, citation-anchored code
• you use Claude Code or compatible coding agents and want paper-to-code automation
• you want ambiguity in a paper's method explicitly flagged rather than guessed

When to avoid

• you need a guaranteed runnable, verified implementation without manual review
• your target paper has no arXiv version or is not machine-learning focused
• you want a standalone application rather than an agent skill

Facets

plugin · maturity active

agent-framework llm-inference code-review developer-tools machine-learning large-language-models developer-tools artificial-intelligence python cli cross-platform claude-code agent-skill paper-reproduction arxiv citation-anchoring code-generation

Member repositories

For agents

markdown · JSON · MCP: product_card(name="PrathamLearnsToCode/paper2code")