Paper2code

What it does

When your agent uses it

• User runs /paper2code with an arxiv URL
• Says implement this paper
• Pastes an arxiv link asking for implementation

Example prompts

• “implement this paper”
• “Use the paper2code skill to convert an arxiv paper into a minimal, citation-anchored Python implementation”
• “/paper2code”

Requirements

• Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

1. 1Paper Acquisition and Parsing
2. 2Contribution Identification
3. 3Ambiguity Audit
4. 4Code Generation
5. 5Walkthrough Notebook

What it can do on your machine

Read from SKILL.md and the folder at commit fcffce7. 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

  Ships 1 file in scripts/ (Python, from the files we listed), which the agent can run.

  Shell commands in SKILL.md call:

  • python
  • pip

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • arxiv.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

Paper2code loads about 1.3k tokens when it runs. Until then it costs about 83 tokens; SKILL.md has 520 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~83

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

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

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); the scripts in this folder are not scanned.

SKILL.md

The full file from PrathamLearnsToCode/paper2code at commit fcffce7, republished under its MIT licence (© PrathamLearnsToCode). 520 words, ~1,326 tokens.

name

paper2code

description

Converts an arxiv paper into a minimal, citation-anchored Python implementation. Trigger when user runs /paper2code with an arxiv URL or paper ID, says "implement this paper", or pastes an arxiv link asking for implementation. Flags all ambiguities honestly. Never invents implementation details not stated in the paper.

pip install pymupdf4llm pdfplumber requests pyyaml

python skills/paper2code/scripts/fetch_paper.py {ARXIV_ID} .paper2code_work/{ARXIV_ID}/

python skills/paper2code/scripts/extract_structure.py .paper2code_work/{ARXIV_ID}/paper_text.md .paper2code_work/{ARXIV_ID}/

✓ paper2code complete for: {paper_title}
  Output directory: {paper_slug}/
  Files generated: {list of files}
  Unspecified choices: {count} (see REPRODUCTION_NOTES.md)
  Mode: {MODE} | Framework: {FRAMEWORK}

© PrathamLearnsToCode, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 56 other files (scripts) in skills/paper2code of PrathamLearnsToCode/paper2code.

• SKILL.md
• guardrails/badly_written_papers.md
• guardrails/hallucination_prevention.md
• guardrails/scope_enforcement.md
• knowledge/loss_functions.md
• knowledge/paper_to_code_mistakes.md
• knowledge/training_recipes.md
• knowledge/transformer_components.md
• pipeline/01_paper_acquisition.md
• pipeline/02_contribution_identification.md
• pipeline/03_ambiguity_audit.md
• pipeline/04_code_generation.md
• pipeline/05_walkthrough_notebook.md
• scaffolds/config_template.yaml
• scaffolds/data_template.py
• scaffolds/evaluate_template.py
• scaffolds/loss_template.py
• … and 40 more

Open the folder on GitHubat commit fcffce7