Individual skill

paper2code

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.

skills/paper2code/SKILL.md

Read pinned source

Source commit fcffce7a1250659ed74f2a96cdf54595c92306c4

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: No
Observed behavior: Network or broad shell
Last checked: Nov 3, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 1,541
Repository last updated: Apr 3, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

agent Repository topic
claude-code Repository topic
skills Repository topic
research Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 5,341 bytes
SKILL.mdcore · 5,341 bytes
SKILL.mdcore · 5,341 bytes
SKILL.mdcore · 5,341 bytes
guardrails/badly_written_papers.mddoc · 9,054 bytes
guardrails/hallucination_prevention.mddoc · 8,309 bytes
guardrails/scope_enforcement.mddoc · 8,064 bytes
knowledge/loss_functions.mddoc · 10,023 bytes
knowledge/paper_to_code_mistakes.mddoc · 10,569 bytes
knowledge/training_recipes.mddoc · 9,304 bytes
knowledge/transformer_components.mddoc · 14,296 bytes
pipeline/01_paper_acquisition.mddoc · 7,123 bytes
pipeline/02_contribution_identification.mddoc · 8,621 bytes
pipeline/03_ambiguity_audit.mddoc · 10,763 bytes
pipeline/04_code_generation.mddoc · 11,415 bytes
pipeline/05_walkthrough_notebook.mddoc · 6,962 bytes
scaffolds/config_template.yamlasset · 2,690 bytes
scaffolds/data_template.pyruns · 3,263 bytes
scaffolds/evaluate_template.pyruns · 1,736 bytes
scaffolds/loss_template.pyruns · 1,431 bytes
scaffolds/model_template.pyruns · 4,236 bytes
scaffolds/readme_template.mddoc · 1,798 bytes
scaffolds/reproduction_notes_template.mddoc · 3,595 bytes
scaffolds/train_template.pyruns · 5,795 bytes
scripts/extract_structure.pyruns · 11,222 bytes
scripts/fetch_paper.pyruns · 15,812 bytes
worked/attention_is_all_you_need/README.mddoc · 2,662 bytes
worked/attention_is_all_you_need/REPRODUCTION_NOTES.mddoc · 6,015 bytes
worked/attention_is_all_you_need/configs/base.yamlasset · 3,490 bytes
worked/attention_is_all_you_need/notebooks/walkthrough.ipynbruns · 27,573 bytes
worked/attention_is_all_you_need/requirements.txtdoc · 39 bytes
worked/attention_is_all_you_need/review.mddoc · 5,238 bytes
worked/attention_is_all_you_need/src/data.pyruns · 6,089 bytes
worked/attention_is_all_you_need/src/evaluate.pyruns · 2,214 bytes
worked/attention_is_all_you_need/src/loss.pyruns · 2,983 bytes
worked/attention_is_all_you_need/src/model.pyruns · 23,099 bytes
worked/attention_is_all_you_need/src/train.pyruns · 3,449 bytes
worked/attention_is_all_you_need/src/utils.pyruns · 3,125 bytes
worked/ddpm/README.mddoc · 2,845 bytes
worked/ddpm/REPRODUCTION_NOTES.mddoc · 6,241 bytes
worked/ddpm/configs/base.yamlasset · 3,936 bytes
worked/ddpm/notebooks/walkthrough.ipynbruns · 13,987 bytes
worked/ddpm/requirements.txtdoc · 39 bytes
worked/ddpm/review.mddoc · 4,515 bytes
worked/ddpm/src/data.pyruns · 3,246 bytes
worked/ddpm/src/evaluate.pyruns · 8,148 bytes
worked/ddpm/src/loss.pyruns · 1,921 bytes
worked/ddpm/src/model.pyruns · 14,869 bytes
worked/ddpm/src/train.pyruns · 6,634 bytes
worked/ddpm/src/utils.pyruns · 8,171 bytes

Read excerpt


# paper2code — Orchestration

You are executing the paper2code skill. This file governs the high-level flow. Each stage dispatches to a detailed reasoning protocol in `pipeline/`. Do NOT skip stages. Do NOT combine stages. Execute them in order.

## Parse arguments

Extract from the user's input:
- `ARXIV_ID`: the arxiv paper ID (e.g., `2106.09685`). Strip any URL prefix.
- `MODE`: one of `minimal` (default), `full`, `educational`.
- `FRAMEWORK`: one of `pytorch` (default), `jax`, `numpy`.

If the user provided a full URL like `https://arxiv.org/abs/2106.09685`, extract the ID `2106.09685`.
If the user provided a versioned ID like `2106.09685v2`, keep the version.