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.

Quality

97%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise, actionable, and has a clearly sequenced, validated workflow. Its main weakness is progressive disclosure: it signals many pipeline/guardrails/knowledge/scaffolds files that are absent from the bundle, leaving most deep references unresolvable.

Suggestions

Add the referenced pipeline/*.md, guardrails/*.md, knowledge/*.md files and scaffolds/ directory to the bundle so each signaled reference resolves to a real file.

Alternatively, if those files are intentionally external, note where they live and add a verification step so missing references fail loudly rather than silently.

Reduce minor redundancy between the inline Stage 4 guardrail pointers and the later 'Guardrails — always active' section by pointing to one canonical list.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence; it dispatches detail to pipeline/guardrails/knowledge files rather than explaining ML concepts inline, and nearly every line is directive. Minor repetition of guardrail pointers is negligible.	3 / 3
Actionability	Concrete, copy-paste-ready commands — 'pip install pymupdf4llm pdfplumber requests pyyaml' and 'python skills/paper2code/scripts/fetch_paper.py {ARXIV_ID} ...' — plus explicit argument parsing. The two referenced scripts exist in the bundle.	3 / 3
Workflow Clarity	Five stages are explicitly ordered ('Do NOT skip stages. Do NOT combine stages. Execute them in order') with validation checkpoints ('Verify the outputs exist before proceeding') and a fallback protocol, matching the feedback-loop anchor.	3 / 3
Progressive Disclosure	The referencing pattern is excellent — one-level-deep, clearly signaled references to pipeline/01_paper_acquisition.md, guardrails/hallucination_prevention.md, knowledge/transformer_components.md, scaffolds/ — but none of those files or directories exist in the actual bundle (only scripts/ is present), so the disclosed structure does not hold up against the real bundle.	2 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, uses third-person voice, gives strong natural triggers, and clearly states both what the skill does and when to invoke it. It is a strong, well-scoped description.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Converts an arxiv paper into a minimal, citation-anchored Python implementation', 'Flags all ambiguities honestly', 'Never invents implementation details' — matching the multi-action anchor.	3 / 3
Completeness	Explicitly answers both what (converts paper to a Python implementation) and when (an explicit 'Trigger when...' clause), the strongest anchor.	3 / 3
Trigger Term Quality	Natural trigger phrasings users would say — '/paper2code with an arxiv URL or paper ID', 'implement this paper', 'pastes an arxiv link asking for implementation' — cover common variations well.	3 / 3
Distinctiveness Conflict Risk	A clear arxiv-to-code niche with distinct triggers ('/paper2code', 'implement this paper', arxiv link) makes overlap with other skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: PrathamLearnsToCode/paper2code
Path: skills/paper2code/SKILL.md
Commit: fcffce7

Reviewed: 13 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.