nature-reader

Build full-paper Chinese-English side-by-side, figure/table/equation-aware, source-grounded Markdown readers for journal or conference papers from PDF, DOI, arXiv, publisher HTML, or pasted text. Use whenever the user asks to translate or read a paper, make 中英文对照/原文对照/全文翻译解读, render equations instead of exposing raw LaTeX, extract figures or tables into the right positions, preserve figure/table placement near relevant prose, or keep exact source anchors for every block. This skill must not degrade into a summary-only output unless the user explicitly asks for a summary. Also trigger on general paper-reading and translation requests even without the word "Nature", such as reading/translating an academic paper, literature reading, understanding a paper, and Chinese phrasings like 读论文、精读论文、论文翻译、文献翻译、文献阅读、学术阅读、帮我读这篇文章、翻译这篇paper.

Quality

91%

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

82%Weight 40%Scale 1-5

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

The body is a tight, well-organized router with a clear five-step workflow and good progressive-disclosure structure. Its main weakness is that several referenced core files and the manifest are absent from the bundle, leaving some navigation broken.

Suggestions

Ship the referenced static layer (manifest.yaml and the core/principles.md, core/workflow.md, core/output-contract.md fragments) and the nature-shared/core/terminology-ledger.md file so the routing paths resolve.

Add the concrete commands or extraction steps that step 4 delegates to the source-format fragments, or at least inline one runnable example, to lift actionability from instruction-style hints to executable guidance.

Restate the pre-response verification checklist (from core/output-contract.md) as a short inline bullet list so the workflow has an explicit final checkpoint in the router itself.

Dimension	Reasoning	Score
Conciseness	The router is lean and assumes Claude's competence — no padding, no explaining what a PDF/DOI is — with directives like 'Do not try to apply the reading logic from memory... Always load fragments from disk as described below.' Every token earns its place.	5 / 5
Actionability	Provides concrete guidance — a five-step routing protocol, enumerated source_format values, a priority-ordered build list, named fragment paths, and an on-demand reference table — but the actions are 'Read [file]' directives and paths rather than executable code or commands, leaving minor gaps.	4 / 5
Workflow Clarity	A clear five-step sequence with an explicit early correction checkpoint ('State the detected value... so they can correct you cheaply') and a priority-ordered build; the final pre-response verification checklist is delegated to a fragment rather than restated inline, a minor gap.	4 / 5
Progressive Disclosure	Well-structured router pointing one level deep to manifest.yaml, static/ fragments, and a clearly-signaled on-demand references/ table; however several referenced paths (manifest.yaml, static/, nature-shared/core/terminology-ledger.md, core/principles.md) do not exist in the bundle, so navigation is partly broken.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

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 excellent: it states concrete capabilities, an explicit 'Use whenever...' trigger with both English and Chinese phrasings, and a distinctive niche. It is comprehensive and clearly distinguishable.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across input formats — 'Build full-paper Chinese-English side-by-side...readers', 'render equations instead of exposing raw LaTeX', 'extract figures or tables into the right positions', 'preserve figure/table placement near relevant prose' — matching the comprehensive-coverage anchor.	5 / 5
Completeness	Clearly answers both what (bilingual figure/table/equation-aware source-grounded reader builder) and when with explicit trigger guidance — 'Use whenever the user asks to translate or read a paper' and 'Also trigger on general paper-reading and translation requests even without the word Nature'.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including English phrases ('translate or read a paper', 'reading/translating an academic paper', 'understanding a paper') and Chinese synonyms ('中英文对照', '读论文、精读论文、论文翻译、文献翻译、文献阅读、学术阅读、帮我读这篇文章、翻译这篇paper'), matching the synonyms-and-extensions anchor.	5 / 5
Distinctiveness Conflict Risk	A clear niche (full-paper bilingual readers preserving equations, figures, tables, and source anchors) with distinct, format-specific triggers and minimal overlap with adjacent skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: Yuan1z0825/nature-skills
Path: skills/nature-reader/SKILL.md
Commit: 3817cd1

Reviewed: about 9 hours 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.