nature-citation

Add strict Nature/CNS citations to manuscript text by splitting long passages into citable segments, searching only accepted flagship and subjournal titles from Nature Portfolio, the AAAS Science family, and Cell Press, filtering by publication time range, and exporting one reference-manager-ready output by default. Use this skill whenever the user asks to input text and automatically get references, add citations to a paragraph/manuscript, find Nature-series or CNS support for statements, create text-to-reference correspondence, "分段引用", "自动给出引用", "Nature系列引用", "CNS及子刊", "支撑文献", "补引用", "找引用", or export EndNote/RIS/ENW/Zotero RDF. Also trigger on general academic-writing citation needs even without the word "Nature", such as adding references while writing a paper, finding sources/literature for a claim, building a reference list, citation/referencing for academic writing, and Chinese phrasings like 学术写作引用、写论文加引用、写paper找文献、加参考文献、配文献、引用文献、文献支撑.

Quality

83%

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

71%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.

A well-structured, lean router with concrete routing and validation guidance, undermined by a progressive-disclosure defect: the core 'always_load' files (manifest.yaml and static/core/*.md) it tells Claude to read are absent from the bundle, so the primary load path cannot actually be followed.

Suggestions

Ship the missing always_load files — manifest.yaml plus static/core/principles.md, static/core/chinese-mode.md, and static/core/workflow.md — or rewrite the routing protocol to load only files that actually exist in the bundle.

If the static/core layer is intentionally absent, replace the manifest-based load step with direct inline links to the existing references/*.md files so the primary path is self-contained.

Tighten the 'Why this split' section; its rationale largely restates the routing protocol and could be cut to recover tokens.

Dimension	Reasoning	Score
Conciseness	The router is short and assumes Claude's intelligence without explaining what citations or Nature journals are, but the 'Why this split' section re-states the layering rationale that the routing protocol already implies, a minor trim opportunity.	4 / 5
Actionability	Gives concrete, executable routing — numbered steps, exact file paths to read, the specific script name with its '--scope' flag, and an on-demand table mapping conditions to reference files — with only minor gaps because full flag detail is deferred to script-usage.md.	4 / 5
Workflow Clarity	The four-step routing protocol and referenced seven-step workflow are clearly sequenced, with explicit validation guidance ('Never present a paper as support merely because its title is related', refetch by PMID for incomplete authors); some checkpoints are delegated to core/workflow.md rather than stated inline, which keeps it just below the top anchor.	4 / 5
Progressive Disclosure	The two-layer structure and on-demand references table are well signaled and the existing references/*.md and scripts/ files are real and one level deep, but the body instructs always_load of manifest.yaml and static/core/{principles,chinese-mode,workflow}.md, none of which exist in the bundle, breaking navigation for the core layer.	3 / 5
	Total	15 / 20 Passed

Description

96%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.

A strong, specific description with explicit 'what' and 'when' coverage and rich bilingual trigger terms. The only soft spot is mild overlap risk from the general academic-writing triggers, which slightly lowers distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'splitting long passages into citable segments', 'searching only accepted flagship and subjournal titles', 'filtering by publication time range', and 'exporting one reference-manager-ready output' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (the opening action sentence) and 'when' via an explicit 'Use this skill whenever the user asks to...' clause with concrete trigger phrases, satisfying the top anchor.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage in both English ('add citations to a paragraph/manuscript', 'build a reference list') and Chinese ('分段引用', '写论文加引用'), plus concrete file-format terms (EndNote/RIS/ENW/Zotero RDF) and synonyms users would actually say.	5 / 5
Distinctiveness Conflict Risk	The Nature/CNS-specific framing carves a clear niche with minimal conflict risk, but the broad 'general academic-writing citation needs' triggers create minor overlap with a generic citation/reference skill, keeping it just below the top anchor.	4 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	14 / 16 Passed

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

Reviewed: about 8 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.