nature-data

Prepare, audit, or revise Nature-ready Data Availability statements, data repository plans, dataset citations, and FAIR metadata checklists for manuscripts. Use when the user asks about Nature data availability, research data sharing, repository selection, accession numbers, restricted or sensitive data, source data, supplementary datasets, DataCite-style dataset references, FAIR metadata for academic publication, or Chinese-to-English data availability wording for Chinese-speaking authors preparing Nature-family submissions. Also trigger on general academic-writing data needs even without the word "Nature", such as writing a data availability statement for any journal, code/data sharing sections, repository selection while writing a paper, and Chinese phrasings like 数据可用性声明、数据可用性、数据共享、代码可用性、学术写作数据声明、写数据声明、数据存放、数据仓库选择.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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, concise router with concrete guardrails and a sensible static/dynamic progressive-disclosure design. Its main defect is that the core layer it instructs Claude to always load (manifest.yaml and static/core/*.md) is missing from the bundle, undermining both actionability and the file navigation it advertises.

Suggestions

Bundle the missing always_load core files (manifest.yaml and static/core/stance.md, chinese-mode.md, workflow.md) so the router's 'load the core every time' instruction is executable.

Add an inline validation checkpoint in Step 3 (e.g., verify every inventoried dataset has a classified route and identifier before drafting) so the workflow has an explicit feedback loop rather than relying on the absent workflow.md.

Confirm the ../nature-shared/journal-formats/nature-machine-intelligence.md path resolves from the installed skill location, or inline the minimal Nature Machine Intelligence requirements to avoid a broken cross-skill reference.

Dimension	Reasoning	Score
Conciseness	The router is lean and assumes Claude's competence, earning most of its tokens; the 'Why this split' section and the list of mirrored sibling skills are mild padding that could be trimmed.	4 / 5
Actionability	Gives concrete inline guidance — explicit file paths to load, named access routes, and hard guardrails ('Do not invent DOIs, accession numbers, repository names, licences...') — but the always_load core files it directs Claude to read are absent from the bundle.	4 / 5
Workflow Clarity	A clearly sequenced four-step routing protocol with explicit guardrails (no inventing identifiers, flag 'available upon request' as weak) and a FAIR/metadata audit checkpoint; the detailed eight-step workflow itself lives in the missing core/workflow.md.	4 / 5
Progressive Disclosure	The static/dynamic split and on-demand reference table are well designed and clearly signaled, but the foundational always_load layer (manifest.yaml, static/core/stance.md, chinese-mode.md, workflow.md) and the nature-shared journal file are referenced yet absent from the bundle, breaking the navigation it promises.	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 concrete actions, comprehensive natural trigger terms (including Chinese variants), and an explicit 'Use when' clause. Its only weakness is deliberate broadening beyond the Nature niche, which slightly raises overlap risk with general academic-writing skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Prepare, audit, or revise') across several distinct deliverables (Data Availability statements, repository plans, dataset citations, FAIR metadata checklists), giving comprehensive coverage rather than vague language.	5 / 5
Completeness	Explicitly answers both 'what' (Prepare/audit/revise... statements, plans, citations, checklists) and 'when' ('Use when the user asks about...', 'Also trigger on...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including synonyms ('Nature data availability', 'research data sharing', 'accession numbers', 'source data') plus concrete Chinese phrasings (数据可用性声明, 数据共享) users would actually say.	5 / 5
Distinctiveness Conflict Risk	Has a clear niche (Nature-family data availability statements) with distinct triggers, but explicit broadening to 'any journal' and 'general academic-writing data needs even without the word Nature' creates minor overlap with general academic-writing skills.	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-data/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.