nature-statistics

Audit, revise, or draft manuscript statistical reporting for Nature / high-impact journal submissions. Use when the user asks to check statistical analysis sections, p values, confidence intervals, sample size, biological versus technical replicates, randomization, blinding, multiple-comparison correction, model assumptions, figure legends, Results statistics wording, reviewer comments about statistics, or Chinese academic drafts needing publication-ready Statistical analysis text. Also trigger on general paper-statistics requests such as 统计审查、统计分析小节、统计方法、p值、样本量、重复数、多重比较、置信区间、效应量、图注统计、审稿人统计意见.

Quality

88%

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

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.

A well-organized, actionable review/audit skill with a concrete workflow and copy-paste output templates. The main gap is two missing ../nature-shared/ cross-references, which break otherwise-clear navigation.

Suggestions

Resolve the two dead cross-references — either add ../nature-shared/journal-formats/nature-machine-intelligence.md and ../nature-shared/core/consistency-sweep.md to the bundle, or inline the NMI and consistency-sweep guidance into local reference files so the links resolve.

Collapse the 'Source hierarchy' section into a one-line pointer to references/source-basis.md to remove the duplication and tighten conciseness.

Add an explicit validate→fix→retry loop in the workflow (e.g., after drafting, re-run the reviewer-checklist QA and iterate until no P0/P1 issues remain) to lift workflow clarity from a 4 to a 5.

Dimension	Reasoning	Score
Conciseness	The body is largely lean — 'Default stance', 'Red lines', output-format templates, and a 'Related files' table all earn their tokens without explaining basic statistics. It stops short of a 5 because the 'Source hierarchy' section partly duplicates references/source-basis.md and the two output-format blocks run long.	4 / 5
Actionability	Instruction-only yet highly actionable: a 9-step workflow naming specific reference files, two copy-paste-ready output-format templates, an explicit AUTHOR_INPUT_NEEDED convention, and concrete 'Red lines' prohibitions cover the common audit and drafting cases.	5 / 5
Workflow Clarity	The 9 numbered steps give a clear sequence with a final-QA checkpoint ('Run final QA. Use references/reviewer-checklist.md before final delivery') and partial-input boundary handling, but there is no explicit validate→fix→retry feedback loop embedded in the steps.	4 / 5
Progressive Disclosure	SKILL.md is a well-structured overview pointing one level deep to a 'Related files' table with 'Open when' signaling, and all six local references/*.md files exist. It is not a 5 because two cross-references in the body and table (../nature-shared/journal-formats/nature-machine-intelligence.md and ../nature-shared/core/consistency-sweep.md) are absent from the bundle, leaving dead navigation links.	4 / 5
	Total	17 / 20 Passed

Description

95%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, third-person description that clearly states both the capability and a rich, bilingual set of triggers. Its only weakness is that the 'what' is carried by just three verbs while the rest of the text is trigger enumeration.

Dimension	Reasoning	Score
Specificity	Names the domain and three concrete actions ('Audit, revise, or draft manuscript statistical reporting'), but the action list is only three verbs and the bulk of the description is triggers rather than enumerated capabilities, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both 'what' ('Audit, revise, or draft manuscript statistical reporting for Nature / high-impact journal submissions') and 'when' with a concrete 'Use when the user asks to check…' clause followed by specific trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage across two languages — 'p values, confidence intervals, sample size, biological versus technical replicates, randomization, blinding, multiple-comparison correction' plus Chinese synonyms like 'p值、样本量、重复数、多重比较、置信区间、效应量、图注统计', matching the comprehensive-synonyms anchor.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Nature / high-impact manuscript statistical reporting) with distinctive triggers (replicates, blinding, multiple-comparison correction, Chinese academic drafts), giving minimal overlap with other skills.	5 / 5
	Total	19 / 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: 2 suspicious	Warning

	Total	15 / 16 Passed

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

Reviewed: about 6 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.