nature-statistics

Audit or improve manuscript statistical reporting, including experimental units, replication, uncertainty, tests, and figure statistics. Use for 统计审查、统计方法小节、图注统计 and reviewer concerns; compute new analyses only when requested with data.

Quality

85%

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-structured, disciplined skill body: crisp stance, bounded inputs, a sequenced workflow with QA, concrete output templates, and a real reference bundle with clear navigation cues. Remaining weaknesses are mild redundancy between sections and two unresolvable cross-bundle reference paths.

Suggestions

Consolidate the inline Workflow file citations or the Related-files table so each file is pointed to from one canonical location.

Add a brief feedback instruction to the final QA step (e.g. 'if P0 issues remain, revise and re-run the checklist before delivery').

Verify or inline the ../nature-shared/journal-formats/nature-machine-intelligence.md and ../nature-shared/core/consistency-sweep.md paths so every referenced target resolves within the deployed bundle.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes competence ("Treat the independent experimental unit as the default `n`") with no padding or explanation of known concepts. Not 5 because of minor redundancy: reference files are cited inline in Workflow steps 5-9 and again in the Related-files table, and "Red lines" partially restates "Default stance".	4 / 5
Actionability	Guidance is fully executable for an instruction-only skill: two copy-paste-ready output-format templates, explicit conventions (AUTHOR_INPUT_NEEDED, [P0/P1/P2] severity labels), a precise n-definition policy, and concrete prohibitions ("Do not invent p values, sample sizes, degrees of freedom..."). Specific examples cover the audit and drafting cases.	5 / 5
Workflow Clarity	The nine-step Workflow is clearly sequenced with design extraction, n-definition, claim-to-analysis mapping, failure-mode checks, and a final QA step using reviewer-checklist.md. Not 5 because there is no explicit feedback loop describing what to do when final QA or completeness checks fail (e.g. return to which step, when to stop).	4 / 5
Progressive Disclosure	All six references/*.md files cited in the body exist and are one level deep, well signaled both inline in the Workflow and via the Related-files table's "Open when" column. Not 5 because the two ../nature-shared/... paths do not resolve against the actual bundle structure, a minor navigation gap.	4 / 5
	Total	17 / 20 Passed

Description

83%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 description with a clear what, an explicit bilingual 'Use for' trigger clause, and a well-drawn computation boundary. The main gaps are missing natural English trigger synonyms and unmentioned body-level capabilities (drafting, reviewer-response support).

Suggestions

Add common English trigger phrases alongside the Chinese ones, e.g. 'statistical review', 'methods section', 'figure legends', 'sample sizes', 'p-values'.

Name the drafting and reviewer-response capabilities in the description so users asking to rewrite a statistical analysis section or answer reviewer comments trigger the skill.

Trim the topic enumeration slightly (e.g. drop 'uncertainty, tests') in favor of one or two action verbs like 'rewrite' or 'draft'.

Dimension	Reasoning	Score
Specificity	"Audit or improve manuscript statistical reporting, including experimental units, replication, uncertainty, tests, and figure statistics" lists several concrete actions and scope areas. It falls short of the 5 anchor because the enumerated items are topics rather than distinct actions and capabilities present in the body (drafting, reviewer-response support) are not named; it exceeds the 3 anchor's '1-2 concrete actions' coverage.	4 / 5
Completeness	It explicitly answers both questions: the "what" (audit or improve manuscript statistical reporting, including experimental units, replication, uncertainty, tests, and figure statistics) and an explicit "Use for..." clause with concrete trigger phrases plus a scope boundary for computation. This matches the 5 anchor; the 4 anchor's weaker 'when' does not apply.	5 / 5
Trigger Term Quality	"Use for 统计审查、统计方法小节、图注统计 and reviewer concerns; compute new analyses only when requested with data" provides natural bilingual trigger phrases a user would actually say. Not 5 because common English variations ("statistical review", "methods section", "figure legends", "sample size") are absent; clearly above the 3 anchor's partial keyword coverage.	4 / 5
Distinctiveness Conflict Risk	"Manuscript statistical reporting" with 统计审查/图注统计-style triggers is a distinct niche with low generic-conflict risk. Not 5 because the evident sibling skill suite (nature-shared journal formats and consistency sweeps) creates minor overlap risk with closely related figure- and methods-writing skills.	4 / 5
	Total	17 / 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: 50851ef

Reviewed: 3 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.