nature-writing

Draft, restructure, or plan Nature-style manuscript sections and initial-submission materials from author-provided claims, results, figures, notes, or Chinese drafts. Use for abstracts, introductions, related work, methods, Results or experiments, discussions, conclusions, titles, full manuscript arguments, and first-submission packages such as cover letters, title pages, highlights, author contributions, availability or declaration text, and reviewer suggestions. Also use to classify Results evidence, decide what belongs in main text, captions, Methods or source data, or Supplementary Information, compress Results to the shortest sufficient evidence chain, prevent revision accretion, and audit paragraph necessity or claim repetition. Trigger on drafting a paper or section, structuring a manuscript, academic writing, first submission, 投稿材料、首次投稿、投稿信、标题页、亮点、作者贡献、数据可用性声明、推荐审稿人.

Quality

89%

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-designed dynamic router that is lean, highly actionable, and clearly sequenced, with strong progressive-disclosure intent via on-demand references. It falls short of top marks only in minor conciseness padding, a lighter validation loop, and several referenced paths absent from the shipped bundle.

Suggestions

Tighten the 'Why this split' section and consolidate the long on-demand bullet list to remove rationale that repeats the routing protocol.

Add an explicit validation/recovery step for drafting (e.g., re-check claim-evidence alignment after each section draft) to strengthen the feedback loop.

Ensure manifest.yaml and the static/ fragments referenced as step-1/step-3 prerequisites are present alongside SKILL.md, or note where they live, so the router's navigation resolves within the bundle.

Dimension	Reasoning	Score
Conciseness	The router is lean for its scope and avoids re-explaining concepts Claude already knows, but a few passages could be tightened — e.g., the 'Why this split' section and the long on-demand bullet list each repeat rationale that could be condensed. Not a level 5 because minor padding remains.	4 / 5
Actionability	Gives concrete, executable instruction throughout: explicit file paths to Read, a five-step protocol, axis-detection rules, and a numbered priority order for applying fragments. As an instruction-only router, the absence of code is not penalized because the guidance is specific and directly actionable.	5 / 5
Workflow Clarity	Five steps are clearly sequenced with a correction checkpoint (state detected axis values before drafting) and a missing-input placeholder rule, but there is no full validate→fix→retry feedback loop for drafting itself, leaving it just below the level-5 anchor.	4 / 5
Progressive Disclosure	Well-structured router with a short overview and a clear on-demand reference table pointing one level deep into references/. Held below 5 because the shipped bundle is missing manifest.yaml (the step-1 linchpin) and the static/ and ../nature-shared/ paths the body routes to, so navigation is partly unresolved against the actual bundle.	4 / 5
	Total	17 / 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, third-person description that comprehensively enumerates concrete drafting and submission actions with explicit 'what' and 'when' guidance plus bilingual trigger terms. The only gap is that the boundary against sibling Nature-family skills is not surfaced in the description itself.

Suggestions

Add a brief boundary clause to the description (e.g., 'initial submission only — not revision correspondence or figure generation') to reduce overlap with nature-response/nature-figure.

Consider trimming the long enumeration of submission-package sub-items slightly, since the core trigger ('first submission') already conveys the use case.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — 'Draft, restructure, or plan', 'classify Results evidence', 'decide what belongs in main text, captions, Methods or source data, or Supplementary Information', 'compress Results to the shortest sufficient evidence chain', 'prevent revision accretion', 'audit paragraph necessity or claim repetition' — giving comprehensive coverage of specific capabilities.	5 / 5
Completeness	Explicitly answers both 'what' ('Draft, restructure, or plan Nature-style manuscript sections and initial-submission materials...') and 'when' ('Use for abstracts, introductions...'; 'Trigger on drafting a paper or section...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural English triggers ('drafting a paper or section', 'structuring a manuscript', 'academic writing', 'first submission') plus bilingual synonyms ('投稿材料、首次投稿、投稿信、标题页、亮点、作者贡献、数据可用性声明、推荐审稿人'), covering the full range of phrases a user would say.	5 / 5
Distinctiveness Conflict Risk	The Nature-style manuscript-drafting niche is clearly scoped to initial submission, but the description does not itself carve the boundary against sibling skills like nature-polishing or nature-response, leaving minor overlap risk with closely related 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
relative_links	Relative link issues: 1 missing	Warning
referenced_paths_exist	Referenced path issues: 1 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: Yuan1z0825/nature-skills
Path: skills/nature-writing/SKILL.md
Commit: 7e626a8

Reviewed: 5 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.