nature-polishing

Polish, restructure, or translate academic prose into concise Nature-leaning English while preserving facts, evidence boundaries, terminology, and citation intent. Use for manuscript paragraphs, abstracts, introductions, Results, discussions, conclusions, titles, Methods, Chinese drafts, proofreading, language editing, and general academic or scientific writing. Also use to shorten bloated Results, allocate evidence across main text, captions, and Supplementary Information, prevent reviewer-driven revision accretion, reduce repeated statistics or claims, and apply paragraph-necessity checks. Covers LaTeX layout or typesetting fixes such as sparse pages, stranded headings, oversized or split figures, float errors, multi-panel arrangement, and sparse Supplementary Information via references/latex-layout.md. Trigger on 学术写作、科研写作、论文润色、SCI写作、英文论文润色、语言润色、润色、改写、学术英语、排版.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/nature-polishing/SKILL.md

Quality

Content

67%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, lean router with a clear five-step workflow and good gating between prose-polishing and layout tasks. However, the bundle it depends on is largely absent — manifest.yaml, the static/ layer, and all ../nature-shared/ files are missing — so the progressive-disclosure structure is broken and the actionable content the router promises is not actually reachable.

Suggestions

Ship the missing bundle files the router depends on (manifest.yaml, the static/ fragments, core/failure-modes.md, and the ../nature-shared/core/*.md and journal-formats/*.md files) so the disclosure is navigable one level deep as designed.

Add a validation/branch step for missing fragments: when a manifest-mapped file is absent, fall back to a documented default or stop and report rather than silently proceeding.

Reconcile the on_demand references table referenced in step 5 — it points at references/ files via the manifest, but the manifest is missing, so the on-demand path is currently unresolvable.

Dimension	Reasoning	Score
Conciseness	The router is lean and assumes Claude's competence — it delegates all logic to on-disk fragments rather than restating principles, and every line ('Do not try to apply the polishing logic from memory', 'Load only what step 2 selected') earns its place.	5 / 5
Actionability	It gives concrete procedural steps (read manifest, detect axes, load fragments, apply in priority order) and names specific files, but the actionable payload those files would carry is absent from the bundle, so the guidance reduces to 'go read files that are not there' — executable in form but not in substance.	3 / 5
Workflow Clarity	The five-step routing protocol is clearly sequenced with a progress checkpoint (state axis values so the user can correct), and the layout branch is well-gated, but there is no validation/recovery loop for the multi-file loading itself — e.g. what to do when a mapped fragment is missing — which matters because several mapped files are in fact absent.	4 / 5
Progressive Disclosure	Structure is excellent in intent (a short router pointing one level deep to manifest.yaml, static/ fragments, and ../nature-shared/ files), but scoring against the actual bundle reveals the disclosure has collapsed: manifest.yaml, static/, core/failure-modes.md, and every ../nature-shared/*.md path are missing — only references/latex-layout.md exists — so the references are not navigable to their content, fitting the 'references are buried / content that should be separate is inline' band below the midpoint.	2 / 5
	Total	14 / 20 Passed

Description

80%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 detailed, third-person description that concretely maps the skill's actions and coverage with strong trigger-term breadth including Chinese keywords. It is slightly long and lacks an explicit 'Use when ...' trigger sentence, which caps completeness at 4.

Suggestions

Add a single explicit 'Use when ...' trigger sentence near the start (e.g. 'Use when polishing or restructuring scientific manuscript prose, translating Chinese drafts to English, or fixing LaTeX layout.') to make the when unambiguous and lift completeness to 5.

Trim the long enumeration of sections into a tighter list to reduce verbosity without losing coverage.

Include a couple of casual English trigger phrases users naturally say (e.g. 'tighten my results', 'make this read more like Nature') alongside the Chinese keywords.

Dimension	Reasoning	Score
Specificity	The description lists many concrete actions — 'shorten bloated Results, allocate evidence across main text, captions, and Supplementary Information', 'prevent reviewer-driven revision accretion', 'apply paragraph-necessity checks' — alongside comprehensive section coverage (abstract, intro, Results, discussion, conclusions, titles, Methods), giving broad and concrete coverage of the skill's capabilities.	5 / 5
Completeness	It clearly answers 'what' (polish/restructure/translate academic prose with evidence-boundary and citation preservation) and supplies a 'Use for ...' plus a closing 'Trigger on ...' clause, but there is no explicit 'Use when ...' trigger sentence, so the when side could be more direct — keeping it just below a 5.	4 / 5
Trigger Term Quality	It includes a strong set of natural terms (manuscript paragraphs, abstracts, Results, language editing, proofreading) plus Chinese trigger keywords (学术写作, 科研写作, 论文润色), but the bulk of triggers are domain jargon rather than the casual phrases a user would naturally say, leaving a few common variations unstated.	4 / 5
Distinctiveness Conflict Risk	The Nature-leaning academic-polishing niche is fairly distinct and the trigger set is specialized (e.g. zh-to-en, reviewer-driven revision accretion), giving minimal conflict risk, though broad overlap remains with general 'academic writing' or 'language editing' 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: 1 missing	Warning

	Total	15 / 16 Passed

Repository: Yuan1z0825/nature-skills
Path: skills/nature-polishing/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.