CtrlK
BlogDocsLog inGet started
Tessl Logo

nature-polishing

Polish, restructure, or translate academic prose into Nature-leaning English using writing-strategy principles, curated Nature/Nature Communications article patterns, and phrase-level support from Academic Phrasebank. Use whenever the user asks to polish a manuscript paragraph, abstract, introduction, results, discussion, conclusion, title, methods section, or Chinese academic draft for publication-quality English. Also covers LaTeX layout/typesetting (排版) fixes — loose or sparse pages, stranded section headings, figures that don't fill the page or split across pages, "Float too large", multi-panel figure arrangement, and Supplementary Information that looks empty — via references/latex-layout.md. Also trigger on general academic/scientific writing requests even without the word "Nature", including academic writing, scientific writing, SCI/paper writing, English manuscript polishing, language editing, proofreading, and Chinese phrasings such as 学术写作、科研写作、论文润色、写paper、SCI写作、英文论文润色、语言润色、润色、改写、学术英语、英文写作.

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A clean, concise router with a well-sequenced workflow, undermined by actionability and progressive-disclosure gaps because several referenced bundle paths (manifest.yaml, static/, core/failure-modes.md) are missing from the actual skill bundle.

Suggestions

Ship the manifest.yaml, static/ fragments, and core/failure-modes.md that the routing protocol instructs Claude to Read, or revise the body to reference files that exist in the bundle.

Add a short fallback near step 1 noting what to do if a referenced fragment is absent, so the workflow degrades gracefully instead of breaking.

Confirm the references.on_demand table and the latex-layout.md path match the actual references/ contents so on-demand loading is unambiguous.

DimensionReasoningScore

Conciseness

The router is lean and assumes Claude's intelligence, delegating detail to on-disk fragments ('Do not try to apply the polishing logic from memory'); nearly every token earns its place, with only minor verbosity in the layout paragraph.

3 / 3

Actionability

Guidance is specific in form (priority order, named files, 'compile and visually inspect'), but the routing protocol directs Claude to Read manifest.yaml, static/, and core/failure-modes.md, which do not exist in the provided bundle—only the references/ files are present, so the executable path is partly broken.

2 / 3

Workflow Clarity

A clearly sequenced five-step protocol with explicit checkpoints ('State the detected axis values in one short line so they can correct you cheaply') and a feedback loop for layout work ('compile and visually inspect... before and after').

3 / 3

Progressive Disclosure

The router-to-fragment design is well structured in principle, but the primary navigation targets it cites (manifest.yaml, static/, core/failure-modes.md) are absent from the bundle; only references/ exists and latex-layout.md resolves correctly, leaving a real structural gap.

2 / 3

Total

10

/

12

Passed

Description

100%

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 names concrete actions, supplies abundant natural trigger terms in both English and Chinese, and explicitly covers both capability and invocation conditions.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Polish, restructure, or translate academic prose', 'LaTeX layout/typesetting fixes') and names specific failure modes like 'stranded section headings' and 'Float too large', matching the score-3 anchor.

3 / 3

Completeness

Explicitly answers both 'what' (polish/restructure/translate prose, LaTeX layout fixes) and 'when' via 'Use whenever the user asks to polish...' and 'Also trigger on general academic/scientific writing requests'.

3 / 3

Trigger Term Quality

Broad coverage of natural user terms including English ('language editing', 'proofreading', 'SCI writing') and Chinese phrasings ('论文润色', '写paper', '润色') that a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (Nature-leaning academic polishing plus LaTeX layout) with distinctive triggers unlikely to fire for unrelated skills; uses third-person voice throughout.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
Yuan1z0825/nature-skills
Reviewed

Table of Contents

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.