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.

67

Quality

81%

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

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.

The body is a well-structured, actionable instruction skill with a clear diagnostic workflow and excellent reference-file navigation, but it is verbose for its scope and inlines some conventional guidance that could move to the bundle. Tightening the body and pushing codified section rules into references would lift the conciseness and progressive-disclosure scores.

Suggestions

Move well-known conventions (past tense in Results, no new data in Conclusion, paragraph one-idea rule) into a reference file to reduce body length and conciseness penalty.

Add at least one worked before/after example (original, polished, why changed) inline so the abstract guidance has a concrete anchor.

Trim restated basics and keep only the codified, non-obvious rules in SKILL.md to push conciseness from 3 toward 4-5.

DimensionReasoningScore

Conciseness

The ~2000-word body is mostly efficient and encodes skill-specific codification, but it restates well-known academic-writing conventions (e.g., past tense in Results, no new data in a conclusion) that Claude already knows and could be tightened.

3 / 5

Actionability

Concrete, executable guidance throughout: word-count ranges (10-30, <=30), ordered writing sequences, a named failure-mode taxonomy, a banned-phrase list, and a defined output format, with only minor gaps (no worked before/after example).

4 / 5

Workflow Clarity

A clear prioritized diagnostic pipeline ('paper type -> section job -> paragraph logic -> claim/evidence/boundary -> sentence polish') with diagnosis-before-editing and explicit checks (overclaim check at conclusion, proofreading checks); minor validation gaps but no destructive/batch cap applies.

4 / 5

Progressive Disclosure

Five real reference files are surfaced via a clear 'Open when' navigation table and inline links at one level of depth, but the 380-line body retains material (section responsibilities, sentence/paragraph rules) that could be split out, keeping it just below the fully-split 5-anchor.

4 / 5

Total

15

/

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.

The description is specific, trigger-rich, and explicitly pairs a concrete 'what' with an explicit 'when' clause using natural section-level vocabulary, all in third-person imperative voice. It carves a clear niche with low conflict risk.

DimensionReasoningScore

Specificity

Names three concrete actions ('Polish, restructure, or translate') and concrete mechanisms (Nature article patterns, Academic Phrasebank), giving multiple specific actions with only minor coverage gaps versus the comprehensive 5-anchor example.

4 / 5

Completeness

Explicitly answers both 'what' (polish/restructure/translate into Nature-leaning English) and 'when' ('Use whenever the user asks to polish a manuscript paragraph, abstract, ...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Rich natural trigger vocabulary ('polish a manuscript paragraph, abstract, introduction, results, discussion, conclusion, title, methods section, or Chinese academic draft') covers the section types users actually name when requesting this skill.

5 / 5

Distinctiveness Conflict Risk

'Nature-leaning English', specific manuscript sections, and 'Chinese academic draft for publication-quality English' define a clear niche with distinct triggers and minimal overlap with unrelated skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
Galaxy-Dawn/claude-scholar
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.