CtrlK
BlogDocsLog inGet started
Tessl Logo

nature-writing

Draft, restructure, or plan Nature-style manuscript sections from author-provided claims, results, figures, notes, or Chinese drafts. Use when the user wants to write or rebuild an abstract, introduction, results narrative, discussion, conclusion, title, or full manuscript argument rather than only polish finished prose.

68

Quality

85%

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

78%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-organized, lean instruction skill with concrete templates, a clear sequenced workflow, and exemplary progressive disclosure via a navigation table pointing to real one-level-deep references. Main room for improvement is making the workflow's verification/recovery loops more explicit.

Suggestions

Add an explicit validate/retry loop to the Writing workflow (e.g. after the paragraph-flow check, state what to do when a paragraph fails the one-message test) to strengthen workflow_clarity.

Tighten the section defaults so each pattern is stated once, pointing to the reference for variants, to reduce minor redundancy with the reference guides.

Expand trigger-term coverage in the description by adding common synonyms like 'methods', 'related work', and 'revise' alongside the existing section list.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it avoids explaining what a manuscript is and uses compact tables/bullets — with only minor redundancy between section defaults and the referenced guides.

4 / 5

Actionability

Provides concrete, copy-paste-ready templates (the one-sentence argument scaffold, each section's arrow pattern, the claim-evidence map format) and a verb-calibration list; instruction-only so absent code is not penalized, but a few patterns could be more fully specified.

4 / 5

Workflow Clarity

An explicit 8-step 'Writing workflow' is clearly sequenced with intake gap-exposure and a paragraph-flow check as checkpoints; not a destructive/batch skill, so no hard cap applies, but explicit error-recovery feedback loops are light.

4 / 5

Progressive Disclosure

SKILL.md is a clean overview with a 'When to open extra files' table mapping each real reference file to a concrete trigger; references are one level deep (examples reached via references/examples/index.md) and all referenced paths exist on disk.

5 / 5

Total

17

/

20

Passed

Description

92%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, specific description that names concrete actions and section types, gives an explicit trigger clause, and carves out a distinct niche from generic editing skills. Minor synonym coverage is the only gap.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Draft, restructure, or plan') applied across a comprehensive set of manuscript sections (abstract, introduction, results narrative, discussion, conclusion, title, full manuscript argument), plus the input types it works from.

5 / 5

Completeness

Clearly answers 'what' (draft/restructure/plan Nature-style sections from provided inputs) and 'when' with an explicit 'Use when...' clause and concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural trigger coverage ('write or rebuild an abstract, introduction, results narrative, discussion, conclusion, title, or full manuscript argument'), though a few common synonyms (e.g. 'methods', 'related work', 'revise') are absent.

4 / 5

Distinctiveness Conflict Risk

Niche is clearly scoped to Nature-style manuscript construction, and the 'rather than only polish finished prose' clause sharply distinguishes it from generic prose-polishing skills.

5 / 5

Total

19

/

20

Passed

Validation

81%

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

Validation13 / 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 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 2 deeper-than-1-level

Warning

Total

13

/

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.