CtrlK
BlogDocsLog inGet started
Tessl Logo

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 when the user wants to write or rebuild an abstract, introduction, related-work, method, experiments, discussion, conclusion, title, full manuscript argument, pre-submission cover letter, title page, highlights, author-contribution statement, availability/declaration text, reviewer suggestions, or a complete initial submission package rather than only polish finished prose. Also trigger on general academic-writing and first-submission requests such as writing a paper from scratch, drafting a manuscript/section, structuring a paper, submission package, 投稿材料、首次投稿、投稿前 cover letter、投稿信、标题页、亮点、作者贡献、数据可用性声明、推荐审稿人.

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.

The router is concise and its 5-step workflow is clearly sequenced with genuine confirmation and validation checkpoints. Its main weakness is that the routing protocol depends on manifest.yaml and the core/static fragment files, none of which are bundled, so the skill cannot load the fragments it instructs Claude to read.

Suggestions

Bundle the missing manifest.yaml and the static/ + core/ fragments the routing protocol references (core/stance.md, core/workflow.md, static/fragments/task/submission-package.md), or rewrite the protocol to route only over the references/ files that actually exist.

Make step 1 executable by ensuring manifest.yaml is present and its declared paths resolve to real files, since the entire load-fragments logic hinges on it.

Flatten the references/examples/ tree (e.g., examples/introduction/* at two levels) or have examples/index.md explicitly catalog every nested path so discovery stays one level deep.

DimensionReasoningScore

Conciseness

The ~80-line router is lean: it delegates detail to fragments ('Do not try to apply the drafting logic from memory... Always load fragments from disk') and avoids explaining concepts Claude already knows; even the 'Why this split' rationale is brief and maintenance-oriented rather than padded.

3 / 3

Actionability

The guidance is structurally concrete — a numbered priority order (1–6), explicit axis values, and an on-demand reference table — but its central executable instruction ('Read manifest.yaml') and the named core fragments ('core/stance.md', 'core/workflow.md', 'static/fragments/task/submission-package.md') refer to files that do not exist in the bundle, so the workflow cannot be executed as written; this is the 'incomplete; missing key details' anchor rather than fully copy-paste ready.

2 / 3

Workflow Clarity

A clearly sequenced 5-step routing protocol with explicit checkpoints: 'State the detected axis values in one short line to the user before drafting, so they can correct you cheaply' (confirmation loop) and 'If essential evidence or boundary is missing, write a placeholder and list it under Assumptions or missing inputs:' (validation loop), matching the 'clear sequence with explicit validation steps' anchor.

3 / 3

Progressive Disclosure

The body describes a sophisticated two-layer architecture (manifest.yaml + static/ + core/) and signals references well via markdown links and an on-demand table, and the references/ layer that actually exists is one-level-deep and well-organized — but the primary navigation artifact manifest.yaml and the core/static fragments the protocol tells Claude to load are absent from the bundle, so the described progressive-disclosure structure does not match the actual bundle.

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.

The description is strong across all dimensions: third-person voice, concrete actions, comprehensive trigger coverage in English and Chinese, and an explicit 'Use when' clause. It is clearly scoped to initial-submission Nature-style writing with a notable boundary against polishing and revision work.

DimensionReasoningScore

Specificity

Opens with concrete actions ('Draft, restructure, or plan Nature-style manuscript sections and initial-submission materials') and enumerates a comprehensive set of deliverables (abstract, introduction, related-work, method, experiments, discussion, conclusion, title, cover letter, title page, highlights, author-contribution statement, availability/declaration text, reviewer suggestions), matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both 'what' ('Draft, restructure, or plan Nature-style manuscript sections and initial-submission materials from author-provided claims, results, figures, notes, or Chinese drafts') and 'when' with an explicit trigger clause ('Use when the user wants to write or rebuild...'), plus a secondary trigger sentence, satisfying the 'clearly answers both what AND when' anchor.

3 / 3

Trigger Term Quality

Covers natural terms users would actually say — section names ('abstract, introduction, related-work, method, experiments, discussion, conclusion, title'), submission materials ('cover letter, title page, highlights, author-contribution statement'), request phrasings ('writing a paper from scratch', 'drafting a manuscript/section', 'structuring a paper'), and Chinese equivalents — giving broad coverage rather than just jargon.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche ('Nature-style manuscript sections and initial-submission materials'), scopes itself with 'rather than only polish finished prose', and the skill body further routes revision correspondence to nature-response — distinct triggers make wrong-skill activation unlikely.

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

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
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.