CtrlK
BlogDocsLog inGet started
Tessl Logo

nature-response

Draft, audit, or revise Nature-style revision correspondence packages: point-by-point reviewer-separated response letters, rebuttal letters, revision cover letters, LaTeX cover/response templates, and red-marked revised-manuscript excerpts. Keep mutually blind reviewers isolated so no reviewer-facing response reveals another reviewer's comments, numbering, recommendation, or author response. Prevent reviewer-driven manuscript accretion by preferring replacement, compression, or SI relocation over appending non-central defense prose. Use for reviewer comments, editor decision letters, pasted editorial emails, response drafts, cover letters, response to reviewers, rebuttal, 修回信, 返修邮件, 编辑邮件, 返修 cover letter, 审稿意见回复, 逐点回复, 大修回复, 小修回复, 回复审稿人, 修改稿回复, 写rebuttal, 回应审稿意见, 标红修改, or LaTeX 模板.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 router with a clear sequenced workflow, explicit validation and feedback loops, and an exemplary progressive-disclosure layout whose referenced files all exist on disk. Only minor conciseness and actionability trimming keeps it from a perfect score.

Suggestions

Break the long run-on sentence in step 3 ('Follow the workflow... parse manuscript metadata, decision type, ... run QA; and derive package readiness') into a bulleted or numbered list so each workflow action is scannable.

Inline a one-line summary of the decision-type gate action (e.g. the exact 'ask Major vs Minor Revision' prompt) so the router is actionable without opening intake-and-routing.md for the most common case.

Consider a short 'Quick path' block at the top for the common minor-revision draft case to reduce reliance on loading the full core for trivial jobs.

DimensionReasoningScore

Conciseness

The router is intentionally short and avoids re-explaining concepts Claude knows, delegating depth to on-demand references; however, step 3 packs a very long run-on enumeration of workflow actions that could be tightened into a list, keeping it just below a 5.

4 / 5

Actionability

Concrete, executable guidance is present — specific file paths, ID conventions (E.1, R1.1, R2.1), and a runnable script (scripts/check_package_consistency.py) with explicit re-run triggers — but the body leans heavily on pointers to other files rather than inlining the steps themselves, leaving minor gaps.

4 / 5

Workflow Clarity

A clear four-step routing protocol is sequenced with explicit validation checkpoints: the mandatory decision-type intake gate, the QA run, and the package-consistency audit re-run after every manuscript edit and before delivery (a genuine validate-fix-retry feedback loop).

5 / 5

Progressive Disclosure

Verified against the bundle: the 12 references/ files (intake-and-routing.md, comment-taxonomy.md, action-mapping.md, tone-and-stance.md, difficult-cases.md, chinese-author-alignment.md, latex-templates.md, package-consistency-audit.md, qa-checklist.md, etc.) and scripts/check_package_consistency.py all exist and match the cited paths; the two-layer static/dynamic split keeps references one level deep and well-signaled via the on-demand table.

5 / 5

Total

18

/

20

Passed

Description

100%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 exemplary: it states concrete capabilities, provides a rich set of English and Chinese trigger phrases, and explicitly pairs 'what' with 'when'. Distinctiveness is strong given the specialized domain.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Draft, audit, or revise', 'point-by-point reviewer-separated response letters', 'rebuttal letters', 'revision cover letters', 'LaTeX cover/response templates', 'red-marked revised-manuscript excerpts' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' ('Draft, audit, or revise Nature-style revision correspondence packages...') and 'when' via a concrete 'Use for...' clause enumerating triggers, matching the score-5 anchor.

5 / 5

Trigger Term Quality

Comprehensive natural-language triggers including English forms ('reviewer comments', 'editor decision letters', 'response to reviewers', 'rebuttal', 'cover letter') and a broad set of Chinese synonyms (修回信, 返修邮件, 编辑邮件, 回复审稿人, 写rebuttal, 标红修改) users would actually say.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — Nature-style revision correspondence with reviewer-isolation and anti-accretion rules — with distinct triggers unlikely to fire for unrelated skills.

5 / 5

Total

20

/

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

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

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.