CtrlK
BlogDocsLog inGet started
Tessl Logo

paper-write

本科与硕士学位论文全流程撰写辅助。支持大纲审核(理工科/文科)、结构仿写(通用/实验/绪论/摘要;文科含文献综述、案例分析、对策建议、文科绪论与摘要)、参考文献获取、融合、润色(含实验章节/文科章节)、缩写、扩写、防 AIGC、中英互译、结构化信息提取。当用户提到论文撰写、大纲审核、论文章节仿写、参考文献、论文润色、防 AIGC、论文翻译、文科论文、文献综述、对策建议时使用。

60

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/paper-write/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

55%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 well-structured as a concise routing index to per-task reference files, but none of the referenced reference/*.md files are present in the bundle, so the progressive-disclosure structure is broken and the promised executable content is unreachable. Workflow clarity also lacks validation checkpoints for risky batch operations.

Suggestions

Ship the missing reference/*.md files (e.g. reference/outline-review-science.md, reference/polish.md) or remove the links — currently every reference path is a broken pointer.

Add explicit validation/checkpoint steps to Step 3 for risky operations like merge.md fusion and anti-aigc rewriting (e.g. 'verify no information lost; re-check citation formatting before output').

Inline at least one concrete, copy-ready example (e.g. a GB/T 7714 citation template or a Word-spacing rule) so the body is actionable even before a reference file is loaded.

DimensionReasoningScore

Conciseness

The body is a lean routing table pointing to per-task reference files with minimal prose, efficiently assuming Claude's competence; only the 注意事项 section adds slightly more commentary than strictly necessary.

4 / 5

Actionability

It gives concrete routing (which reference file to load per task) and a few explicit constraints (Word 适配, 信息零丢失), but the actual executable prompts live in unloaded reference files, so the body itself stops at pointers rather than copy-ready instructions.

3 / 5

Workflow Clarity

A clear 3-step sequence (识别任务类型 → 收集输入 → 执行并输出) is present, but it lacks explicit validation/checkpoint steps for batch or risky operations such as reference merging and anti-AIGC rewriting, which caps clarity at 3 per the feedback-loop rule.

3 / 5

Progressive Disclosure

The body is organized as one-level-deep references (reference/*.md), which would normally score well, but the referenced bundle directory does not exist in the skill package — every link is a broken pointer, so there is no actual progressive-disclosure structure to navigate.

1 / 5

Total

11

/

20

Passed

Description

88%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, comprehensive, and clearly answers both what and when with a concrete trigger clause, defining a distinct thesis-writing niche. Trigger terms are extensive but lean toward internal task labels over natural user phrasing, keeping that dimension at 4.

DimensionReasoningScore

Specificity

Enumerates many concrete actions (大纲审核、结构仿写、参考文献获取、融合、润色、缩写、扩写、防 AIGC、中英互译、结构化信息提取) with sub-variants, matching the comprehensive-coverage anchor.

5 / 5

Completeness

Explicitly answers 'what' (full pipeline of thesis-writing actions) and 'when' with a concrete '当用户提到...' trigger clause, satisfying the top anchor.

5 / 5

Trigger Term Quality

The trigger clause lists many natural terms (论文撰写、大纲审核、论文章节仿写、参考文献、论文润色、防 AIGC、论文翻译、文科论文、文献综述、对策建议), but most are phrased as skill-internal task labels rather than verbatim user utterances and omit common synonyms.

4 / 5

Distinctiveness Conflict Risk

The niche is narrow (本/硕学位论文撰写, with 理工/文科 splits) and triggers are domain-specific, giving it a clear niche with minimal conflict risk against general 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

relative_links

Relative link issues: 23 missing

Warning

Total

15

/

16

Passed

Repository
xstongxue/best-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.