CtrlK
BlogDocsLog inGet started
Tessl Logo

5writing

数学建模竞赛论文撰写阶段,支持 Typst 和 LaTeX 双引擎。根据 ANALYSIS_MODELING_REPORT.md、RESULTS_REPORT.md 和 figures/*.pdf 选择比赛模板、排版引擎、组织章节,并在论文正文中按章节直接插入图表。

54

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./skills/5writing/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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-sequenced, actionable workflow with concrete engine-specific code and gating logic, but it is heavy on inlined per-competition section lists and LaTeX syntax that would benefit from being split into reference files, and it lacks an explicit compile-validation feedback loop.

Suggestions

Move the large per-competition section-file enumerations and the LaTeX 写作要点 syntax reference into separate reference files (e.g. references/section_layouts.md, references/latex_syntax.md) and link to them from SKILL.md to improve progressive disclosure.

Add an explicit compile-validation feedback loop (e.g. 'Run xelatex twice; if errors appear, fix the .tex and recompile; verify paper/main.pdf exists and has non-zero size') to lift workflow clarity.

Consolidate the duplicated Typst/LaTeX section lists into a single table keyed by competition + engine to reduce token cost.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete commands and code, but the long enumeration of per-competition section file lists (changsanjiao/cumcm/dongsansheng/shuweibei/default/stats/mcm etc.) and repeated LaTeX mirror lists add padding that could be consolidated or moved to a reference.

3 / 5

Actionability

Provides mostly executable guidance: concrete bash checks (ls ... && echo OK || echo MISSING), copy commands, compile commands (xelatex/typst), and full figure/bib code snippets in both engines, with only minor gaps (e.g. exact copy command not shown verbatim).

4 / 5

Workflow Clarity

Clear numbered sequence (步骤 0–6) with engine-selection gating, template existence checks (OK/MISSING branches), and compile-twice guidance for cross-references; missing an explicit post-compile validation/feedback loop (no 'verify PDF built / fix errors / recompile' checkpoint), keeping it just below 5.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ absent), and a large amount of per-template section enumeration and LaTeX syntax reference is inlined in SKILL.md that would be better split into referenced files; the one external pointer (../_references/math_modeling_norms.md) is signaled but the bulk structure stays inline.

3 / 5

Total

14

/

20

Passed

Description

58%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 concretely names the domain and several specific actions with concrete input files, but it omits an explicit 'when to use' trigger clause, which caps completeness, and lacks natural user-facing trigger synonyms.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g. 'Use when writing or typesetting a math modeling competition paper, or when the user mentions 撰写论文/排版/Typst/LaTeX 论文').

Include natural trigger synonyms and file extensions a user might say, such as '写论文'、'排版'、'.tex'、'.typ'、'摘要'。

Optionally surface the compile/verify actions (xelatex/typst compile) in the description so the capability list is more comprehensive.

DimensionReasoningScore

Specificity

Lists several concrete actions (选择比赛模板、排版引擎、组织章节、按章节插入图表) tied to concrete inputs (ANALYSIS_MODELING_REPORT.md、RESULTS_REPORT.md、figures/*.pdf), with minor gaps in coverage (e.g.,编译/校验动作未在 description 中明示).

4 / 5

Completeness

Clearly states 'what' (撰写阶段选择模板/引擎/组织章节/插入图表) but has no 'Use when...' clause or equivalent explicit 'when' trigger guidance, capping completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Contains domain-relevant terms (数学建模竞赛论文撰写、Typst、LaTeX) but lacks the natural phrases/synonyms a user would say (e.g. '写论文'、'排版'、'.tex'、'.typ') and offers no common variations.

3 / 5

Distinctiveness Conflict Risk

The Typst/LaTeX 数学建模论文撰写 niche with specific named competitions is fairly distinct and unlikely to trigger for unrelated skills, with only minor overlap risk against a generic '写作/排版' skill.

4 / 5

Total

14

/

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
jihe520/MathModelAgent
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.