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。

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./skills/5writing/SKILL.md

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear, validated multi-step workflow for both Typst and LaTeX engines. Its weak spots are verbosity from repeated per-template listings and inline content that would benefit from being moved to separate reference files.

Suggestions

Factor the repeated per-template chapter-file listings into a single reference table (e.g. references/section_layouts.md) and link to it, reducing duplication across template variants.

Move the 'LaTeX 写作要点' section into a separate LaTeX reference file, keeping SKILL.md a concise overview that points to it.

Consolidate the dual-engine examples: present a single canonical figure/reference snippet with engine-specific deltas noted inline rather than restating each fully twice.

Dimension	Reasoning	Score
Conciseness	Content is mostly lean and assumes competence, but it repeats near-identical chapter file listings across many template variants and duplicates every example for both Typst and LaTeX, which could be tightened; it is not yet the 'every token earns its place' level.	2 / 3
Actionability	Concrete, copy-paste-ready commands and code are provided throughout — 'ls "$SKILL_DIR/templates/…"', 'typst compile main.typ', 'xelatex -interaction=nonstopmode main.tex', and full figure/reference/equation snippets in both engines.	3 / 3
Workflow Clarity	Steps 0–6 form a clear sequence with an explicit validation checkpoint (the OK/MISSING template-access check in step 2 with a documented rebuild fallback) and compile-twice cross-reference handling.	3 / 3
Progressive Disclosure	There is one-level-deep signaling (e.g. '../_references/math_modeling_norms.md' and delegating Typst syntax to the typst-author skill), but large blocks — per-template chapter listings and the entire 'LaTeX 写作要点' section — are inline rather than split into reference files.	2 / 3
	Total	10 / 12 Passed

Description

82%Weight 40%Scale 1-3

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, third-person, and clearly distinct, with good natural trigger terms. Its main weakness is the absence of an explicit 'Use when…' clause, which caps completeness at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when writing or formatting a math modeling competition paper, or when the user asks to typeset results in Typst/LaTeX.'

Drop the internal report filenames (ANALYSIS_MODELING_REPORT.md, RESULTS_REPORT.md) from the description — they are workflow internals, not user-facing trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: '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' (select template, choose engine, organize chapters, insert figures), matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	It clearly answers 'what' but has no 'Use when…' / '当…时使用' trigger clause, so per the judging guidelines completeness is capped at 2 even though the 'when' intent is implied by the domain framing.	2 / 3
Trigger Term Quality	Natural domain terms a user would say are present — '数学建模竞赛论文撰写', 'Typst', 'LaTeX', '撰写论文' — giving good coverage of the phrasings users actually use.	3 / 3
Distinctiveness Conflict Risk	The niche is clearly distinct — Typst/LaTeX paper writing tied to math modeling competitions and specific upstream report files — making conflict with unrelated skills unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: jihe520/MathModelAgent
Path: skills/5writing/SKILL.md
Commit: 11f3862

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

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.