6verity

数学建模竞赛最终验证和验收阶段，支持 Typst 和 LaTeX 双引擎。用于论文写完后检查章节数量、标题顺序、图表引用、数值一致性、占位符、内部文件泄露、参考文献、代码可复现性、编译和提交就绪状态。

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/6verity/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.

A thorough, actionable, well-sequenced verification workflow with strong validation feedback loops and executable commands, slightly held back by length/redundancy and a mostly-inline structure rather than progressive disclosure into separate files.

Suggestions

Tighten redundant sections — collapse the repeated 通用检查 (两种引擎) blocks and trim the lengthy PDF visual-check bullet list into the most decision-relevant checks.

Move the per-engine detail (Typst vs LaTeX check lists) and the full PDF visual-check enumeration into a reference file (e.g. references/visual_checks.md), keeping SKILL.md as a tighter overview that links one level deep.

Dimension	Reasoning	Score
Conciseness	The body is action-oriented and avoids explaining concepts Claude already knows, but at ~240 lines it includes redundancy (repeated 通用检查 blocks, a long PDF visual-check enumeration) that could be tightened.	2 / 3
Actionability	It provides concrete executable bash commands — the writing_check.sh invocation with real flags, typst/xelatex compile, and pdftoppm/mutool/magick fallbacks — backed by an actual script in scripts/, with placeholder variables explicitly justified.	3 / 3
Workflow Clarity	A clearly sequenced 9-step workflow with explicit validation checkpoints, FAIL→fix→rerun feedback loops, and hard-error/warning standards acting as checklists, matching the top anchor.	3 / 3
Progressive Disclosure	Sections are well-organized and references are one-level-deep and signaled (scripts/writing_check.sh exists), but most detail is inline in SKILL.md rather than split into separate reference files, so it reads as more than an overview.	2 / 3
	Total	10 / 12 Passed

Description

67%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.

A specific, well-scoped description that clearly conveys what the skill does and its distinct niche, but it lacks an explicit 'Use when…' trigger clause and frames triggers as a workflow stage rather than natural user phrasings.

Suggestions

Add an explicit 'Use when…' clause naming natural user triggers, e.g. 'Use when the paper is written and ready for final acceptance, or when the user asks to verify/check/accept a math modeling competition paper.'

Surface common trigger phrasings users would actually say (e.g. '论文验收', '检查论文', '编译检查', '提交前检查') alongside the stage framing to improve trigger_term_quality.

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete actions — 检查章节数量、标题顺序、图表引用、数值一致性、占位符、内部文件泄露、参考文献、代码可复现性、编译和提交就绪状态 — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	The 'what' is thorough, but there is no explicit 'Use when…' clause; the 'when' (论文写完后 / 最终验证和验收阶段) is only implied, so per the guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	It includes relevant domain terms (数学建模竞赛、论文、编译、参考文献) but frames the skill as a 'stage' rather than surfacing natural trigger phrasings a user would say, missing common variations.	2 / 3
Distinctiveness Conflict Risk	The niche is sharply defined — math modeling competition final verification supporting Typst and LaTeX — making it unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 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/6verity/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.