paper-write-sci

根据 LaTeX 论文项目撰写、修订和润色 SCI 期刊论文，默认 AI 自主模式，也支持人机协作仅输出审查计划；提供作者风格化写作、数字事实核验、逻辑树多轮审查与 PDF/Word 渲染闭环。⚠️ 不适用：仅改格式/样式参数、纯参考文献管理、图片处理、非论文写作任务。

Quality

76%

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/paper-write-sci/SKILL.md

Quality

Content

85%

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

The content is highly actionable and well-structured with a clear multi-phase workflow, explicit validation checkpoints, and well-signaled one-level-deep references that all resolve to real files. Its main weakness is mild verbosity from repeating the run-directory/intermediate-file conventions.

Suggestions

Consolidate the repeated run-directory path and intermediate-file constraints into a single canonical statement; reference it from the other sections instead of restating it in 目标, 输出, 中间文件约束, and 阶段 0.

Tighten the 风格系统 and 阶段 3 guidance, which restate some rules already covered in 约束, to reduce token redundancy.

Dimension	Reasoning	Score
Conciseness	The body is largely actionable and avoids explaining concepts Claude already knows, but it is long and somewhat repetitive — the run-directory path and intermediate-file rules are restated multiple times (e.g. 目标/输出/中间文件约束/阶段 0), so it could be tightened toward the lean anchor.	2 / 3
Actionability	It gives an exact executable command ('python3 scripts/prepare_workspace.py --paper-dir ... [--mode ...] [--style ...]'), concrete build-chain precedence, specific file paths, and a default section ordering — copy-paste ready guidance matching the fully-executable anchor.	3 / 3
Workflow Clarity	It defines a clear six-phase sequence (阶段 0–5) with explicit validation checkpoints — '在写入任何新数字前，必须先过数字审查', '结束前，必须通过章节职责终审、全文一致性终审和逻辑树终审', and '若有阻塞性问题，修复后再复审' — meeting the feedback-loop anchor.	3 / 3
Progressive Disclosure	SKILL.md is an overview that points one level deep to real bundle files (all 11 references/templates and the script verified present) via clear '按需读取的参考文件' and '参考文件' navigation sections, with guidance on when to read each — matching the well-signaled one-level-deep anchor.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 and well-differentiated with an explicit exclusion list, but its trigger terms are parked in metadata keywords rather than natural user phrasing, and it lacks an explicit 'Use when' clause.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g. 'Use when writing or revising SCI journal papers in LaTeX, polishing manuscripts, or running number/logic reviews').

Surface one or two natural-language user phrasings (e.g. '写论文/改论文/润色论文') in the description body itself rather than relying solely on the keywords list.

Dimension	Reasoning	Score
Specificity	It lists multiple concrete actions — '撰写、修订和润色', '作者风格化写作、数字事实核验、逻辑树多轮审查与 PDF/Word 渲染闭环' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It clearly states what the skill does but lacks an explicit 'Use when...' trigger clause; the 'when' is only implied by the scope and the ⚠️ 不适用 exclusion, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	It exposes relevant terms (SCI论文写作, 期刊论文, LaTeX论文, 论文润色, 风格化写作, 数字审查, 逻辑审查) but they sit in frontmatter keywords rather than natural phrasing a user would say, and common variations like '写论文/改论文' are missing, so coverage is partial rather than comprehensive.	2 / 3
Distinctiveness Conflict Risk	The narrow niche (SCI/LaTeX paper writing with style/number/logic audits) plus an explicit non-applicability list ('不适用：仅改格式/样式参数、纯参考文献管理、图片处理、非论文写作任务') makes it clearly distinguishable and unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
referenced_paths_exist	Referenced path issues: 1 missing, 17 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: huangwb8/ChineseResearchLaTeX
Path: skills/paper-write-sci/SKILL.md
Commit: 01044a6

Reviewed: 3 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.