ChineseResearchLaTeX is a collection of LaTeX templates and an AI-assisted workflow for preparing Chinese research documents such as grant proposals, papers, theses, and academic CVs. Researchers use it to plan, format, review, compile, and revise these documents with human oversight. The catalogue skills and instructions support its agent-based research-writing workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add huangwb8/ChineseResearchLaTeX --skill paper-select-journalgit clone --depth 1 https://github.com/huangwb8/ChineseResearchLaTeXWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/huangwb8/chineseresearchlatex/paper-select-journal)<a href="https://agentmods.dev/skills/huangwb8/chineseresearchlatex/paper-select-journal"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/paper-select-journal/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/huangwb8/chineseresearchlatex/paper-select-journal"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/paper-select-journal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00194 | $0.03106 |
| Opus 5.5 | $0.00078 | $0.01242 |
| Sonnet 5.5 | $0.00039 | $0.00621 |
| Haiku 4.5 | $0.00019 | $0.00311 |
Grade A, and why
paper-select-journal scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Select Journal
核心原则
- 当前信息必须实时核验：scope、官网、业内认可度、中科院分区、近 3 个月论文都属于时效性信息，不能靠旧记忆。
- 中间文件只允许落在当前工作目录下的
.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/paper-select-journal/隐藏目录；用户若明确指定其他目录，才可覆盖默认值。 - Set1 不再依赖固定语义权重。脚本只负责最小硬过滤与候选池整理，真正的语义规划由当前宿主模型完成。
- Set1 不是最终答案。最终报告只保留证据充分的 Set3，最多 10 个期刊。
- 不能推荐明显预警、垃圾期刊或影响因子低于
3的期刊；若确实保留低于3的例外，必须写明“为何它仍是领域内人类专家认可的稳妥选择”。 - 宁可少报，也不要为了凑满 10 个而硬凑。
输入与工作区
- 用户需求可选，manuscript 必选。
- manuscript 可来自粘贴的标题 / 摘要 / 全文片段，或本地
.md、.txt、.tex、.pdf、.docx，也可混合提供。 - 一旦进入隐藏工作区流程，后续供脚本读取的
analysis/*.json必须保留在当前 run 目录内；不要把manuscript_profile.json、set2_scope_review.json、final_recommendations.json指到 run 目录外。
先初始化隐藏工作区：
python3 <skill_root>/scripts/init_workspace.py --project-root .
脚本会创建 .bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/paper-select-journal/{yyyy-mm-dd-hh-mm}/，其中至少包含：
inputs/analysis/candidates/pubmed/reports/
后续所有中间文件都必须留在该 run 目录内。
流程
输入
按用户请求和配置文件提供必要输入；缺失信息应明确列出并停止依赖该输入的步骤。
执行步骤
先写 manuscript 画像
完整理解论文后，把结果写入 analysis/manuscript_profile.json。
- 模板：
templates/manuscript_profile.template.json - 写法：
references/manuscript-profile.md最低字段： titleabstractkeywordsmanuscript_summary
画像的作用是帮助 AI 理解稿件，而不是喂给固定打分公式。
如果用户偏好复杂，优先把偏好写成自然语言放进 target_journal_brief 或 notes，不要为了脚本凑很多硬编码线索。
如果确实需要保留低 IF 的人工例外期刊，只能作为后续人工补录候选，并且必须在最终报告里解释“为什么它虽然低于阈值，仍是领域内稳妥选择”。
用内置 2023IF.xlsx 做 Set1 候选池
内置目录：assets/journal_catalog/2023IF.xlsx
运行：
python3 <skill_root>/scripts/shortlist_journals.py \
--workspace .bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/paper-select-journal/{yyyy-mm-dd-hh-mm} \
--profile .bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/paper-select-journal/{yyyy-mm-dd-hh-mm}/analysis/manuscript_profile.json
产物：
candidates/set1_candidates.jsoncandidates/set1_candidates.md
这里的脚本只做最小硬过滤：
- 影响因子下限
- 用户明确排除的期刊
- 基础元数据整理（JIF、分区、OA 比例、引用量）
不要把这一步输出误解为“已经按语义排好序的最终 shortlist”。 你必须读取该候选池，再结合 manuscript 自主规划真正值得进入 Set2 的期刊。
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/journal_catalog/2023IF.xlsx 1546 KB
- CHANGELOG.md 5.1 KB
- config.yaml 2.2 KB
- README.md 6.5 KB
- references/journal-quality-checklist.md 999 B
- references/manuscript-profile.md 908 B
- references/report-schema.md 486 B
- scripts/common.py 3.5 KB runs code
- scripts/fetch_pubmed_recent.py 9.6 KB runs code
- scripts/init_workspace.py 4.5 KB runs code
- scripts/render_report.py 4.9 KB runs code
- scripts/shortlist_journals.py 9.1 KB runs code
- templates/final_recommendations.template.json 1.1 KB
- templates/manuscript_profile.template.json 681 B
- templates/scope_review.template.json 730 B
- templates/set3_similarity_review.template.json 524 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +21 lines a8d3eac0fc66
- 1mo ago First seen · 243 lines · 194 tokens per session scan A 8a4697046157
paper-select-journal is a skill published in the GitHub repository huangwb8/ChineseResearchLaTeX (2,980 stars, last pushed 10d ago), licensed MIT. It adds 194 tokens to every session and 3,106 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
semantic-scholar-deep
Deep research over the Semantic Scholar Graph API. Covers endpoints missing from allenai's lookup skill — paper references (backward citations), recommendations, batch paper lookup (up to 500 IDs), snippet search, and multi-hop citation graph traversal (BFS forward/backward). Use when the user asks to build a citation…
adaptyv
Cloud laboratory platform for automated protein testing and validation. Use when designing proteins and needing experimental validation including binding assays, expression testing, thermostability measurements, enzyme activity assays, or protein sequence optimization. Also use for submitting experiments via API…
openevidence
Query OpenEvidence (clinical evidence assistant) without an MCP server. Closely mirrors the openevidence-mcp tool surface - check auth, list question history, fetch an article, or ask a new question (with optional follow-up thread). Use when the user asks medical / evidence-based clinical questions, references…
thesis-control
Use when AI-assisted thesis or manuscript edits risk claim drift, scope creep, loss of intended use, experiment-role promotion, or repeated revisions that fail to converge; provides author-intent control, lightweight or strict contracts, drift audits, revision escalation, and human gates.
manuscript-reframe
Reframe report-like academic drafts into paper-form scientific arguments while preserving or explicitly renegotiating author intent; requires an approved old-versus-proposed spine, evidence and argument baselines, analysis-role control, and post-edit drift review.
onescience-primitives
A resource-search tool for finding reusable OneScience building blocks. It searches a catalogue for the most relevant scientific workflow components and returns their supporting details and usage contracts.