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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/huangwb8/ChineseResearchLaTeXnpx agentmods add skills/huangwb8/chineseresearchlatex/research-literature-reviewWrote 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/research-literature-review)<a href="https://agentmods.dev/skills/huangwb8/chineseresearchlatex/research-literature-review"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/research-literature-review/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/research-literature-review"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/research-literature-review.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 | $0.00127 | $0.04184 |
| Opus 5 | $0.00063 | $0.02092 |
| Sonnet 5 | $0.00025 | $0.00837 |
| Haiku 4.5 | $0.00013 | $0.00418 |
Grade A, and why
research-literature-review 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 4d 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Literature Review
定位与检索依赖
- 目标:在一个隔离工作目录内完成“检索 → 去重 → 评分 → 选文 → 写作 → 校验 → PDF/Word 导出”的完整综述流水线。
- 适用:用户明确要系统综述、文献综述、related work、文献调研,并希望得到 LaTeX + BibTeX + PDF/Word 产物。
- 不适用:只想补单条参考文献、只想润色已有正文、只想写普通摘要或与综述无关的文章。
- 最高原则:以最佳可用证据和写作质量完成综述;不确定时说明处理方式,不为赶进度牺牲可信度。
research-literature-search是阶段 1/2 的必需依赖(contractrls.v1)。review 只消费其 manifest、canonical candidates 和 provenance,不再内嵌 provider 或执行第二套 canonical 去重。- 旧名
systematic-literature-review仅作为 prompt 兼容别名保留;.systematic-literature-review/仍是稳定历史工作区名。
输入
最少需要:
{主题}:一句话主题。- 可选范围:时间、语言、研究类型、数据库偏好等。
- 档位:
Premium/Standard/Basic;未指定时读取config.yaml默认值。 - 目标字数与参考文献范围:未指定时按
config.yaml.scoring.default_*_range。 - 输出目录或安全化前缀:未指定时使用安全化主题名。
- 查询输入:阶段 1 前必须提供符合公开 schema 的多查询 JSON;推荐用
--query-file,也可填写当前 run 的input/queries.json。
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
- 当用户环境中出现因本 skill 设计缺陷导致的 bug 时,优先使用
bensz-collect-bugs按规范记录到~/.bensz-skills/bugs/,严禁直接修改用户本地 Claude Code / Codex 中已安装的 skill 源码。 - 若 AI 仍可通过 workaround 继续完成用户任务,应先记录 bug,再继续完成当前任务。
- 当用户明确要求“report bensz skills bugs”等公开上报动作时,调用本地
gh与bensz-collect-bugs,仅上传新增 bug 到huangwb8/bensz-bugs;不要 pull / clone 整个 bug 仓库。
准备
- 记录主题、档位、字数/参考范围与输出目录。
- 先读取
references/ai_query_generation_prompt.md,生成查询 JSON。公开 schema 支持以下三种形态:{"queries": [{"query": "...", "rationale": "..."}]}[{"query": "...", "rationale": "..."}]["query 1", "query 2"]
- 剔除空查询后,有效数量必须满足
config.yaml:query_input.min_queries/max_queries(默认 5–25)。 - 已知工作目录时,直接将文件保存到
<work-dir>/input/queries.json,或用--query-file <path>让 runner 将显式输入复制到该位置。工作目录尚未建立时,先运行--prepare-only,填充打印出的input/queries.json,再以--resume ... --resume-from 1继续。 - 开始前优先阅读:
references/ai_query_generation_prompt.mdreferences/ai_scoring_prompt.mdreferences/expert-review-writing.mdreferences/review-tex-section-templates.md- 涉及翻译时再读
references/multilingual-guide.md
多查询检索(调用 research-literature-search)
What ships with it
60 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.
- CHANGELOG.md 86 KB
- config.yaml 15 KB
- examples/longevity-lifestyle-01/longevity_lifestyle_01_review.docx 44 KB
- examples/longevity-lifestyle-01/longevity_lifestyle_01_review.pdf 379 KB
- examples/longevity-lifestyle-01/longevity_lifestyle_01_review.tex 39 KB
- examples/longevity-lifestyle-01/longevity_lifestyle_01_参考文献.bib 65 KB
- examples/longevity-lifestyle-01/longevity_lifestyle_01_工作条件.md 5.2 KB
- examples/longevity-lifestyle-01/longevity_lifestyle_01_验证报告.md 1.6 KB
- examples/longevity-lifestyle-01/references.bib 65 KB
- latex-template/gbt7714-nsfc.bst 142 KB
- latex-template/nature-reviews-template.tex 2.7 KB
- qa/test_resume_state.py 2.6 KB runs code
- qa/test_workspace_layout.py 6.8 KB runs code
- README.md 21 KB
- references/✅_update_complete_checklist.md 664 B
- references/ai_query_generation_prompt.md 1.3 KB
- references/ai_scoring_prompt.md 2.4 KB
- references/development-validation-guide.md 1.1 KB
- references/expert-review-writing.md 1.8 KB
- references/mcp-literature-search-engines.md 1.0 KB
- references/multilingual-guide.md 1.2 KB
- references/relevance-scoring-notes.md 1.1 KB
- references/review_example_01.pdf 4561 KB
- references/review-tex-section-templates.md 1.4 KB
- references/skill_update_ai_scoring.md 603 B
- references/v3.0_ai_scoring_summary.md 524 B
- references/validation_feng_zhang_crispr_cong2013_gold.json 10 KB
- requirements.txt 73 B
- scripts/.systematic-literature-review/cost/price_config.yaml 2.6 KB
- scripts/api_cache.py 14 KB runs code
- scripts/api_health_monitor.py 2.4 KB runs code
- scripts/build_evidence_cards.py 3.7 KB runs code
- scripts/build_gold_feng_zhang_crispr_cong2013.py 5.7 KB runs code
- scripts/build_reference_bib_from_papers.py 11 KB runs code
- scripts/compile_latex_with_bibtex.py 16 KB runs code
- scripts/config_loader.py 5.2 KB runs code
- scripts/convert_latex_to_word.py 4.2 KB runs code
- scripts/crossref_search.py 1.3 KB runs code
- scripts/dedupe_papers.py 2.2 KB runs code
- scripts/detect_domain.py 11 KB runs code
- scripts/error_handling.py 14 KB runs code
- scripts/exponential_backoff_retry.py 1.7 KB runs code
- scripts/generate_bibtex_from_dois.py 6.3 KB runs code
- scripts/generate_bibtex.py 15 KB runs code
- scripts/generate_validation_report.py 15 KB runs code
- scripts/global_rate_limiter.py 2.2 KB runs code
- scripts/layout_paths.py 2.3 KB runs code
- scripts/multi_language.py 29 KB runs code
- scripts/multi_query_search.py 8.7 KB runs code
- scripts/multi_source_abstract.py 1.2 KB runs code
- scripts/openalex_search.py 1.6 KB runs code
- scripts/organize_run_dir.py 4.4 KB runs code
- scripts/path_scope.py 6.7 KB runs code
- scripts/pipeline_cost.py 16 KB runs code
- scripts/pipeline_cost.yaml 2.6 KB
- scripts/pipeline_runner.py 74 KB runs code
- scripts/plan_word_budget.py 14 KB runs code
- scripts/progress_utils.py 12 KB runs code
- scripts/prompt_templates.py 16 KB runs code
- scripts/provider_detector.py 3.4 KB runs code
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.
- 4d ago Changed · -18 lines f2223b8e8278
- 7d ago Changed · +13 lines 164dffac11b6
- 10d ago Changed · +18 lines · -40 tokens per session 100d0c6b05e8
- 13d ago First seen · 217 lines · 167 tokens per session scan A decdf862ecad
research-literature-review is a skill published in the GitHub repository huangwb8/ChineseResearchLaTeX (2,726 stars, last pushed yesterday), licensed MIT. It adds 127 tokens to every session and 4,184 once invoked, about $0.0006 per session on Opus 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
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
clipboard
Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".
neo4j-modeling-skill
Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…
git-commit
A Git assistant for reviewing local changes and creating conventional commit messages, which are standardized summaries of code changes. It can also run Git hooks and push the commit.