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-searchWrote 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-search)<a href="https://agentmods.dev/skills/huangwb8/chineseresearchlatex/research-literature-search"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/research-literature-search/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-search"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/research-literature-search.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 | $0.00109 | $0.01830 |
| Opus 5 | $0.00055 | $0.00915 |
| Sonnet 5 | $0.00022 | $0.00366 |
| Haiku 4.5 | $0.00011 | $0.00183 |
Grade A, and why
research-literature-search 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Literature Search
定位与边界
本 Skill 是文献检索生产者：把主题和 5–25 条查询转换为一个可复核的候选文献 bundle。它只负责召回、字段规范化、canonical 去重、来源审计和可选摘要补全；评分、纳入/排除判断、子主题、参考文献配额、正文和导出交给下游 Skill。
research-literature-review 必须通过本 Skill 的 manifest 和 canonical 候选消费检索结果，不得在阶段 1/2 复制 provider 或再次改变 canonical 去重结果。
输入契约
- 必需：
topic和显式查询 JSON（--query-file/--queries）。支持{"queries": [...]}、对象数组、字符串数组。 - 空查询会剔除；有效查询默认 5–25 条，数量不满足时 fail-closed。
- 可选：
domain、年份/文献类型/预印本过滤、provider 顺序、每查询/总量上限、scope root。 - 所有输出路径必须位于调用方指定的 scope root 内；不接受路径穿越或 manifest 中的外部绝对路径。
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
# 独立检索，生成 manifest bundle
python3 skills/research-literature-search/scripts/search_runner.py run \
--topic "HER2 antibody-drug conjugates in breast cancer" \
--query-file ./queries.json \
--output-dir ./.bensz-api/search-bundle
# 对选文后的 JSONL 做可选摘要状态整理
python3 skills/research-literature-search/scripts/search_runner.py enrich-abstracts \
--input selected_papers.jsonl --output selected_papers_enriched.jsonl
# 校验交接包（review 消费前必须通过）
python3 skills/research-literature-search/scripts/search_runner.py validate \
--bundle ./.bensz-api/search-bundle
run 默认不对全量候选强制补全。使用 enrich-abstracts 对 selected 或指定子集处理；输出 abstract_status、abstract_provenance、缺失摘要 warning 和统计。综述仍在选文后调用该能力，以保持请求量和选文行为兼容。
输出
每次运行都生成独立目录，manifest.json 是唯一入口：
manifest.json
candidates_raw.jsonl # 脱敏的最小 provider 命中信封
candidates_normalized.jsonl # rls.paper.v1，去重前
candidates_deduped.jsonl # canonical 候选池，下游默认读取
provenance.jsonl # provider/query/rank 到 canonical 的映射
dedupe_map.json # 合并边及 canonical 选择依据
search_log.json # 兼容旧 Search Log 字段的可读日志
候选 schema 版本为 rls.paper.v1，必须有非空 title、字符串数组 authors、identifiers、abstract_status、publication、sources、query_matches 和 quality_warnings；同时在边界生成 doi/abstract/venue/year/url/source 等旧扁平字段。缺失值用 null/[]，不填虚构占位文本。
manifest 的 status 只有三种语义：success（完整成功）、partial_success（仍有可用候选但存在失败/跳过/截断/字段缺失）、failed（输入、路径、provider 或产物不可消费）。research-literature-review 只接受前两者，并校验 artifact hash、schema 和数量。
What ships with it
20 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 1.3 KB
- config.yaml 1017 B
- README.md 3.0 KB
- references/bundle-schema.md 861 B
- references/paper-schema.md 905 B
- references/provider-guide.md 712 B
- requirements.txt 27 B
- scripts/candidate_schema.py 16 KB runs code
- scripts/dedupe_papers.py 10 KB runs code
- scripts/manifest.py 4.1 KB runs code
- scripts/multi_source_abstract.py 1.1 KB runs code
- scripts/normalize_papers.py 4.3 KB runs code
- scripts/providers/__init__.py 298 B runs code
- scripts/providers/crossref.py 737 B runs code
- scripts/providers/openalex.py 1.0 KB runs code
- scripts/providers/semantic_scholar.py 647 B runs code
- scripts/query_contract.py 4.3 KB runs code
- scripts/rls_contract.py 437 B runs code
- scripts/search_runner.py 24 KB runs code
- scripts/validate_bundle.py 6.9 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 · +14 lines 87e9db9cdff0
- 7d ago First seen · 87 lines · 109 tokens per session scan A f616ee05baf7
research-literature-search is a skill published in the GitHub repository huangwb8/ChineseResearchLaTeX (2,726 stars, last pushed yesterday), licensed MIT. It adds 109 tokens to every session and 1,830 once invoked, about $0.0005 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 2026-09-05.
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.