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-ideaWrote 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-idea)<a href="https://agentmods.dev/skills/huangwb8/chineseresearchlatex/research-idea"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/research-idea/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-idea"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/research-idea.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 | $0.00115 | $0.03122 |
| Opus 5.5 | $0.00046 | $0.01249 |
| Sonnet 5.5 | $0.00023 | $0.00624 |
| Haiku 4.5 | $0.00012 | $0.00312 |
Grade A, and why
research-idea 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Idea
目标
从用户资料与可审计文献证据中建立研究脉络，提出科学问题和可证伪假设，分开判断科学价值、可信度与近期投入，形成有界推荐、当前范围内无合格候选或证据不足结论。候选必须来自前置调查，不得仅凭资料臆造。
相邻 Skill：research-topic-extractor 提取检索主题；research-literature-search 生成 rls.v1 候选与 provenance；research-literature-radar 建立全量 landscape；research-literature-interpretation 逐篇解读；parallel-vibe 独立审查。完整综述使用 research-literature-review，实验/分析计划使用 research-plan。
流程
输入
- 必需：文本、文件/目录、URL、论文线索、实验现象、仓库或 PR 背景中的至少一种。
- 可选：研究目标、时间/资源边界、输出路径、审查轮数和人数。
- 默认报告目录：
./docs/ideas/；默认任务区：./.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/research-idea/。 - 默认审查 3 轮、每轮 3 人；论文解读最多并行 3 个任务。
执行步骤
-
启动与归纳。 阅读 运行说明，锁定任务目录，只用
scripts/start_workflow.py建立 BSK 身份；仅当status=initialized且 run/visit/attempt 非空时开始 literature 阶段。摘要目标贡献、服务的问题/决策和资源状态，只保存必要的脱敏内容。用research-topic-extractor生成主题、5–10 个英文关键词、2–5 个核心问题，并在input/theme.json引用原始产物。 -
文献证据。 用
research-literature-radar消费 Search manifest 和全部 canonical 候选，生成逐条覆盖的 landscape 与 hash/计数摘要；未全量对账或 hash 漂移时停止。对入选论文调用research-literature-interpretation：一任务一论文、最多并行 3 个、不嵌套；只有可对账的宿主回执才称“独立 agent”。全文优先，只有摘要时收缩结论；记录稳定来源、证据深度/范围、问题、方法、结果、限制和支持/反驳关系。 -
研究 map。 按 研究综合指南 写
output/research-map.md，包含研究线比较、landscape 覆盖、关键关系、稳定 O 机会编号、R 核心论文锚点和 Search record ID。说明对象/测量、前提、最强反例及所需辨别证据；来源关系与“待验证综合判断”分开。时间先后、术语相似或测量差异不自动证明继承、因果或矛盾。 -
生成与筛选候选。 以用户摘要、主题、证据和 map 为共同事实，用
parallel-vibe n=3独立生成候选；首轮不预设最佳方向，agent 不互读草稿。初始探索 3–7 个，最终可保留一个或零个。按 报告模板 写问题、假设、关键预测、反证、价值/非平凡性、创新/颠覆潜力、最近工作增量、最强替代方向、可信度、投入和脉络依据；工作证据用 O/R 编号，正式报告用 O 与学术引注。定义性假设、无知识增量、方法名代替机制或无意义场景迁移优先重构/淘汰。全部不合格时最多用新证据或新解释重新探索一次；资料不足保持insufficient。 -
候选级查新。 对每个拟保留候选生成
candidates/Cx/theme.json，围绕直接近邻、等价假设、反方证据和适用边界提出 5–25 条查询，调用research-literature-search生成独立rls.v1bundle。逐条消费 canonical 候选，按 查新指南 保存novelty/Cx/novelty-decision.json。摘要可排除明显不等价工作；决定新颖性的近邻才升级全文。决定性近邻未核验时可带缺口进入审查，但scientific_evidence_sufficient=false、claim_eligible=false。淘汰项记录未执行查新的原因，不伪造结果。
What ships with it
26 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 13 KB
- config.yaml 5.9 KB
- README_EN.md 7.9 KB
- README.md 6.7 KB
- references/agent-review-prompt.md 2.2 KB
- references/novelty-check.md 3.9 KB
- references/report-template.md 7.7 KB
- references/research-synthesis.md 6.4 KB
- references/runtime-guide.md 7.2 KB
- references/states/candidates/STATE.md 2.7 KB
- references/states/completed/STATE.md 1.8 KB
- references/states/index.json 1.9 KB
- references/states/literature/STATE.md 2.3 KB
- references/states/reporting/STATE.md 2.7 KB
- references/states/review/STATE.md 2.7 KB
- references/verifiers/hypothesis-merit/VERIFIER.md 5.9 KB
- references/verifiers/index.json 1.5 KB
- references/verifiers/stage-readiness/scripts/evidence_consistency.py 1.9 KB runs code
- references/verifiers/stage-readiness/VERIFIER.md 8.4 KB
- scripts/check_completion.py 41 KB runs code
- scripts/check_dependencies.py 3.1 KB runs code
- scripts/edge_rules.py 11 KB runs code
- scripts/init_workspace.py 8.2 KB runs code
- scripts/phase_entry.py 26 KB runs code
- scripts/start_workflow.py 12 KB runs code
- scripts/validate_report.py 21 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.
- 1mo ago Changed 170018478cb6
- 1mo ago Changed · -103 lines 964d397fcd34
- 1mo ago Changed · +2 lines 72f1aae1016a
- 1mo ago Changed · +1 lines ed24bbd10613
- 1mo ago Changed dc11900ec934
- 1mo ago Changed · +14 lines b64eebd09753
- 1mo ago Changed · -8 lines · -28 tokens per session ff3825005df7
- 1mo ago Changed · +29 lines · +12 tokens per session dd0f936ed1c6
- 1mo ago Changed · +2 lines · -49 tokens per session 6a4b4afb4ed1
- 1mo ago First seen · 170 lines · 180 tokens per session scan A de8eb3883bfd
research-idea is a skill published in the GitHub repository huangwb8/ChineseResearchLaTeX (2,980 stars, last pushed 10d ago), licensed MIT. It adds 115 tokens to every session and 3,122 once invoked, about $0.0005 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.