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-explain-figuresgit 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-explain-figures)<a href="https://agentmods.dev/skills/huangwb8/chineseresearchlatex/paper-explain-figures"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/paper-explain-figures/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-explain-figures"><img src="https://agentmods.dev/badge/skills/huangwb8/chineseresearchlatex/paper-explain-figures.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 139 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00160 | $0.01984 |
| Opus 5 | $0.00080 | $0.00992 |
| Sonnet 5 | $0.00032 | $0.00397 |
| Haiku 4.5 | $0.00016 | $0.00198 |
Grade C, and why
paper-explain-figures scanned grade C with 1 finding 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 3d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/paper-explain-figures How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
paper-explain-figures
对用户提供的 1 张或多张论文 Figure：
- 将 Figure 转为
.jpg（用于视觉理解；转换失败则保留原图并显式说明） - 在 Figure 附近自动检索“生成该图的源代码”（可能找不到；找不到则为
NULL） - 综合三类信息输出可读性强的报告：
- 理解 1：视觉理解（从 jpg/原图直接读图）
- 理解 2：源代码理解（以代码为准；代码决定图的真实含义）
- 理解 3：用户人工解读（帮助猜测用户关注点；可能有误）
输入
用户会输入 1 个或多个信息：
- 1 个或多个 figure 文件的绝对路径
- 可选：对 figure 的人工解读（全局或按 figure 分配）
- 可选：用户显式给出源代码文件绝对路径（优先作为“候选入口”）
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
- 因本 skill 设计缺陷导致的 bug，先用
bensz-collect-bugs规范记录到~/.bensz-skills/bugs/，不要直接修改用户本地已安装的 skill 源码；若有 workaround，先记 bug，再继续完成任务。 - 只有用户明确要求“report bensz skills bugs”等公开上报时，才用本地
gh上传新增 bug 到huangwb8/bensz-bugs；不要 pull / clone 整个仓库。
文件位置： xxx 源代码： xx.R 第xxx-xxx行
图表核心含义
...
变量定义
| 元素 | 定义 |
|---|---|
| ... | ... |
解读要点
- ...
- ...
解释
...
科学价值
...
为保证“每张图的解读相互独立”，本 skill 采用 worker 脚本在 shell 中启动独立进程执行：
- `codex exec "..."`（推荐：更容易做本地文件读取 + 视觉理解）
- `claude -p "..."`（可选）
并发上限默认 **3**（可在 `paper-explain-figures/config.yaml` 调整）。
在当前目录运行（推荐，产物会落到当前目录与 `.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/paper-explain-figures/`）：
```bash
python3 paper-explain-figures/scripts/paper_explain_figures.py \
--fig /abs/path/to/figure1.png \
--fig /abs/path/to/figure2.pdf \
--note "你对这些图的关注点/背景解释（可选）"
如果该 skill 已做系统级安装（路径因平台而异，以下仅示例）：
python3 ~/.codex/skills/paper-explain-figures/scripts/paper_explain_figures.py --fig /abs/path/to/figure.png
常用参数（按需）：
# 启用并行（默认串行，减少 API 限流/封禁风险）
python3 paper-explain-figures/scripts/paper_explain_figures.py --fig /abs/path/to/figure.png --parallel
# 并发上限（默认 3；也可改 config.yaml:defaults.max_parallel）
python3 paper-explain-figures/scripts/paper_explain_figures.py --fig /abs/path/to/figure.png --parallel --max-parallel 3
# 指定 runner（codex/claude/local）
python3 paper-explain-figures/scripts/paper_explain_figures.py --fig /abs/path/to/figure.png --runner codex
⚠️ 安全提示：--runner shell 已禁用，因为它无法对“.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/paper-explain-figures 之外绝不泄露中间文件”提供严格保证。
在触发目录执行：
rm -rf .bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/paper-explain-figures
输出
- 最终报告：默认输出到当前工作目录
paper-explain-figures_report.md - 所有中间文件与日志：落到
.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/paper-explain-figures/（按 run/job 分目录保存）
每张图在同一个 Markdown 文件中以 ## 级标题分隔：
What ships with it
5 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.
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.
- 3d ago Changed · +8 lines 1a3c579c8ad8
- 11d ago First seen · 141 lines · 160 tokens per session scan C 1e1d03ddfc8f
paper-explain-figures is a skill published in the GitHub repository huangwb8/ChineseResearchLaTeX (2,721 stars, last pushed 3d ago), licensed MIT. It adds 160 tokens to every session and 1,984 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agricultural-sciences-professor
Use when a task needs the judgment of a tenure-track or tenured Agricultural Sciences faculty member at a land-grant university — deciding whether to submit a grant this cycle versus wait, allocating time across the teaching/research/extension appointment split, diagnosing a stalled graduate student or field trial, or…
biology-professor
Use when a task needs the judgment of a Biology Professor at a research university — writing or defending an NIH/NSF grant budget, deciding authorship order on a paper, navigating an IACUC or biosafety protocol, mentoring a PhD student through a stalled project, or converting a course when active-learning data doesn't…
chemistry-teacher-postsecondary
Use when a task needs the judgment of a Postsecondary Chemistry Teacher — grading a lab report where the numeric result misses the "expected" value but the methodology is sound, distinguishing a conceptual misunderstanding from an arithmetic slip on a problem set, deciding how much procedural freedom to give students…
results-analysis
This skill should be used when the user asks to "analyze experimental results", "run strict statistical analysis", "compare model performance", "generate scientific figures", "check significance", "do ablation analysis", or mentions interpreting experiment data with rigorous statistics and visualization. It focuses on…
nature-response
Draft, audit, or revise point-by-point reviewer response letters for Nature-family manuscript revisions. Use when the user provides reviewer comments, editor decision letters, revision notes, response drafts, or asks how to respond to major/minor revision requests, rebuttal letters, response to reviewers, peer-review…
obsidian-literature-workflow
Use this skill for project-scoped literature review built on Sources/Papers, with synthesis landing in Knowledge, writing handoff in Writing, and the default literature canvas under Maps/literature.canvas.