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/skills --skill bensz-rmd-rulesgit clone --depth 1 https://github.com/huangwb8/skillsWrote 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/skills/bensz-rmd-rules)<a href="https://agentmods.dev/skills/huangwb8/skills/bensz-rmd-rules"><img src="https://agentmods.dev/badge/skills/huangwb8/skills/bensz-rmd-rules/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/skills/bensz-rmd-rules"><img src="https://agentmods.dev/badge/skills/huangwb8/skills/bensz-rmd-rules.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 | $0.00053 | $0.10758 |
| Opus 5 | $0.00026 | $0.05379 |
| Sonnet 5 | $0.00011 | $0.02152 |
| Haiku 4.5 | $0.00005 | $0.01076 |
Grade A, and why
bensz-rmd-rules 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 5d 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 — 659 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bensz-rmd-rules
目标
规范 AI 开发 R Markdown 分析脚本的行为准则。当用户要求"写 Rmd 分析"、"开发 R 脚本"、"做数据分析"时触发。核心原则：遵循主业与副业分离架构（.R 保留完整数据，.Rmd 应用业务阈值），优先使用用户已有 R 包资源；图表默认按 Nature 级别可读性与出版质量生成；专家级解读兼顾弱背景读者，提供四层框架、指标导读与不常用指标首次解释协议；路径验证确保跨平台兼容性。前提：luckyBase 为硬依赖。
流程
输入
输入为项目的 .R/.Rmd 文件、已有 R 包资源、数据字典、分析目标和输出要求；运行前确认 luckyBase::Plus.library() 可用，并读取 config.yaml、模板和与当前分析直接相关的 references。
执行步骤
核心原则概览
| 原则 | 核心要求 |
|---|---|
| 现有资源优先 | 优先使用用户已有的 R 包和函数，不重复造轮子 |
| 人类可读 | 代码简洁优雅，天然适合人类审查 |
| 混合架构 | .R 负责数据处理/计算（保留完整数据），.Rmd 负责可视化/分析（应用业务阈值） |
| 函数分离 | 专用函数脚本 _functions.R，避免污染全局环境 |
| 数据筛选分离 | .R 不应用阈值筛选（方便审查原始状态），.Rmd 根据业务需求应用阈值（确保分析价值） |
| 不过度保护 | 避免过多防御性代码，以人类为中心 |
| 跨平台兼容 | 代码在 macOS/Linux/Windows 上均可运行，路径使用相对路径 |
| 完整因果链 | 代码前解释"为什么"，结果后解读"意味什么" |
| 分层指标解释 | 默认读者背景较弱；不常用指标先导读、首次详解、后续简写 |
现有资源优先原则
R 包资源清单
优先使用用户已有的 R 包资源。完整包清单详见 [config.yaml:r_packages]，主要包括：
| 包名 | 用途 | 典型场景 |
|---|---|---|
| ccs | 泛癌症基因组分类计算框架 | 癌症分型、亚型分类 |
| GSClassifier | 转录组学综合分类工具 | 基因签名分类、预测模型 |
| lucky | 常规 R 函数集合 | 生存分析、差异表达、可视化 |
| luckyBase | lucky 系列基础辅助包 | 包管理、基础工具函数 |
| luckyExperiment | 生物学实验数据处理 | 实验数据处理 |
| luckyGEO | GEO 数据下载与处理 | GEO 数据下载、处理 |
| luckyModel | 第三方生物信息学模型 | 模型集成、预测 |
luckyBase 强制要求（硬性规定）
⚠️ 关键 1：luckyBase 必须强制加载
luckyBase 是本技能的核心依赖，必须强制加载，不得跳过或提供降级方案。
⚠️ 关键 2：必须使用 luckyBase::Plus.library 自动安装/加载包
# 正确做法（强制）
luckyBase::Plus.library("ggplot2")
luckyBase::Plus.library("DT")
# 错误做法（禁止）
library(ggplot2) # 禁止直接使用 library()
if (!requireNamespace("ggplot2", quietly = TRUE)) { # 禁止手动检查
install.packages("ggplot2")
}
⚠️ 关键 3：必须使用 luckyBase::convert 进行基因 ID 转换
在涉及基因 ID 转换的场景（如 ENSEMBL → SYMBOL、ENTREZID → SYMBOL），必须使用 luckyBase::convert() 函数：
# 正确做法（强制）
gene_symbols <- luckyBase::convert(
ids = gene_ensembl_ids,
from_type = "ENSEMBL",
to_type = "SYMBOL",
organism = "human"
)
# 错误做法（禁止）
# 禁止使用 biomaRt、AnnotationDbi 等其他包手动转换
# 禁止硬编码 ID 映射表
理由：
luckyBase::Plus.library()自动处理包的安装和加载，无需手动检查luckyBase::convert()提供统一的基因 ID 转换接口，支持多物种、多 ID 类型- 避免重复造轮子，保持代码简洁
What ships with it
46 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 58 KB
- config.yaml 11 KB
- qa/test_metric_explanation_protocol.py 1.7 KB runs code
- qa/test_toc_hover_stability.py 1010 B runs code
- qa/test_windows_cli_and_dt_helper.py 1.8 KB runs code
- README.md 28 KB
- references/candidate_r.md 2.4 KB
- references/code_block_explanations.md 3.0 KB
- references/code_style_guide.md 5.8 KB
- references/cross_platform.md 3.7 KB
- references/delivery_verification.md 3.6 KB
- references/expert_discussion_template.md 7.3 KB
- references/figure_interpretation_criteria.md 2.3 KB
- references/four_tier_interpretation_framework.md 17 KB
- references/gene_id_guidelines.md 4.8 KB
- references/htmlwidget_visibility_rules.md 2.4 KB
- references/hybrid_architecture_examples.md 2.0 KB
- references/hybrid_architecture_guide.md 5.3 KB
- references/interpretation_narrative_examples.md 5.6 KB
- references/interpretation_templates.md 15 KB
- references/liquid_glass_theme_guide.md 10 KB
- references/metric_explanation_protocol.md 5.8 KB
- references/no_overdefensive_code.md 4.6 KB
- references/numeric_accuracy_verification.md 1.3 KB
- references/plot_language.md 2.7 KB
- references/plot_quality_standards.md 7.0 KB
- references/workflow_checklist.md 3.4 KB
- scripts/bootstrap_liquid_glass.py 3.1 KB runs code
- scripts/check_figure_table_interpretation.py 20 KB runs code
- scripts/check_htmlwidget_visibility.py 10 KB runs code
- scripts/check_interpretation_quality.py 29 KB runs code
- scripts/check_plot_readability.R 11 KB
- scripts/check_rmd_template_yaml.py 3.3 KB runs code
- scripts/validate_paths.R 7.3 KB
- templates/00.Environment.R 4.7 KB
- templates/complexheatmap_template.R 2.8 KB
- templates/datatables_helper.R 1.5 KB
- templates/functions_template.R 1.2 KB
- templates/liquid_glass_lightbox.html 23 KB
- templates/liquid_glass_theme.css 32 KB
- templates/nature_colors.R 356 B
- templates/nature_theme.R 2.6 KB
- templates/plot_delivery_helpers.R 7.0 KB
- templates/plotly_template.R 1.7 KB
- templates/R_data_template.R 2.1 KB
- templates/Rmd_template.Rmd 11 KB
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.
- 5d ago Changed · +9 lines · -104 tokens per session 909c9ba4af6b
- 6d ago Changed · +30 lines ac03599679ab
- 11d ago First seen · 620 lines · 157 tokens per session scan A dde4962045fb
bensz-rmd-rules is a skill published in the GitHub repository huangwb8/skills (48 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 10,758 once invoked, about $0.0003 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
boostprompt
Use quando uma necessidade de negócio ou técnica precisar de discovery estruturado em pt-BR e de um prompt de implementação autocontido.
voice-calibration
Learns a user's personal writing and speaking style through interactive writing prompts, then generates a reusable voice profile. Use when the user says "learn my writing style," "write like me," "capture my voice," "voice calibration," "mimic my tone," "my writing style," or wants AI to match their personal…
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
baoyu-diagram
Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system…
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
agent-wiki
Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.