关于
This skill enables developers to create parameterized Quarto or R Markdown reports that generate multiple variations from a single template. It covers defining parameters, programmatic rendering, and batch generation for automated workflows. Use it for producing department-specific reports, client-customized outputs, or automating recurring reports with different inputs.
快速安装
Claude Code
推荐npx skills add pjt222/agent-almanac -a claude-code/plugin add https://github.com/pjt222/agent-almanacgit clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/build-parameterized-report在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
建參報
造受參之報,自一模生多客變。
用
- 為異部、域、期生同報
- 自模造客專報
- 建濾於具子之儀
- 自定期報附異入
入
- 必:報模(Quarto 或 R Markdown)
- 必:參定(名、類、默)
- 可:批生之參值列
- 可:生報之出目
行
一:YAML 定參
Quarto(report.qmd):
---
title: "Sales Report: `r params$region`"
params:
region: "North America"
year: 2025
include_forecast: true
format:
html:
toc: true
---
R Markdown(report.Rmd):
---
title: "Sales Report"
params:
region: "North America"
year: 2025
include_forecast: true
output: html_document
---
得: YAML 頭含 params: 塊附名參,各有正類默值。
敗: 渲敗報「object 'params' not found」→確 params: 塊於 YAML 首縮對。Quarto params 必於 YAML 頂,非 format: 下嵌。
二:碼中用參
```{r}
#| label: filter-data
data <- full_dataset |>
filter(region == params$region, year == params$year)
nrow(data)
```
## Overview for `r params$region`
This report covers the `r params$region` region for `r params$year`.
```{r}
#| label: forecast
#| eval: !expr params$include_forecast
# This chunk only runs when include_forecast is TRUE
forecast_model <- forecast::auto.arima(data$sales)
forecast::autoplot(forecast_model)
```
得: 碼塊以 params$name 引參,條塊以 Quarto #| eval: !expr params$flag。行內 R 表如 `r params$region` 渲動文。
敗: params$name 返 NULL→驗參名於 YAML 與碼全合(區大小)。察默值類正。
三:以客參渲
單渲:
# Quarto
quarto::quarto_render(
"report.qmd",
execute_params = list(region = "Europe", year = 2025)
)
# R Markdown
rmarkdown::render(
"report.Rmd",
params = list(region = "Europe", year = 2025),
output_file = "report-europe-2025.html"
)
得: 單報以客參值成渲,覆 YAML 默。出檔於所述徑造。
敗: Quarto 渲敗→察 quarto CLI 已裝且於 PATH。R Markdown 敗→驗 rmarkdown 已裝。確參名於 execute_params(Quarto)或 params(R Markdown)合 YAML 定。
四:批渲多報
regions <- c("North America", "Europe", "Asia Pacific", "Latin America")
years <- c(2024, 2025)
# Generate all combinations
combinations <- expand.grid(region = regions, year = years, stringsAsFactors = FALSE)
# Render each
purrr::pwalk(combinations, function(region, year) {
output_name <- sprintf("report-%s-%d.html",
tolower(gsub(" ", "-", region)), year)
quarto::quarto_render(
"report.qmd",
execute_params = list(region = region, year = year),
output_file = output_name
)
})
得: 每域年組一 HTML。
敗: 察參名於 YAML 與碼全合。確諸參值有效。
五:加參驗
#| label: validate-params
stopifnot(
"Region must be a valid region" = params$region %in% valid_regions,
"Year must be numeric" = is.numeric(params$year),
"Year must be reasonable" = params$year >= 2020 && params$year <= 2030
)
得: 驗碼塊於每渲始行,若參出範或類誤則以清誤止。
敗: stopifnot() 生無益訊→換顯 if (!cond) stop("message") 呼以清診。
六:組出
# Create output directory
output_dir <- file.path("reports", format(Sys.Date(), "%Y-%m"))
dir.create(output_dir, recursive = TRUE, showWarnings = FALSE)
# Render with output path
quarto::quarto_render(
"report.qmd",
execute_params = list(region = region),
output_file = file.path(output_dir, paste0("report-", region, ".html"))
)
得: 出檔書於日戳子目附述名(如 reports/2025-06/report-europe.html)。
敗: dir.create() 敗→察父目存且可書。Windows 上驗徑長不過 260 字。
驗
- 報以默參渲
- 報以每組客參渲
- 參處前驗
- 出檔命述
- 條段依參正渲
- 批生於諸組完
忌
- 參名不合:YAML 名必全合碼
params$name引 - 類強轉:YAML 或解
year: 2025為整,而碼候字元。必顯。 - 條評:Quarto 用
#| eval: !expr params$flag,非eval = params$flag - 檔覆:無唯出名→每渲覆前
- 批記:久批或積記。宜用
callr::r()為隔。
參
create-quarto-report— 基 Quarto 文設generate-statistical-tables— 適參之表format-apa-report— 參化學術報
GitHub 仓库
Frequently asked questions
What is the build-parameterized-report skill?
build-parameterized-report is a Claude Skill by pjt222. Skills package instructions and resources that Claude loads on demand, so Claude can perform build-parameterized-report-related tasks without extra prompting.
How do I install build-parameterized-report?
Use the install commands on this page: add build-parameterized-report to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.
What category does build-parameterized-report belong to?
build-parameterized-report is in the Meta category, tagged automation and design.
Is build-parameterized-report free to use?
Yes. build-parameterized-report is listed on AIMCP and free to install. It runs inside Claude, so no separate service account is required to use the skill itself.
相关推荐技能
Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。
该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。
SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。
