Explore

Find agent skills by outcome

15,097 skills indexed with the new KISS metadata standard.

Showing 24 of 15,097Categories: Data & Insights, Coding & Debugging, Data, Openclaw
Data
PromptBeginner5 minmarkdownQuality: 28

Ultra-micro Functional Analyst Prompt

Act as a senior functional analyst: work in phases, state all assumptions, preserve existing behaviour, no UML/Gherkin/specs without explicit approval, be direct and analytical.

0
Data
PromptBeginner5 minmarkdownQuality: 24

Small Functional Analyst mode

Functional Analyst Mode

0
Data
PromptBeginner5 minmarkdownQuality: 28

Functional Analyst

Act as a Senior Functional Analyst. Your role prioritizes correctness, clarity, traceability, and controlled scope, following UML2, Gherkin, and Agile/Scrum methodologies. Below are your core principl...

0
Data
PromptBeginner5 minmarkdownQuality: 28

Probably the most useful standalone thing here. Source it and run `check_data(df)` on any data frame to get a formatted report of dimensions

NA counts

0
Data
PromptBeginner5 minmarkdownQuality: 24

│ ├── statistics.md # Hypothesis tests

distributions

0
Data
PromptBeginner5 minmarkdownQuality: 24

│ ├── visualization.md # par

layout

0
Data
PromptBeginner5 minmarkdownQuality: 24

│ ├── data-wrangling.md # Subsetting traps

apply family

0
Coding & Debugging
PromptBeginner5 minmarkdownQuality: 28

I'm a political science PhD candidate who uses R regularly but would never call myself *an R person*. I needed a Claude Code skill for base R — something without tidyverse

without ggplot2

0
Data
PromptBeginner5 minmarkdownQuality: 24

# boxplot(%s ~ %s

data = df

0
Data
PromptBeginner5 minmarkdownQuality: 24

# fit_aov <- aov(%s ~ %s

data = df)

0
Data
PromptBeginner5 minmarkdownQuality: 24

fit <- lm(%s ~ %s

data = df)

0
Data
PromptBeginner5 minmarkdownQuality: 24

# t.test(%s ~ %s

data = df)

0
Data
PromptBeginner5 minmarkdownQuality: 24

if (is.null(data_file)) data_file <- paste0(project_name

.csv)

0
Data
PromptBeginner5 minmarkdownQuality: 24

check_data <- function(df

top_n_levels = 8) {

0
Data
PromptBeginner5 minmarkdownQuality: 24

# saveRDS(df

data_clean.rds)

0
Data
PromptBeginner5 minmarkdownQuality: 24

# fit_aov <- aov(outcome_var ~ group_var

data = df)

0
Data
PromptBeginner5 minmarkdownQuality: 24

t.test(outcome_var ~ group_var

data = df)

0
Data
PromptBeginner5 minmarkdownQuality: 24

abline(lm(outcome_var ~ predictor

data = df)

0
Data
PromptBeginner5 minmarkdownQuality: 24

df <- read.csv(your_data.csv

stringsAsFactors = FALSE)

0
Coding & Debugging
PromptBeginner5 minmarkdownQuality: 24

- `arrows`: `code = 1` (head at start)

`code = 2` (head at end

0
Data
PromptBeginner5 minmarkdownQuality: 24

- Formula interface: `pairs(~ var1 + var2 + var3

data = df)`.

0
Data
PromptBeginner5 minmarkdownQuality: 24

- Formula interface: `cor.test(~ x + y

data = df)` — note the `~` with no LHS.

0
Data
PromptBeginner5 minmarkdownQuality: 28

- Default bandwidth: `bw = nrd0` (Silverman's rule of thumb). For multimodal data

consider `SJ` or `bcv`.

0
Data
PromptBeginner5 minmarkdownQuality: 28

- Default kernel: `gaussian`. Range of density extends beyond data range (controlled by `cut`

default 3 bandwidths).

0