AgentSkillify

Explore

Find agent skills by outcome

6,591 skills indexed with the new KISS metadata standard.

Showing 24 of 6,591Categories: Communication, Research & Learning, Data
Data
PromptBeginner5 minmarkdown

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 minmarkdown

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 minmarkdown

│ ├── visualization.md # par

layout

0
Data
PromptBeginner5 minmarkdown

│ ├── statistics.md # Hypothesis tests

distributions

0
Data
PromptBeginner5 minmarkdown

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

apply family

0
Data
PromptBeginner5 minmarkdown

# boxplot(%s ~ %s

data = df

0
Data
PromptBeginner5 minmarkdown

# fit_aov <- aov(%s ~ %s

data = df)

0
Data
PromptBeginner5 minmarkdown

fit <- lm(%s ~ %s

data = df)

0
Data
PromptBeginner5 minmarkdown

# t.test(%s ~ %s

data = df)

0
Data
PromptBeginner5 minmarkdown

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

.csv)

0
Data
PromptBeginner5 minmarkdown

check_data <- function(df

top_n_levels = 8) {

0
Data
PromptBeginner5 minmarkdown

# saveRDS(df

data_clean.rds)

0
Data
PromptBeginner5 minmarkdown

# fit_aov <- aov(outcome_var ~ group_var

data = df)

0
Data
PromptBeginner5 minmarkdown

t.test(outcome_var ~ group_var

data = df)

0
Data
PromptBeginner5 minmarkdown

abline(lm(outcome_var ~ predictor

data = df)

0
Data
PromptBeginner5 minmarkdown

df <- read.csv(your_data.csv

stringsAsFactors = FALSE)

0
Data
PromptBeginner5 minmarkdown

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

data = df)`.

0
Data
PromptBeginner5 minmarkdown

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

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

0
Data
PromptBeginner5 minmarkdown

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

default 3 bandwidths).

0
Data
PromptBeginner5 minmarkdown

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

consider `SJ` or `bcv`.

0
Data
PromptBeginner5 minmarkdown

- For composite hypotheses (parameters estimated from data)

p-values are **conservative** (too large). Use `dgof` or `ks.test` with `exact = NULL` for discrete distributions.

0
Data
PromptBeginner5 minmarkdown

- Returns a matrix of p-values

not test statistics.

0
Data
PromptBeginner5 minmarkdown

- If data fits too exactly (no residual noise)

convergence check fails — use `control = list(scaleOffset = 1)` or jitter data.

0
Data
PromptBeginner5 minmarkdown

- Returns data frame with `size`

`isdir`

0