What makes Data Cleaning and Statistical Analysis Skill notable?

1.1K downloads. Trust evidence available

How should Data Cleaning and Statistical Analysis Skill be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Data Cleaning and Statistical Analysis Skill

Provides data cleaning, quality checks, statistical test selection, analysis, and academic interpretation for quantitative behavioral and experimental datasets. Skill: Data Cleaning and Statistical Analysis Skill Owner: scc-nyy Summary: Provides data cleaning, quality checks, statistical test selection, analysis, and academic interpretation for quantitative behavioral and experimental datasets. Tags: latest:1.0.0 Version history: v1.0.0 | 2026-05-27T06:06:21.060Z | auto Initial release of the Data Cleaning and Statistical Analysis Skill: - Supports data cleaning, validation,

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

1.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.0release · observed May 27, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s179vtwr780g2tqjavbgxdbxex87gynh:data-cleaning-and-statistical-analysis-skill

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-scc-nyy-data-cleaning-and-statistical-analysis-skill/snapshot"

Documentation

CLAWHUB

8,078 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

# Data Cleaning and Statistical Analysis Skill

## Purpose

This skill supports data cleaning, quality checking, statistical analysis, and academic interpretation of quantitative datasets. It is especially useful for experimental psychology, clinical research, behavioral science, education research, questionnaire studies, and project-based data analysis.

## When to Use

Use this skill when the user needs help with:

- Cleaning raw CSV, Excel, SPSS-exported, PsychoPy, PsychoJS, or online experiment data.
- Checking whether behavioral data are valid or usable.
- Identifying missing values, duplicate rows, abnormal reaction times, impossible responses, or coding problems.
- Splitting or merging datasets.
- Creating derived variables such as accuracy, mean reaction time, omission errors, commission errors, learning scores, block-level performance, or change scores.
- Selecting statistical tests based on research design.
- Running descriptive statistics, t-tests, ANOVA, repeated-measures ANOVA, mixed ANOVA, correlation, regression, chi-square tests, or nonparametric tests.
- Explaining statistical results in academic language.

## Inputs

The user may provide:

- A dataset file such as `.csv`, `.xlsx`, `.sav`, or `.tsv`.
- A description of the study design.
- Variable names and coding rules.
- Grouping information, such as patient group vs healthy control group.
- Experimental condition labels, such as block, trial type, congruent/incongruent, target/non-target, or pre/post.
- Required output format, such as APA style, thesis writing, tables, graphs, or plain-language explanation.

## Core Workflow

### 1. Understand the Research Design

Before analysis, identify:

- Whether the design is between-subjects, within-subjects, mixed, cross-sectional, longitudinal, or pre-post.
- What the independent variables are.
- What the dependent variables are.
- Whether the main research question is group difference, condition difference, association, prediction, or change over time.
- Whether the data come from behavioral tasks, questionnaires, clinical scales, or physiological measures.

### 2. Inspect the Dataset

Check:

- Number of rows and columns.
- Variable names.
- Data types.
- Missing values.
- Duplicate participant IDs.
- Unexpected category labels.
- Range and distribution of key variables.
- Whether trial numbers and block numbers match the intended experimental design.

### 3. Clean the Data

Common cleaning steps include:

- Removing practice trials when formal analysis should only include experimental trials.
- Excluding invalid trials, such as no response, timeout, or incorrect response when reaction time analysis requires correct trials only.
- Filtering implausible reaction times according to task-specific rules.
- Recoding categorical variables.
- Creating participant-level summary scores.
- Calculating condition-level means and accuracy.
- Checking whether each participant has enough valid trials.

### 4. Choose Statistical Tests

Select tests

_meta.json

{
  "ownerId": "kn7bqn4x5hyyadrbad1a45a3kn87hpzr",
  "slug": "data-cleaning-and-statistical-analysis-skill",
  "version": "1.0.0",
  "publishedAt": 1779861981060
}

skill-card.md

## Description:

Provides data cleaning, quality checks, statistical test selection, analysis, and academic interpretation for quantitative behavioral and experimental datasets.

This skill is ready for commercial/non-commercial use.

## Publisher:

[scc-nyy](https://clawhub.ai/user/scc-nyy)

### License/Terms of Use:

MIT-0

## Use Case:

Researchers, students, analysts, and developers use this skill to inspect quantitative datasets, clean common data quality issues, choose suitable statistical tests, and draft academic-style interpretations for behavioral, clinical, education, questionnaire, and experimental studies.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Datasets may contain identifiable clinical, participant, or study data.

Mitigation: Avoid sharing identifiable data unless the current agent environment is approved for that data; prefer de-identified datasets when possible.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/scc-nyy/skills/data-cleaning-and-statistical-analysis-skill)

## Skill Output:

**Output Type(s):** [Text, Markdown, Code, Guidance]

**Output Format:** [Markdown with summaries, tables, statistical explanations, and optional code snippets]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May include data quality summaries, cleaning decisions, exclusion criteria, descriptive-statistics tables, statistical test recommendations, APA-style result writeups, and assumption warnings.]

## Skill Version(s):

1.0.0 (source: server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular