skills.rest
shiwenwen
shiwenwenCOMMUNITY
Explore all skills by this author →
GitHub

ha-data-analytics

Analyzes CSV/XLSX data and produces validated local Artifact reports with quality checks.

1.6k|149|Updated Mar 13, 2026
Search Tags:#Report#artifact#CSV#Data Analysis#kpi#Data Quality#metric diagnosis
One-click install
npx skills add https://github.com/shiwenwen/hope-agent --skill ha-data-analytics
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ha-data-analytics
Source: https://github.com/shiwenwen/hope-agent/tree/main/skills/ha-data-analytics
Command: npx skills add https://github.com/shiwenwen/hope-agent --skill ha-data-analytics

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Turning raw CSV/XLSX files into trustworthy, decision-ready analysis usually requires manual data-quality checks, careful metric definitions, and reproducible calculations. This Skill enforces a rigorous local-first workflow that separates facts from interpretation, validates every claim, and packages results as a versioned, shareable offline Artifact instead of an unverifiable chat answer.

Core Features & Use Cases

  • Structured Analysis Workflow: Guides KPI readouts, metric diagnosis, product/business decisions, and data tables through context, sources, quality, analysis, visualization, report, validation, and registration stages.
  • Data Quality & Claim Validation: Runs deterministic checks for freshness, duplicates, grain, denominators, joins, and outliers, and blocks 'ready' status when blocking checks fail.
  • Versioned Artifact Output: Produces the AnalysisArtifactV1 JSON contract with charts, tables, fallbacks, and sources, validated by a bundled Python script and registered via the artifact tool for offline HTML/ZIP/Markdown/PDF export.
  • Use Case: Attach a Q2 activation CSV and ask why activation fell; the Skill decomposes the metric by segment, runs duplicate and denominator checks, recomputes key figures independently, and delivers a validated report Artifact with charts and caveats.

Quick Start

Ask the agent to analyze your attached CSV or XLSX file, diagnose the metric you care about, and create a validated local Artifact report.

Frequently Asked Questions about ha-data-analytics

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I analyze a CSV file and get a shareable report?▼

Attach the CSV file and state the question, audience, and metric definition. The Skill runs data-quality checks, computes results deterministically, and registers a versioned Artifact you can export as HTML, ZIP, Markdown, or PDF.

What data quality checks run before a report is marked ready?▼

Checks cover freshness, schema stability, missingness, duplicates, grain, denominators, joins, coverage, sample size, outliers, and time alignment. Any failed blocking check forces the Artifact status to partial or blocked instead of ready.

Can I use this for KPI dashboards and metric diagnosis?▼

Yes, it supports KPI readouts with target comparisons, metric diagnosis via numerator/denominator decomposition, and dashboard-style Artifacts. Every KPI must expose its numerator, denominator, time window, and refresh time.

Does the analysis require uploading data to the cloud?▼

No, the workflow is local-first: working files and artifact.json stay in the workspace, and the artifact tool copies results into managed local storage. Export to HTML, ZIP, Markdown, or PDF is an owner action and never implies public hosting.

What happens when data is missing or ambiguous?▼

The Skill never invents rows, definitions, or sources. Missing essentials downgrade the Artifact to partial or blocked status, and ambiguous metric definitions block the work until resolved.

How is the analysis artifact validated before delivery?▼

A bundled Python script validates the artifact.json against the AnalysisArtifactV1 schema, checking source hashes, dataset bounds, chart bindings, fallbacks, and claim validations. Key figures are also recomputed independently before registration.

Related Skills

Explore More Data & Analytics Skills→
gztcodegztcode

lark-sheets

Create, manipulate, and export Lark spreadsheets as xlsx or csv files.

Community
Intermediate
coalesce-labscoalesce-labs
20

meeting-cleanup

Batch process meeting transcripts into summaries, decisions, and action items with owners.

Official
Intermediate
wfukatsuwfukatsu
12

research-landscape

Synthesize market data into competitive matrices and Kano classifications.

Community
Advanced
agentic-inagentic-in
577

Jupyter Live Kernel

Run interactive Jupyter notebook sessions with live kernel management.

Official
Intermediate