Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Data Analysis & Reference Enrichment

A two-mode skill: a decision-first, five-phase data analysis workflow, plus tooling to enrich or decompose skill/agent reference files.

Data & AnalyticsIntermediate★ 421⑂ 44AI score 7/10Last updated: Sep 19, 2026

What it does

The skill routes your request into one of two modes.

A. Data analysis (5 phases)

  1. FRAME — name the decision, the options, and the default action; "analysis without a decision is arithmetic"
  2. DEFINE — lock metric formulas, populations, windows and segments before loading data
  3. EXTRACT — pandas with a csv.DictReader fallback; quality gates on coverage, time gaps, segment size (30+) and missingness (<20%)
  4. ANALYZE — Wilson score confidence intervals, Bonferroni correction for 6+ comparisons, effect size with base-rate context
  5. CONCLUDE — one-sentence headline, honest limitations, evidence mapped back to the decision

B. Reference enrichment / decomposition

  • Extracts domain-heavy blocks out of a bloated SKILL.md into reference files, with snapshot-and-restore on validation failure
  • Gap analysis → research → compile (max 500 lines/file, do-pairing rule) → two-tier validation → integration

Who it's for

  • Analysts, PMs and growth folks running A/B tests, funnels, cohorts and KPI reporting
  • Teams tired of dashboards that never say what to do next
  • Advanced users maintaining their own Claude skills/agents (Mode B)

Examples

  • "Analyze the A/B test in experiment_results.csv" → conversion delta with Wilson CIs, small segments merged or flagged, recommendation tied to the launch decision
  • "Show monthly signup trend and churn cohorts" → data-quality report first, then a trend-template summary with stated limitations
  • "My SKILL.md is bloated, decompose it" → detects extractable blocks, snapshots the file, moves content into references, restores automatically if validation fails

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/notque/vexjoy-agent/HEAD/skills/analysis/data/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/analysis/data folder from the GitHub repo notque/vexjoy-agent into my ~/.claude/skills/data/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/notque/vexjoy-agent.git /tmp/vexjoy-agent && mkdir -p ~/.claude/skills && cp -r /tmp/vexjoy-agent/skills/analysis/data ~/.claude/skills/data

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repository: git clone https://github.com/notque/vexjoy-agent.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r vexjoy-agent/skills/analysis/data ~/.claude/skills/data
  5. Confirm the bundled docs came along: ls ~/.claude/skills/data/references
  6. For Mode B, keep the repo's scripts/ directory and run Claude Code from the repo root, since the skill calls python3 scripts/*.py.
  7. Restart Claude Code and try: "analyze this CSV for me".
  8. Optional: pip install pandas for richer profiling (the skill falls back to the standard library otherwise).
View source on GitHub ↗License: MIT