Is the Explore Data skill free?

Yes. The skill itself is free from HalalifyMusic/fable-mode. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Explore Data SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.

How do I install Explore Data?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Explore Data with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Explore Data

Profiles a table or file end-to-end: nulls, cardinality, outliers, and next-step analyses.

by HalalifyMusic · HalalifyMusic/fable-mode

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 16, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · fa55e69

Run on a deliberately messy 10-row orders.csv, it caught every planted issue (USA/usa casing, a -15 refund, a 999999/'TBD' placeholder row, a duplicate C004 order, a 2099 future date, a null customer_id) and packaged it with severity bands and 5 concrete follow-up analyses — the unguided baseline caught the same issues but as an unstructured list with no severity or next-step framing.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 5/5

What Explore Data does

Generates a structured data profile for a table or uploaded file — row/column counts, per-column null rates and cardinality, numeric/date/string distributions, and a heuristic data-quality scan (placeholders, duplicates, case inconsistency, future dates). Triggers when encountering a new dataset, checking quality before analysis, or deciding which dimensions/metrics to explore next.

How to install Explore Data

git clone https://github.com/HalalifyMusic/fable-mode.git
mkdir -p ~/.claude/skills
cp -r fable-mode/skills/explore-data ~/.claude/skills/explore-data

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Explore Data

/explore-data Profiles a table or file end-to-end: nulls, cardinality, outliers, and next-step analyses.

It also activates on plain-language prompts like these:

Profile this orders.csv file for nulls, outliers, and quality issues
What should I check before analyzing this new dataset?
Scan this table for duplicates, placeholders, and future dates

Frequently asked questions

Is the Explore Data skill free?: Yes. The skill itself is free from HalalifyMusic/fable-mode. SkillProof publishes the install command and an independent test verdict at no cost.
Does Explore Data work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. Run on a deliberately messy 10-row orders.csv, it caught every planted issue (USA/usa casing, a -15 refund, a 999999/'TBD' placeholder row, a duplicate C004 order, a 2099 future date, a null customer_id) and packaged it with severity bands and 5 concrete follow-up analyses — the unguided baseline caught the same issues but as an unstructured list with no severity or next-step framing.
What is the Explore Data SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
How do I install Explore Data?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Explore Data with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.