Is the ChatBI MVP Architecture skill free?

Yes. The skill itself is free from yugef3h/leo-skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the ChatBI MVP Architecture SkillProof Score?

9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.

How do I install ChatBI MVP Architecture?

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 ChatBI MVP Architecture 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.

ChatBI MVP Architecture

Reference architecture for building a conversational BI (NL-to-SQL) MVP.

by yugef3h · yugef3h/leo-skills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.6/10
Tested: Jul 16, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · c5c5678

Design task 'wire up NL query to SQL with a semantic layer' got a shallow direct-LLM-to-SQL answer from an unguided baseline; the skill forced the two-stage S2SQL-then-deterministic-translator split (with a corrector chain and self-consistency voting) that concretely blocks the table-name-hallucination failure mode the naive design is prone to.

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 9/10
Docs & honesty 5/5

What ChatBI MVP Architecture does

Walks through a 5-layer ChatBI architecture (NL2SQL via a semantic S2SQL layer, multi-turn dialogue, RAG schema recall, auto-charting, attribution analysis) modeled on Tencent's SuperSonic project. Triggers when the user wants to build a natural-language-to-SQL analytics tool or reference SuperSonic's design.

How to install ChatBI MVP Architecture

git clone https://github.com/yugef3h/leo-skills
mkdir -p ~/.claude/skills
cp -r leo-skills/skills/chatbi-mvp ~/.claude/skills/chatbi-mvp

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

Commands — how to trigger ChatBI MVP Architecture

/chatbi-mvp Reference architecture for building a conversational BI (NL-to-SQL) MVP.

It also activates on plain-language prompts like these:

Design a natural-language-to-SQL pipeline like Tencent's SuperSonic
How should I architect a conversational BI tool with a semantic layer?
Help me avoid table-name hallucination in my NL2SQL chatbot design

Frequently asked questions

Is the ChatBI MVP Architecture skill free?: Yes. The skill itself is free from yugef3h/leo-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does ChatBI MVP Architecture work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. Design task 'wire up NL query to SQL with a semantic layer' got a shallow direct-LLM-to-SQL answer from an unguided baseline; the skill forced the two-stage S2SQL-then-deterministic-translator split (with a corrector chain and self-consistency voting) that concretely blocks the table-name-hallucination failure mode the naive design is prone to.
What is the ChatBI MVP Architecture SkillProof Score?: 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install ChatBI MVP Architecture?: 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 ChatBI MVP Architecture 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.