Is the FTShare Market Data skill free?

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

What is the FTShare Market Data SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install FTShare Market 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 FTShare Market 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.

FTShare Market Data

153 no-key endpoints for A-share, HK and US market data via one run.py

by FTShare-Lab · FTShare-Lab/FTShare-skills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Aug 10, 2026
Environment: Claude Code 2.x (agent harness)

153 sub-skills behind one run.py dispatcher, and crucially no API key: live calls came back with ChiNext quotes stamped 2026-08-10, all 300 CSI 300 constituent weights as of 2026-07-31, Tencent's HK share count and market cap, June 2026 China CPI, and same-week block trades. The no-skill baseline could still scrape ChiNext turnover leaders from Eastmoney's raw push2 endpoint, but only with undocumented f3/f6/f12 field codes, and it could not get the index weights at all: csindex.com.cn returned HTTP 500 and the other sources 403'd or 404'd, while the skill returned them in one command with an as-of date. One documented example is broken in practice: stock-quotes-list --order_by "change_rate desc" sorts nulls first and hands back three delisted shells before any live stock, whereas stock-daec-stocks with the same flag sorts correctly. Output and error messages are Chinese-only, which matters if you are wiring this into an English pipeline.

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 8/10
Docs & honesty 4/5

What FTShare Market Data does

A single dispatcher over 153 financial data endpoints covering A-share quotes and candlesticks, IPOs, block trades, margin trading, convertible bonds, ETFs, funds, index constituent weights, Chinese macro series, plus Hong Kong and US listings and financial statements. Every call goes through run.py against the public market.ft.tech gateway with no API key or login. Triggers when you ask for a stock code, live quote, valuation, K-line, index weight or macro figure for Chinese, Hong Kong or US markets.

How to install FTShare Market Data

git clone --depth 1 https://github.com/FTShare-Lab/FTShare-skills.git
mkdir -p ~/.claude/skills
cd FTShare-skills && cp -r ftshare-market-data ~/.claude/skills/ftshare-market-data

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

Commands — how to trigger FTShare Market Data

/ftshare-market-data 153 no-key endpoints for A-share, HK and US market data via one run.py

It also activates on plain-language prompts like these:

Get today's ChiNext quote leaders and CSI 300 constituent weights
Pull Tencent's Hong Kong listing profile and financials for me
What's the latest China CPI print and margin trading data?

Frequently asked questions

Is the FTShare Market Data skill free?: Yes. The skill itself is free from FTShare-Lab/FTShare-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does FTShare Market Data work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Aug 10, 2026. Verdict: Tested · Works. 153 sub-skills behind one run.py dispatcher, and crucially no API key: live calls came back with ChiNext quotes stamped 2026-08-10, all 300 CSI 300 constituent weights as of 2026-07-31, Tencent's HK share count and market cap, June 2026 China CPI, and same-week block trades. The no-skill baseline could still scrape ChiNext turnover leaders from Eastmoney's raw push2 endpoint, but only with undocumented f3/f6/f12 field codes, and it could not get the index weights at all: csindex.com.cn returned HTTP 500 and the other sources 403'd or 404'd, while the skill returned them in one command with an as-of date. One documented example is broken in practice: stock-quotes-list --order_by "change_rate desc" sorts nulls first and hands back three delisted shells before any live stock, whereas stock-daec-stocks with the same flag sorts correctly. Output and error messages are Chinese-only, which matters if you are wiring this into an English pipeline.
What is the FTShare Market Data SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install FTShare Market 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 FTShare Market 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.