ClawHub

Quantflow Skill

v1.1.1

面向中文自然语言的量化金融数据研究技能。用于把"看看这只股票最近怎么样""帮我查财报趋势""最近哪个板块最强""北向资金在买什么""给我导出一份行情数据"这类请求，转成可执行的数据获取、清洗、对比、筛选、导出与简要分析流程。适用于 A 股、指数、ETF/基金、财务、估值、资金流、公告新闻、板块概念与宏观数据等研究...

⭐ 0· 102·0 current·0 all-time
by@yejinlei
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name and description (quantitative research, data fetching, cleaning, export, AKQuant backtests) match the declared requirements (akshare, akquant, network access) and the included scripts which call akshare/akquant APIs. There are no unrelated credentials, binaries, or configuration paths requested.
ℹ
Instruction Scope
SKILL.md stays on-topic (data workflows, interface names, caching, output formats). The repository includes example scripts that implement backtests and call buy/sell methods (AKQuant Strategy classes) — appropriate for backtesting demos but worth noting: if AKQuant is later configured for live execution, similar code could be repurposed to place orders. The skill does not instruct reading unrelated local files or exfiltrating data.
✓
Install Mechanism
No install spec; SKILL.md recommends pip installs for akshare and akquant which is proportionate. There are no downloads from untrusted URLs or archive extracts. Example code is included but not automatically installed.
✓
Credentials
The skill requests no environment variables or credentials. Network access is declared and justified because akshare fetches market data. There are no unexplained secret requests or cross-service credentials.
✓
Persistence & Privilege
always is false and the skill does not ask to modify other skills or system-wide config. Autonomous invocation is allowed by platform default but not combined with other red flags here.
Assessment
This skill appears coherent and focused on fetching market/macroeconomic data and running backtests with Akshare/AKQuant. Before installing: (1) confirm you trust akshare and akquant from PyPI and keep them up to date; (2) run the example scripts in a sandbox environment (no production brokerage credentials) — AKQuant can support live execution if configured, so do not provide any broker API keys or trading credentials unless you intentionally want live trading; (3) expect the skill to perform network requests to public data sources; (4) if you only want read-only analysis, avoid connecting any live-execution plugins or credentials.

Like a lobster shell, security has layers — review code before you run it.

latestvk976w91sb4gtn1t6wr6c8p3k1183ndy9

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments