Taco Strategy

v1.0.0

Taco 交易策略引擎。触发场景:用户问该买什么/该做什么/有什么机会/推荐策略/扫描市场/交易信号/autopilot 配置/策略列表/执行推荐交易。关键词:recommend, strategy, what to trade, 交易策略, 推荐, 该买什么, 有什么机会, scan, signal, auto...

0· 77·0 current·0 all-time
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
The skill's name and description match its behavior: fetching market data, computing indicators, proposing trades, and delegating execution to a separate 'taco' skill. One minor mismatch: the SKILL.md expects a separate 'taco' skill (get-balance, get-kline, execute order) but the registry metadata does not declare that dependency — this is an assumption rather than a secret requirement.
Instruction Scope
The instructions are narrowly scoped to market data retrieval (taco skill or public Hyperliquid API), indicator calculation, regime detection, strategy matching, and presenting recommended trades. The workflow explicitly requires waiting for user confirmation before calling the execution skill and forbids fabricating data when market data is unavailable. The instructions do not ask to read unrelated files or environment variables.
Install Mechanism
No install spec or code files are present (instruction-only), so nothing is downloaded or written to disk. This minimizes supply-chain/install risk.
Credentials
The skill requests no environment variables or credentials. It relies on an existing 'taco' skill to access account balances and to place orders; that dependency is logical for its purpose but means users should ensure the 'taco' skill has appropriate, audited access to their trading account.
Persistence & Privilege
The skill does not request persistent installation privileges (always is false). It instructs the agent to wait for explicit user confirmation before executing trades, which reduces the risk associated with autonomous invocations (though platform-level autonomous invocation remains possible).
Assessment
This skill is internally consistent with a trading strategy engine, but before enabling it you should: 1) verify you trust and have installed the referenced 'taco' skill (it will be the component that holds your account credentials and actually places orders); 2) confirm the agent will always ask for your explicit confirmation before executing trades (the SKILL.md says so, but enforcement depends on the platform and the 'taco' skill); 3) be aware it calls a public Hyperliquid API for fallback market data — confirm you are comfortable with that endpoint; and 4) if you do not want any chance of automated trading, restrict autonomous invocation or review the 'taco' skill's permissions first.

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

latestvk979xr2zhefab0xxgn3sc8rp7183yddg

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments