T Trading
v1.0.0基于维加斯通道EMA多层通道与斐波那契回撤，提供A股和加密货币短线交易的多维度结构化技术分析和明确操作建议。
⭐ 5· 11.9k·2 current·2 all-time
byenoyao@wscats
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (EMA channels + Fibonacci for A‑share and crypto short‑term trading) match the SKILL.md content. The skill is prompt‑based, needs no binaries, env vars, or installs — all proportional to a prompt-only technical-analysis skill.
Instruction Scope
The SKILL.md stays within the trading-analysis domain and provides detailed, deterministic rules and output templates. One vagueness: it says 'if you have real‑time data fetching ability → automatically fetch' without naming data sources or endpoints; that grants the agent discretion to call whatever market data connectors it has access to. The skill does not instruct reading unrelated files, exfiltrating secrets, or contacting hidden endpoints.
Install Mechanism
No install spec and no code files to run. This is the lowest‑risk model: nothing is written to disk and no external packages are pulled.
Credentials
The skill requires no environment variables, credentials, or config paths. Requested capabilities are proportional to the stated purpose (technical analysis).
Persistence & Privilege
always is false, no special persistence or system modifications are requested. The skill is user‑invocable and may be invoked autonomously by the agent (default platform behavior), which is appropriate for this kind of prompt skill.
Assessment
This skill is a pure Markdown, prompt-based trading-analysis tool and appears coherent with its description. Before enabling: (1) be aware it auto-activates on many trading-related keywords — if you don't want that, disable auto-triggering in your agent settings; (2) the skill may ask the agent to fetch live market data if the agent has connectors — confirm which data sources the agent will use (exchange APIs, paid feeds, or public endpoints) and that you trust them; (3) it produces concrete entry/stop/target prices — do not treat outputs as financial advice (the skill includes a disclaimer); (4) because it is instruction-only, it cannot exfiltrate secrets itself, but any network calls performed by your agent or connectors are outside the skill and should be reviewed. If you need higher assurance, require the user to supply price/EMA data instead of allowing automatic fetches.Like a lobster shell, security has layers — review code before you run it.
latestvk9751dparbh5zp94k5td3hcevs82whag
License
MIT-0
Free to use, modify, and redistribute. No attribution required.