Token导航 LogoToken导航

Agent Skill · 开发

wyckoff-a-share(威科夫股份)

wyckoff-a-share 用于处理图像、截图、视觉识别或图片素材相关工作,适合在 OpenClaw 中需要让 Agent 分析图片、整理视觉素材或辅助图像流程时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

wyckoff-a-share 是开发类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为需要联网;许可证为 MIT-0,第三方扫描已通过,按安装量在开发类的 21,746 个 Skill 里排第 4,723。

总安装 7,638周安装 312GitHub Stars 公开资料未说明下载 2,446核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:wyckoff-a-share(威科夫股份)
来源仓库:https://github.com/youngcan-wang/wyckoff-a-share
安装命令:
openclaw skills install wyckoff-a-share
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install wyckoff-a-share

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

基于威科夫方法分析股票持仓与图表图像的工具。整合持股成本、数量与现金数据生成专业分析报告。适用于技术分析教学与投资策略辅助决策。wyckoff-a-share 属于开发类 Skill,可作为该场景下的辅助能力补充。安装命令:openclaw skills install wyckoff-a-share。

需提供 CSV 数据文件或手动录入持仓明细。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install wyckoff-a-share;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

wyckoff-a-share 怎么安装?

在终端执行 openclaw skills install wyckoff-a-share。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

wyckoff-a-share 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

wyckoff-a-share 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

wyckoff-a-share 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

wyckoff-a-share 用的人多吗?

公开数据是累计安装 7,638 次,近一周安装 312 次,下载 2,446 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

wyckoff-a-share 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理开发类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
wyckoff-a-share

威科夫股份 · 本页

7,638—需要联网MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
akshare-online-alpha
description
Run Wyckoff master-style analysis from stock codes, holdings (symbol/cost/qty), cash, CSV data, and optional chart images. Use when users want online multi-source data fetching with source switching, strict Beijing-time trading-session checks, fixed system prompt analysis, single-stock analysis, holding rotation, holding add/reduce suggestions, or empty-position cash deployment suggestions.

Akshare Online Alpha

Use this skill when the user wants Wyckoff-style analysis with online data fetch and source fallback.

Input Schema

Single/multi symbol analysis:

  • Inputs: stock code(s), optional CSV, optional chart image, text goals.

Portfolio decision analysis:

  • holdings (can be empty): [股票A+成本+数量, 股票B+成本+数量, ...]
  • cash: available cash amount
  • candidate (optional): stock code not currently in holdings
  • Optional CSV/image/text instructions are still supported.

Portfolio example:

  • holdings = [600519+1450+100, 000001+10.2+3000]
  • cash = 80000
  • candidate = 300750

When To Use / Not Use

Use this skill when at least one condition is true:

  • User provides stock code(s) and asks for current/near-current analysis.
  • User provides holdings + cash + candidate and asks whether to switch positions.
  • User asks whether current holdings should be increased/reduced/kept.
  • User has no holdings and asks how to act with available cash.
  • User asks to combine CSV + online validation.
  • User provides chart image and asks for Wyckoff interpretation.

Do not use this skill when:

  • User only asks for generic Python/chart debugging unrelated to market analysis.
  • User requests purely offline historical analysis with no online data requirement.

Auto Intent Inference

When holdings/cash/candidate are provided, do not require the user to say "switch / add / reduce / empty-position".

Infer automatically from provided fields:

  • holdings non-empty + candidate provided: include rotation comparison and per-holding actions.
  • holdings non-empty + no candidate: provide per-holding add/reduce/hold/exit suggestions.
  • holdings empty + cash provided: provide empty-position cash deployment suggestion.

Required Execution Order

  1. Validate input and parse structured fields:
  • Determine symbol-only flow or portfolio flow from input fields.
  • CSV (if provided): main source for historical structure.
  • Text instructions: constraints and goals.
  • Image (if provided): supplemental intraday/micro-structure signal.
  • In portfolio flow, parse holdings/cash/candidate(optional) before analysis.
  1. Resolve current Beijing time before any trading suggestion:
  • Fetch actual current time from tool/system.
  • Convert to Asia/Shanghai.
  • Print 当前北京时间:YYYY-MM-DD HH:MM(UTC+8).
  • Determine if in A-share continuous auction window.
  1. Enforce trading-session rules:
  • If not in tradable session, only provide post-market review/next-day plan/order strategy.
  • Do not output immediate intraday execution commands.
  1. Fetch data with online source switching:
  • Use rules/source-fallbacks.md order.
  • For each symbol, keep source audit log.
  • If source fails, schema check fails, or rows are insufficient, switch source.
  • In portfolio flow, fetch all holding symbols and candidate symbol when provided.
  1. Perform Wyckoff analysis first:
  • Analyze latest 500 days structure with MA50/MA200.
  • Identify phases/events without forcing full phase set.
  • Allow event-date news checks only for verification, not as decision basis.
  1. In portfolio flow, produce a Wyckoff-style portfolio recommendation:
  • For each holding, give one action: add / reduce / hold / exit.
  • If candidate is provided, compare candidate vs current holdings from structure strength, phase position, and event quality.
  • If candidate is provided, identify which current holding is structurally weakest and whether rotation is needed.
  • If holdings are empty, provide an empty-position suggestion using available cash and current structure context.
  • Use cost/qty/cash to give concrete action suggestions in narrative form.
  • Keep final recommendation in Wyckoff tone and clearly state action labels such as switch / partial switch / hold / add / reduce.
  1. Plot only when allowed:
  • If current time is intraday trading time, skip plotting.
  • Otherwise generate plotting code/result using hard rendering constraints from system prompt.

Fixed Output Contract

Always output in this order:

  1. 当前北京时间:YYYY-MM-DD HH:MM(UTC+8)
  2. Trading verdict:
  • 当前是否可盘中交易:是/否
  • If no: 当前不可盘中交易(原因:...)
  1. Data audit table per symbol:
  • symbol
  • source_used
  • rows_kept
  • window_end_date
  • fallback_count
  1. Wyckoff analysis result:
  • Current cycle background and phase (only what is evidenced).
  • Key events (SC/ST/Spring/LPS/SOS/UTAD if present) with concise rationale.
  • Action boundaries respecting T+1 and current session status.
  1. Portfolio action section (portfolio flow only):
  • Holdings snapshot from provided cost/qty/cash.
  • Per-holding action suggestions (add / reduce / hold / exit) with reasoning.
  • Candidate vs weakest holding comparison (if candidate is provided).
  • Empty-position cash action suggestion (if holdings are empty).
  • Final action summary in Wyckoff tone.
  1. Plotting section (only when allowed by session rules):
  • Python code and/or generated chart result with Chinese annotation constraints.

Failure And Degrade Rules

  • If all data sources fail for a symbol, report that symbol as data_unavailable and continue with remaining symbols.
  • If fewer than 30 valid rows are available, do not force phase labeling; return "insufficient structure depth".
  • If image is unreadable, explicitly state parse failure reason and continue with text/CSV path.
  • Never invent OHLCV rows, event timestamps, or trading-day status.

Hard Constraints

  • Do not change the fixed prompt wording unless explicitly requested.
  • Do not fabricate missing OHLCV rows.
  • Do not ignore image input if image is parseable.
  • Do not use opaque white text boxes in chart annotations.
  • If fetching data requires running Python scripts, run them only in a sandboxed environment.
  • Prefer direct web/API fetch first; use Python scripts only when needed for fallback, parsing, or normalization.

Resources

  • rules/alpha-system-prompt.md: fixed role and hard rules.
  • rules/source-fallbacks.md: online source switching policy.

平台分布

OpenClaw

70.95%
按下载量换算1,735

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills