Agent skill

Akshare Online Alpha

by LeoYeAI in LeoYeAI/openclaw-master-skills

Run Wyckoff master-style analysis from stock codes, holdings (symbol/cost/qty), cash, CSV data, and optional chart images.

MITAuto-check passedBusiness, Finance & HR

Install Akshare Online Alpha

skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill akshare-online-alpha -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LeoYeAI/openclaw-master-skills akshare-online-alpha --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/wyckoff-a-share .claude/skills/akshare-online-alpha && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
akshare-online-alpha
GitHub stars
2.2k
Token cost
~1.6k tokens
SKILL.md length
768 words
Files
6
Skills in repo
1,235
Repo updated
First seen
Licence
MIT

At a glance

Run Wyckoff master-style analysis from stock codes, holdings (symbol/cost/qty), cash, CSV data, and optional chart images.

  • Works in 2 steps: 当前北京时间:YYYY-MM-DD HH:MM(UTC+8) → Trading verdict
  • Users want online multi-source data fetching with source switching
  • SKILL.md covers Input Schema, When To Use / Not Use, Auto Intent Inference and Required Execution Order, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Akshare Online Alpha is an agent skill from LeoYeAI/openclaw-master-skills. 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.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files (for example `.clawhub/origin.json`, `_meta.json` and `agents/openai.yaml`).

It sits in Business, Finance & HR, covering Prompt engineering, Stock and market analysis and CSV and tabular files. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.

When your agent uses it

  • Users want online multi-source data fetching with source switching
  • Strict Beijing-time trading-session checks
  • Fixed system prompt analysis
  • Single-stock analysis

Example prompts

  • “/akshare-online-alpha”

Requirements

  • Python 3

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. 当前北京时间:YYYY-MM-DD HH:MM(UTC+8)
  2. Trading verdict

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Akshare Online Alpha loads about 1.6k tokens when it runs. Until then it costs about 104 tokens; SKILL.md has 768 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~104
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 768 words, ~1,605 tokens.

Download SKILL.mdSave it as .claude/skills/akshare-online-alpha/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
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.
Show full SKILL.md (262 more words)Show less

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.

© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files in skills/wyckoff-a-share of LeoYeAI/openclaw-master-skills.

  • SKILL.md
  • .clawhub/origin.json
  • _meta.json
  • agents/openai.yaml
  • rules/alpha-system-prompt.md
  • rules/source-fallbacks.md

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Akshare Online Alpha next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Akshare Online Alpha compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Akshare Online Alpha this skillLeoYeAI/openclaw-master-skills2.2k—~1.6kAutomated safety check: PassMIT
Regimejackson-video-resources/markov-hedge-fund-method484—~1.6kAutomated safety check: PassCustom licence
Mx Stocks Screenerhiboys/ExploreFinance365—~697Automated safety check: PassNone
Anti Gambling Tradermars-tw/anti-gambling-trader-tw907—~1.9kAutomated safety check: PassMIT
Data UpdateSixian-Li/plain-backtest204—~1.6kAutomated safety check: PassMIT
Tushare Datazillionare/zillionare3222 repos~2.3kAutomated safety check: PassNone

Similar skills

  • Regime

    jackson-video-resources/markov-hedge-fund-method

    Detect the market regime (Bull / Bear / Sideways) for ANY asset and turn it into a tradeable signal or a risk filter.

    484 GitHub stars~1.6k tokensUpdated 4 mo ago
    Business, Finance & HRAuto-check passed
  • Mx Stocks Screener

    hiboys/ExploreFinance

    基于东方财富数据库,支持通过自然语言输入筛选A港美股、基金、债券等多种资产,支持多元指标筛选,含技术面、消息面、基本面及市场情绪等,可用于全球资产速筛、跨市场监控、投资组合构建、策略回测等场景。返回结果包含数据说明及 csv 文件。Natural language screener for investment assets across global markets, including…

    365 GitHub stars~697 tokensUpdated 3 mo ago
    Business, Finance & HRAuto-check passed
  • Anti Gambling Trader

    mars-tw/anti-gambling-trader-tw

    分析台股 / 台股ETF / 台指期選擇權 / 美股 / 加密貨幣 / 外匯的交易紀錄 (CSV / JSON / Excel),用統計學判斷使用者的獲利是「可重複的優勢」還是 「運氣 + 倖存者偏差(賭博)」,不適合長期投資會明確勸退。內建反詐工具: 掃描群組對話的詐騙話術(scan-text)、檢驗老師宣稱的績效(guru-check)、…

    907 GitHub stars~1.9k tokensUpdated 2 days ago
    Documents & OfficeAuto-check passed
  • Data Update

    Sixian-Li/plain-backtest

    Operate and assess the Quant workspace market-data layer through the tested data-update CLI.

    204 GitHub stars~1.6k tokensUpdated 13 days ago
    Documents & OfficeAuto-check passed
  • Tushare Data

    zillionare/zillionare

    面向中文自然语言的 Tushare 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场景。

    322 GitHub starsUsed in 2 repos~2.3k tokens
    Business, Finance & HRAuto-check passed
  • Tradingview MCP

    atilaahmettaner/tradingview-mcp

    AI Trading Intelligence — live prices, 30+ technical indicators, backtesting (6 strategies), walk-forward overfitting detection, trade logs, equity curves, licensed news sentiment (Marketaux), and…

    5k GitHub stars~1.3k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed

More from LeoYeAI/openclaw-master-skills

All 1,200 skills in this repo
  • DevOps Pipeline Management

    LeoYeAI/openclaw-master-skills

    Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • Feishu Document Collaboration

    LeoYeAI/openclaw-master-skills

    Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.

    2.2k GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed
  • Files Memory System

    LeoYeAI/openclaw-master-skills

    Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.

    2.2k GitHub stars~3.8k tokensUpdated 2 mo ago
    Auto-check passed
  • GEO-Claw AI Visibility Agent

    LeoYeAI/openclaw-master-skills

    Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Google Workspace CLI

    LeoYeAI/openclaw-master-skills

    Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.

    2.2k GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check: notes
  • HealthFit Health Advisors

    LeoYeAI/openclaw-master-skills

    Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.

    2.2k GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Akshare Online Alpha

What does Akshare Online Alpha do?

Run Wyckoff master-style analysis from stock codes, holdings (symbol/cost/qty), cash, CSV data, and optional chart images. Akshare Online Alpha is an agent skill from LeoYeAI/openclaw-master-skills. Run Wyckoff master-style analysis from stock codes, holdings (symbol/cost/qty), cash, CSV data, and optional chart images.

When should I use Akshare Online Alpha?

Akshare Online Alpha fits situations like: users want online multi-source data fetching with source switching; strict Beijing-time trading-session checks; fixed system prompt analysis; single-stock analysis.

How do I install Akshare Online Alpha in Claude Code?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill akshare-online-alpha -a claude-code`. Or copy the skill folder (skills/wyckoff-a-share in LeoYeAI/openclaw-master-skills) into .claude/skills/akshare-online-alpha in your project. Claude Code loads it when a task matches its description.

How do I install Akshare Online Alpha in Codex?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill akshare-online-alpha -a codex`. Or copy the skill folder (skills/wyckoff-a-share in LeoYeAI/openclaw-master-skills) into .agents/skills/akshare-online-alpha in your project. Codex loads it when a task matches its description.

Can I use Akshare Online Alpha in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill akshare-online-alpha -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/akshare-online-alpha, .gemini/skills/akshare-online-alpha, .github/skills/akshare-online-alpha and .opencode/skills/akshare-online-alpha in your project.

What does Akshare Online Alpha need to run?

SKILL.md names no scripts, command-line tools or credentials: Akshare Online Alpha is instructions for the agent only. Our summary lists: Python 3.

Does Akshare Online Alpha access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Akshare Online Alpha safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Akshare Online Alpha use?

Akshare Online Alpha is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Akshare Online Alpha use?

About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Akshare Online Alpha?

Skills that share tags, products or a category with Akshare Online Alpha: Regime (jackson-video-resources/markov-hedge-fund-method, 484 stars), Mx Stocks Screener (hiboys/ExploreFinance, 365 stars), Anti Gambling Trader (mars-tw/anti-gambling-trader-tw, 907 stars) and Data Update (Sixian-Li/plain-backtest, 204 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Akshare Online Alpha?

LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.

Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.