Skip to content
Back to search

apocdata

"A-share data service with structured announcement parsing: every announcement carries an AI summary, category, importance level and sentiment, fully traceable to source. Also 45+ endpoints for quotes, financials, capital flows, dragon-tiger lists and macro data. Free tier for instant access; register for higher quotas. Use when users ask for A-share stock quotes, financials, capital flows, technical factors, news, announcements, sectors, convertible bonds, macro data, or comprehensive stock analysis through the ApocData public API. Trigger keywords: 股票, 行情, 估值, 财务, 资金流, 涨停, 跌停, 炸板, 打板, 连板, 板块, 概念, 可转债, 宏观, 公告, 调研, 龙虎榜, 游资, 北向资金, 两融, 排行, 人气榜, 指数, 筹码, 获利盘, ST, 分红, 回购, 大宗交易, 量化因子, 技术面, 交易日历, 下修, 转股价, 业绩快报, 股东户数, 解禁, profile, ApocData, A股数据. Do NOT trigger for: cryptocurrency, crypto, Bitcoin, US stocks, US market, futures, options, forex, Hong Kong stocks, 加密货币, 比特币, 美股, 期货, 外汇, or any non-A-share market."

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/apocdata--apocdata-skill/badge.svg)](/listings/apocdata--apocdata-skill)

HTML

<a href="/listings/apocdata--apocdata-skill"><img src="/api/listings/apocdata--apocdata-skill/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These steps run a script from the network that findsafeskills does not scan.

Quick Install (recommended)

mkdir -p ~/.claude/skills/apocdata
curl -sL https://gitee.com/apocdata/ApocData-skill/repository/archive/v2.0.5.tar.gz \
  | tar xz -C ~/.claude/skills/apocdata --strip-components=1

Restart Claude Code and the skill will be auto-detected.

MCP Install (Claude Desktop / Cursor / ChatGPT)

{
  "mcpServers": {
    "apocdata": {
      "command": "npx",
      "args": ["-y", "@apocdata-info/mcp-server"]
    }
  }
}

OpenAPI Import (GPT Actions / Dify / Coze / n8n)

https://www.apocdata.com/api/blade-dataplatform/open/data/openapi.json

Import and use — free tier, no registration needed.

Alternative: install script

curl -sL https://gitee.com/apocdata/ApocData-skill/raw/main/scripts/install.sh | bash

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

SKILL.md · Manifest · 189 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. ---
  2. name: apocdata
  3. description: "A-share data service with structured announcement parsing: every announcement carries an AI summary, category, importance level and sentiment, fully traceable to source. Also 45+ endpoints for quotes, financials, capital flows, dragon-tiger lists and macro data. Free tier for instant access; register for higher quotas. Use when users ask for A-share stock quotes, financials, capital flows, technical factors, news, announcements, sectors, convertible bonds, macro data, or comprehensive stock analysis through the ApocData public API. Trigger keywords: 股票, 行情, 估值, 财务, 资金流, 涨停, 跌停, 炸板, 打板, 连板, 板块, 概念, 可转债, 宏观, 公告, 调研, 龙虎榜, 游资, 北向资金, 两融, 排行, 人气榜, 指数, 筹码, 获利盘, ST, 分红, 回购, 大宗交易, 量化因子, 技术面, 交易日历, 下修, 转股价, 业绩快报, 股东户数, 解禁, profile, ApocData, A股数据. Do NOT trigger for: cryptocurrency, crypto, Bitcoin, US stocks, US market, futures, options, forex, Hong Kong stocks, 加密货币, 比特币, 美股, 期货, 外汇, or any non-A-share market."
  4. ---
  5. # 天启至数 ApocData — A 股数据服务
  6. > **让 AI 读懂 A 股公告。** 全市场公告解析为结构化数据:AI 摘要(`summary`)、
  7. > 类型(`category`)、重要性(`importance`)、情感倾向(`sentiment`),条条可溯源(`url`);
  8. > 并覆盖行情、财务、资金流、龙虎榜、宏观等 45+ 数据接口。
  9. > 免费体验额度开箱即用,注册解锁更高额度与更多能力。
  10. > 支持 WorkBuddy / Codex / Hermes / DeepSeek / Kimi / 千问 / 智谱清言等所有 Agent。
  11. ## 安装
  12. ```bash
  13. # v2.0.5 多文件结构(推荐)
  14. mkdir -p ~/.claude/skills/apocdata
  15. curl -sL https://gitee.com/apocdata/ApocData-skill/repository/archive/v2.0.5.tar.gz \
  16. | tar xz -C ~/.claude/skills/apocdata --strip-components=1
  17. ```
  18. 重启 Claude Code 后自动生效。
  19. ---
  20. ## 基础用法
  21. 所有接口均为 HTTP GET,用 curl 直接调用:
  22. ```bash
  23. BASE="https://www.apocdata.com/api/blade-dataplatform/open/data"
  24. # 查单只股票行情
  25. curl -s "$BASE/quote?symbol=000001"
  26. # 查股票基本信息(含 PE/PB/市值)
  27. curl -s "$BASE/stock?symbol=000001"
  28. ```
  29. ### OpenAPI 3 接入(GPT Actions / Coze / Dify / n8n / Zapier)
  30. | 端点 | 用途 |
  31. |---|---|
  32. | `https://www.apocdata.com/api/blade-dataplatform/open/data/openapi.json` | **OpenAPI 3 JSON(推荐,导入即用)**,免费体验额度匿名访问,覆盖全部公开接口 |
  33. > spec 的 `servers.url` 已内置为公网基址,导入后各接口路径直接拼接即可调用,无需再改 base。
  34. 免费体验额度,无需注册即可调用;注册解锁更高额度与更多数据能力。
  35. ---
  36. ## 场景速查(按用户意图找接口组合)
  37. > 拿到自然语言意图时,**优先查本表选定接口组合**,再去参考文件看字段细节,避免漏调或乱调。
  38. | 用户意图 | 推荐调用顺序 | 关键说明 |
  39. |---|---|---|
  40. | 个股综合画像 / 「这只票怎么样」 | **推荐**:`profile/full?symbol=X`(一次返回 8 维数据) | 等价于并发调 8 个单接口,延时减 60%+ |
  41. | 个股综合画像(分步精细化) | `quote` → `stock` → `financial` → `tech-factor` → `moneyflow` → `announcements` | 需要按维度独立控制 limit/fields 时用 |
  42. | **多只股票行情对比 / 批量查涨跌** | **`quotes?symbols=A,B,C`**(**3 只以上必须用,禁止逐只轮询**) | 最多 10 只,一次返回,省 3 倍请求 |
  43. | 估值评估 / 「贵不贵」 | `stock` → `financial` → `daily?limit=30` | 看 PE/PB/PEG,结合近期走势判断 |
  44. | 资金动向追踪 / 「主力在干嘛」 | `moneyflow` → `hsgt` → `hk-hold` → `dragon-tiger` → `hot-money-detail` | 北向 20:00 后更新 |
  45. | 涨停盘后复盘 / 「今天涨停的共性」 | `limit-list?kind=U` → `limit-step` → `sector-flow` → `hot-money-detail` | date 不传默认最新交易日 |
  46. | 板块 / 概念热度 | `sector-flow` → `concepts` → `concept-stocks` 或 `ths-boards` → `ths-board-stocks` | 东方财富与同花顺双源板块数据,可交叉验证 |
  47. | 新闻 / 市场事件 | ~~`news?q=关键词`~~ **已下线** → 改用 `announcements` 查正式披露 | `/news` 接口已下线 |
  48. | 公告 / 事件驱动 | `announcements` → `survey` → `share-float` → `repurchase` → `dividend` | 公告正文可选;`summary` 可能为空,使用前需判空 |
  49. | 大盘择时 / 宏观判断 | `index-daily?tsCode=000300.SH` → `macro/latest?type=PMI` → `macro/latest?type=CPI` → `hsgt` | 宏观接口最多 12 条 |
  50. | 可转债套利 | `convertible-bonds` → `cb-price-chg` → `quote`(正股) | 用 stkCode 反查正股可转债 |
  51. | 找游资偏好的票 | `hot-money` → `hot-money-detail` → `dragon-tiger` | 当日游资明细 + 历史席位 |
  52. | 退市/风险排查 | `st` → `share-float` → `holders` → `announcements` | st 返回 null 即非 ST |
  53. | 业绩超预期追踪 | `express` → `financial` → `survey` → `announcements` | express 是季报前的先行指标 |
  54. | 找具体行业 / 名字模糊 | `stocks?q=名称或代码&industry=行业` → `stock` 逐只确认 | `q` 模糊匹配名称/代码;`industry` 是独立精确过滤参数 |
  55. ---
  56. ## 接口分组总览
  57. > 全部 **45 个活跃业务接口按使用场景分 11 组**(`/news` 已下线)。详细参数和返回字段见对应的参考文件。
  58. | 组别 | 主题 | 接口数 | 参考文件 |
  59. |---|---|---|---|
  60. | A | 行情与估值 | 10 | `references/group-a-quote.md` |
  61. | B | 财务与基本面 | 8 | `references/group-b-financial.md` |
  62. | C | 资金博弈 | 7 | `references/group-c-capital.md` |
  63. | D | 涨跌停与情绪 | 4 | `references/group-d-limitup.md` |
  64. | E | 事件与信息 | 3(活跃 2) | `references/group-e-events.md` |
  65. | F | 板块/概念 | 4 | `references/group-f-sector.md` |
  66. | G | 可转债 | 2 | `references/group-g-convertible.md` |
  67. | H | 量化与技术 | 2 | `references/group-h-quant.md` |
  68. | I | 宏观 | 3 | `references/group-i-macro.md` |
  69. | J | 工具 | 1 | `references/group-j-tools.md` |
  70. | K | Agent 增强 | 2 | `references/group-k-agent.md` |
  71. ---
  72. ## 参考文件导航
  73. 根据用户需求,读取对应的参考文件获取完整接口细节:
  74. ### 全局规则(优先读取)
  75. | 参考文件 | 何时读取 |
  76. |---------|---------|
  77. | `references/boundaries.md` | 首次调用任何接口前、遇到错误/空数据时、需理解 header/缓存/freshness 时 |
  78. | `references/safety-rules.md` | 生成任何金融分析输出前(强制行为规则) |
  79. ### 接口字典(按主题按需加载)
  80. | 参考文件 | 何时读取 |
  81. |---------|---------|
  82. | `references/group-a-quote.md` | 查行情、估值、排行、指数、搜索股票、ST 状态 |
  83. | `references/group-b-financial.md` | 查财务报表、分红、股东、回购、大宗交易、限售解禁 |
  84. | `references/group-c-capital.md` | 查资金流、北向资金、两融、龙虎榜、游资 |
  85. | `references/group-d-limitup.md` | 查涨跌停、连板天梯、板块资金流、筹码分布 |
  86. | `references/group-e-events.md` | 查公告、机构调研(新闻已下线) |
  87. | `references/group-f-sector.md` | 查概念板块(东方财富)、行业板块(同花顺)、成分股 |
  88. | `references/group-g-convertible.md` | 查可转债列表、转股价变动 |
  89. | `references/group-h-quant.md` | 查量化因子注册表、个股技术面因子 |
  90. | `references/group-i-macro.md` | 查 GDP/CPI/PPI/PMI 宏观数据 |
  91. | `references/group-j-tools.md` | 查交易日历 |
  92. | `references/group-k-agent.md` | 用 profile/full 综合画像、factor-categories 因子分类 |
  93. ### 示例与场景
  94. | 参考文件 | 何时读取 |
  95. |---------|---------|
  96. | `references/examples.md` | 需要多接口配合的复杂分析场景(综合画像/涨停复盘/北向跟踪/可转债/宏观择时) |
  97. ---
  98. ## 调用工作流
  99. 1. **收到用户意图** → 先查上方「场景速查表」确定接口组合
  100. 2. **首次调用前** → 读取 `references/boundaries.md` 了解 limit 上限和参数易错点
  101. 3. **需要具体端点参数/返回字段** → 按场景速查表指向的组别,读取对应 `references/group-*.md`
  102. 4. **生成分析输出前** → 读取 `references/safety-rules.md` 遵守强制行为规则
  103. 5. **简单查询**(如「查下茅台行情」)→ 只需场景速查表 + `group-a-quote.md`,无需加载全部文件
  104. ---
  105. ## 关键约束速记(调任何接口前先扫一眼)
  106. ### limit 上限(超限静默截断,不报错)
  107. | 接口 | 上限 | 接口 | 上限 |
  108. |---|---|---|---|
  109. | `daily` | 30 | `quotes` | 10 只 |
  110. | `macro` | 12 | `ranking`/`limit-list`/`dragon-tiger` 等 | 50 |
  111. | `announcements` | 30 | `calendar` | 跨度 ≤ 366 天(**超范围会报错**) |
  112. ### 参数易错点
  113. - **枚举参数优先用英文**:`sector-flow?type=industry/concept/region`
  114. - **中文关键字必须 URL 编码**:用 `curl -G --data-urlencode "q=年报"`
  115. - **symbol vs tsCode**:A 股 `symbol=000001`(6 位);指数 `tsCode=000300.SH`;可转债 `stkCode=688535.SH`
  116. - **日期参数按接口区分**:`calendar` 使用 `start/end`;`announcements` 使用 `startDate/endDate`(可单独传入,也兼容旧版 `start/end` 别名)。日期格式均为 YYYYMMDD
  117. - **错误响应**:HTTP 400 + `success=false` + `X-Tdc-Error-Code` header;先检查状态再读 data
  118. - **不存在 symbol**:返回 `RESOURCE_NOT_FOUND`,先用 `stocks` 搜索确认
  119. - **公告空结果需复核**:`announcements` 的成功空数组可能是批次尚未完成或临时故障,不代表公告被删除;先看 `X-Tdc-Freshness-*`,再用日期窗口和 `q` 复查
  120. > 完整 header 说明、错误码表、缓存策略、Freshness SLA、fields 裁剪、compact 模式等详见 `references/boundaries.md`。
  121. ---
  122. ## 注意事项
  123. - 所有接口**只读**;免费体验额度无需注册即可调用,注册解锁更高额度与更多数据能力
  124. - symbol 统一 **6 位数字代码**;指数/可转债用带后缀的 `tsCode`
  125. - 单次请求超时建议 10 秒;复杂画像优先**并发**调用
  126. - **收盘后 `quote` 价格已是最终收盘价**:盘后 `quote` 返回 official close(与 `daily` 偏差 0.000%),`as_of` 可能显示 14:57 但价格准确,可放心使用;仅盘中(09:30-15:00)`quote` 为 15min 延迟快照
  127. - **空数据需结合场景判断**:`success=true` + 空数组可能是数据稀疏,也可能是批次尚未完成;公告和概念接口应检查 `trade_date` / `updated_at` 并适当重试
  128. - **token 紧张时**:用 `?fields=` 裁剪 + `?format=compact` 紧凑模式,可省 60-90% token
  129. - **小模型(<15B)**:用 `references/SKILL-compact.md`(~3KB 精简版)代替全文注入,避免关键信息被淹没
  130. - 输出分析必须标注数据时效(`trade_date` / `delayed_minutes` / Freshness header)
  131. - 数据来源:天启云(ApocData Cloud),公告 T+0 08:00,北向 20:00
  132. ---
  133. ## 金融输出安全约束(摘要)
  134. > 完整规则见 `references/safety-rules.md`。以下为 6 条强制规则摘要:
  135. 1. **数据时效透明** — 每次输出必须显示 `trade_date` / `delayed_minutes`
  136. 2. **数据来源分层** — 区分原始数据、AI 摘要、模型推断
  137. 3. **异常数据约束** — `success=false` 或关键字段缺失时停止确定性结论
  138. 4. **交叉验证** — 关键数据至少两个来源确认
  139. 5. **禁止买卖指令** — 严禁"买入/卖出/必涨/稳赚"等确定性表述
  140. 6. **免责声明** — 每次输出末尾注明"仅供研究参考,不构成投资建议"
README.md · README · 349 lines · 1 finding marked

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # 天启至数 ApocData — A股数据服务 (ApocData A-Share Data Skill)
  2. <p align="center">
  3. <b>English</b> |
  4. <a href="./README.zh-CN.md">简体中文</a>
  5. </p>
  6. <p align="center">
  7. <img src="https://img.shields.io/badge/endpoints-45-green" alt="45 endpoints"/>
  8. <img src="https://img.shields.io/badge/MCP-46_tools-blue" alt="MCP 46 tools"/>
  9. <img src="https://img.shields.io/badge/free_tier-available-brightgreen" alt="Free tier available"/>
  10. <img src="https://img.shields.io/badge/license-Apache_2.0-blue" alt="License"/>
  11. </p>
  12. > ## Let AI read A-share announcements
  13. >
  14. > **The A-share announcements and fundamentals database built for AI · parsed · structured · traceable**
  15. > All-market announcements parsed into structured data: AI summary · category · importance · sentiment, fully traceable to source. Also 45+ endpoints for quotes, financials, capital flows, dragon-tiger lists and macro data. Free tier for instant access; register for higher quotas. Compatible with WorkBuddy, Codex, Hermes, DeepSeek, Kimi, Qwen, Zhipu and any AI agent that supports tool calling.
  16. The [`SKILL.md`](./SKILL.md) in this repository is a capability card that can
  17. be loaded directly into AI agents, letting LLMs query A-share market data
  18. and complete research tasks without any SDK.
  19. ---
  20. ## Quick Try
  21. Copy-paste and run, no config needed:
  22. ```bash
  23. curl -s "https://www.apocdata.com/api/blade-dataplatform/open/data/quote?symbol=600519"
  24. ```
  25. <details>
  26. <summary>Click to expand sample response</summary>
  27. ```json
  28. {
  29. "code": 200, "success": true,
  30. "data": {
  31. "symbol": "600519", "name": "Kweichow Moutai",
  32. "close": 1528.00, "pct_chg": -0.52,
  33. "volume": 2856321, "delayed_minutes": 15
  34. }
  35. }
  36. ```
  37. *Actual response has more fields; above is a simplified example.*
  38. </details>
  39. ---
  40. ## Announcement Parsing — from PDF to structured data
  41. Conventional data sources hand you the raw announcement text and leave the reading and parsing to you. ApocData returns the parsed, structured result, ready for an AI agent to consume.
  42. Every announcement carries:
  43. - **AI summary** (`summary`) — the key facts extracted, no need to read the full document
  44. - **Category** (`category`) — earnings, dividend, buyback, share increase/decrease, litigation and more, filterable programmatically
  45. - **Importance level** (`importance`) — locate the announcements that actually matter
  46. - **Sentiment** (`sentiment`) — positive / negative / neutral, to help judge the direction of impact
  47. - **Source link** (`url`) — every conclusion traces back to the original announcement
  48. Also returned: `title`, `ann_date`, `publish_time`, `keywords`, `source`, and
  49. `content` (full Markdown body, on `includeContent=true`).
  50. Covers all-market announcements, including Stock Connect constituents, ST and delisting-risk securities.
  51. ---
  52. ## Why ApocData?
  53. | | **ApocData** | 数据源A | 数据源B | 数据源C |
  54. |---|---|---|---|---|
  55. | Announcement parsing | **Structured + AI summary + sentiment** | Raw text | Raw text | Raw text |
  56. | Access | **Free tier, no registration** | Paid token | Python env + install | Application approval |
  57. | Setup steps | **0** | 3+ (register → token → config) | 2+ (pip + deps) | Manual review |
  58. | AI Agent native | **Skill + MCP** | Plugin (legacy) | Not supported | Not supported |
  59. | curl one-liner | **Direct** | Need SDK | Need SDK | Need SDK |
  60. | A-share endpoints | **45** | 100+ (paywalled) | 100+ (free) | 200+ (paid) |
  61. | MCP support | **46 tools** | None | None | None |
  62. *Comparison based on publicly available info as of 2026-08.*
  63. ---
  64. ## Core Capabilities
  65. - **Announcement parsing** — all-market announcements parsed by AI into structured fields
  66. (`title` / `category` / `importance` / `ann_date` / `summary` / `sentiment` / `url`), directly
  67. usable for reasoning and traceable to the source document (mainstream data sources mostly ship
  68. announcements as raw text)
  69. - **Full-dimension coverage** — quotes, financials, valuation, capital flows, limit-up review,
  70. dragon-tiger lists, sectors & concepts, convertible bonds, macro indicators and trading
  71. calendar: 11 groups, 45+ endpoints, one consistent definition set
  72. - **Multiple integration paths** — Skill package (one-command install), MCP server (46 tools),
  73. plain HTTP endpoints (direct curl), covering every mainstream AI ecosystem
  74. - **Traceable** — every data point traces back to the original announcement, so AI conclusions
  75. can be checked
  76. ---
  77. ## Table of Contents
  78. - [Announcement Parsing](#announcement-parsing--from-pdf-to-structured-data)
  79. - [Why ApocData?](#why-apocdata)
  80. - [Core Capabilities](#core-capabilities)
  81. - [Overview](#overview)
  82. - [Use Cases](#use-cases)
  83. - [Data Service Platform](#data-service-platform)
  84. - [Installation](#installation)
  85. - [Project Structure](#project-structure)
  86. - [Basic Usage](#basic-usage)
  87. - [Endpoint Overview](#endpoint-overview)
  88. - [Editions & Capabilities](#editions--capabilities)
  89. - [Notes & Compliance](#notes--compliance)
  90. ---
  91. ## Overview
  92. ApocData is the A-share announcements and data layer built for AI: parsed,
  93. structured, traceable. Announcement parsing is the core — every announcement
  94. becomes structured data an agent can reason over directly — and around it sits
  95. full-dimension coverage of quotes, financials, capital flows, dragon-tiger
  96. lists, quantitative factors and macro indicators, designed for AI agents,
  97. quantitative research, investment content, and institutional applications.
  98. ---
  99. ## Use Cases
  100. - *"What are the key points in Kweichow Moutai's recent earnings flash?"* → key
  101. figures extracted as structured fields, traceable to the original announcement
  102. - *"Analyse the valuation of 688017 — how does it compare with its peers?"* →
  103. PE/PB/market cap aggregated with financial metrics and the last 30 sessions
  104. - *"Which ST stocks published material announcements in the past 30 days?"* →
  105. ranked by risk level, each with an AI summary and a source link
  106. - *"Which sectors has northbound capital been flowing into?"* → Stock Connect
  107. plus sector capital flows, with the top inflow sectors summarised automatically
  108. ---
  109. ## Data Service Platform
  110. **Platform URL:** <https://www.apocdata.com>
  111. The data service platform is the unified entry point for ApocData. It provides:
  112. - **Open API (free tier)** — This is what the Skill connects to. A free trial
  113. quota is callable straight away, ideal for quick validation and lightweight usage.
  114. - **OpenAPI documentation & SDKs** — Python / TypeScript supported.
  115. - **Registered & Professional editions (with API key)** — Higher quotas, deeper history,
  116. lower latency, and richer data fields. See [Editions & Capabilities](#editions--capabilities).
  117. > The base URL used by this Skill: `https://www.apocdata.com/api/blade-dataplatform/open/data`
  118. ---
  119. ## Installation
  120. ### Quick Install (recommended)
  121. ```bash
  122. mkdir -p ~/.claude/skills/apocdata
  123. curl -sL https://gitee.com/apocdata/ApocData-skill/repository/archive/v2.0.5.tar.gz \
  124. | tar xz -C ~/.claude/skills/apocdata --strip-components=1
  125. ```
  126. Restart Claude Code and the skill will be auto-detected.
  127. ### MCP Install (Claude Desktop / Cursor / ChatGPT)
  128. ```json
  129. {
  130. "mcpServers": {
  131. "apocdata": {
  132. "command": "npx",
  133. "args": ["-y", "@apocdata-info/mcp-server"]
  134. }
  135. }
  136. }
  137. ```
  138. ### OpenAPI Import (GPT Actions / Dify / Coze / n8n)
  139. ```
  140. https://www.apocdata.com/api/blade-dataplatform/open/data/openapi.json
  141. ```
  142. Import and use — free tier, no registration needed.
  143. ### Alternative: install script
  144. ```bash
  145. curl -sL https://gitee.com/apocdata/ApocData-skill/raw/main/scripts/install.sh | bash
    • Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
    • Line 199 on GitHub
  146. ```
  147. ---
  148. ## Project Structure
  149. This Skill uses a **multi-file structure** for progressive loading — the entry
  150. `SKILL.md` is a slim router (~180 lines), and detailed endpoint specs are
  151. loaded on demand from the `references/` directory:
  152. ```
  153. ├── SKILL.md # Entry point (slim router, ~180 lines)
  154. ├── README.md # This file (human-facing docs)
  155. ├── CHANGELOG.md # Version history
  156. ├── references/ # On-demand reference docs (loaded per topic)
  157. │ ├── boundaries.md # Interface boundaries, headers, error codes, cache, freshness
  158. │ ├── group-a-quote.md # A. Quotes & Valuation (10 endpoints)
  159. │ ├── group-b-financial.md # B. Financials & Fundamentals (8 endpoints)
  160. │ ├── group-c-capital.md # C. Capital Flow (7 endpoints)
  161. │ ├── group-d-limitup.md # D. Limit-up & Sentiment (4 endpoints)
  162. │ ├── group-e-events.md # E. Events & Information (3 endpoints)
  163. │ ├── group-f-sector.md # F. Sectors & Concepts (4 endpoints)
  164. │ ├── group-g-convertible.md # G. Convertible Bonds (2 endpoints)
  165. │ ├── group-h-quant.md # H. Quant & Technical (2 endpoints)
  166. │ ├── group-i-macro.md # I. Macro (3 endpoints)
  167. │ ├── group-j-tools.md # J. Tools (1 endpoint)
  168. │ ├── group-k-agent.md # K. Agent Enhanced (2 endpoints)
  169. │ ├── examples.md # Multi-endpoint analysis examples (5 scenarios)
  170. │ └── safety-rules.md # Financial output safety constraints (6 rules)
  171. └── scripts/
  172. └── install.sh # One-line install script
  173. ```
  174. **Why multi-file?** A simple query like "what's the price of Moutai" only needs
  175. the entry SKILL.md + one reference file (~4K tokens), instead of loading the
  176. entire 47KB monolith (~15K tokens). This reduces token consumption by 70%+.
  177. ---
  178. ## Basic Usage
  179. All endpoints are HTTP GET, called with `curl`:
  180. ```bash
  181. BASE="https://www.apocdata.com/api/blade-dataplatform/open/data"
  182. # Get real-time quote
  183. curl -s "$BASE/quote?symbol=000001"
  184. # Get stock info (PE/PB/market cap)
  185. curl -s "$BASE/stock?symbol=000001"
  186. # Get comprehensive profile (8 dimensions in one call)
  187. curl -s "$BASE/profile/full?symbol=688017"
  188. ```
  189. ---
  190. ## Endpoint Overview
  191. | Group | Topic | Endpoints |
  192. |-------|-------|-----------|
  193. | A | Quotes & Valuation | 10 |
  194. | B | Financials & Fundamentals | 8 |
  195. | C | Capital Flow | 7 |
  196. | D | Limit-up & Sentiment | 4 |
  197. | E | Events & Information | 2 (+ 1 deprecated) |
  198. | F | Sectors & Concepts | 4 |
  199. | G | Convertible Bonds | 2 |
  200. | H | Quant & Technical | 2 |
  201. | I | Macro | 3 |
  202. | J | Tools | 1 |
  203. | K | Agent Enhanced | 2 |
  204. | **Total** | | **45 active** (+ 1 deprecated) |
  205. ---
  206. ## Editions & Capabilities
  207. ApocData is organized into four editions to match different use cases.
  208. All editions share the same API contract; capabilities are filtered by
  209. edition whitelist. **This Skill defaults to the free-tier open endpoints.
  210. Register to unlock higher quotas and more data capabilities.**
  211. ### Edition Lineup
  212. | SKU | Edition | Target Users |
  213. | ----- | ------------ | ----------------------------------------------------- |
  214. | FREE | Free | Individuals / AI agent demos |
  215. | PRO | Professional | Investment research / content creators |
  216. | QUANT | Quant | Quantitative research teams |
  217. | ENT | Enterprise | Institutional embedding / private deployment |
  218. ### Capability Comparison (selected)
  219. | Capability | Free | Pro | Quant | Enterprise |
  220. | ------------------ | ----------- | -------------- | ------- | ---------------- |
  221. | Daily calls | 2,000 | 50,000 | 300,000 | Custom |
  222. | QPS limit | 2 | 10 | 30 | Custom |
  223. | Snapshot latency | 15 min | 1 min | ≤ 30s | Custom (≤ 10s) |
  224. | Daily K depth | 30 days | 5 yrs + adj. | Full | Full |
  225. | Quant factors | — | 20 | Full | Full + custom |
  226. | MCP Tools | 8 | 14 | 18 | 18+ custom |
  227. | Availability SLO | best-effort | 99.0% | 99.5% | 99.9% (contract) |
  228. | Support | Community | Email 48h | Email 24h | Dedicated channel + phone |
  229. ---
  230. ## Endpoint Verification
  231. > **Last verified:** 2026-08-12 12:21 CST
  232. | Check | Result |
  233. |---|---|
  234. | Core endpoints tested | 12/12 -> HTTP 200
  235. | Total active endpoints | 45 (across 11 groups) |
  236. | Avg latency | ~217ms
  237. | Deprecated | `/news` (HTTP 410, documented in group-e) |
  238. Verified endpoints: `quote`, `stock`, `daily`, `financial`, `moneyflow`, `hsgt`,
  239. `limit-list`, `announcements`, `concepts`, `macro/latest`, `calendar`, `profile/full`.
  240. Full 45-endpoint coverage is validated via the scenario quick-reference table in `SKILL.md`.
  241. ---
  242. ## Notes & Compliance
  243. - Free tier: callable without registration, suited to quick validation and light usage
  244. - Registered users: higher quotas and more data capabilities (see the platform editions page)
  245. - All endpoints are **read-only**
  246. - Data source: ApocData Cloud (天启云), synced with A-share market data
  247. - Free tier quotes have a ~15-minute delay (see `delayed_minutes` in response)
  248. - Announcements: T+0 at 08:00; Northbound capital: 20:00
  249. - This Skill is for **research assistance only** — not investment advice
  250. - Financial output safety constraints are enforced via `references/safety-rules.md`
  251. ---
  252. ## Get Started
  253. Free tier, callable without registration; registered users unlock higher quotas
  254. and more data capabilities.
  255. [Try free →](https://www.apocdata.com) · [Register →](https://www.apocdata.com/register) · [Star on Gitee →](https://gitee.com/apocdata/ApocData-skill)
  256. ---
  257. ## License
  258. See [LICENSE](./LICENSE) for details.
scripts/install.sh · Bundled script · 31 lines · 1 finding marked
  1. #!/usr/bin/env bash
  2. # ApocData Skill — one-line installer
  3. # Usage: curl -sL https://gitee.com/apocdata/ApocData-skill/raw/main/scripts/install.sh | bash
    • Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
    • Line 3 on GitHub
  4. set -euo pipefail
  5. VERSION="${APOCDATA_VERSION:-v2.0.5}"
  6. REPO="apocdata/ApocData-skill"
  7. INSTALL_DIR="${HOME}/.claude/skills/apocdata"
  8. echo "🔧 Installing ApocData Skill ${VERSION}..."
  9. # Create target directory
  10. mkdir -p "${INSTALL_DIR}"
  11. # Download and extract
  12. echo "📦 Downloading from Gitee..."
  13. curl -sL "https://gitee.com/${REPO}/repository/archive/${VERSION}.tar.gz" \
  14. | tar xz -C "${INSTALL_DIR}" --strip-components=1
  15. # Verify
  16. if [ -f "${INSTALL_DIR}/SKILL.md" ] && [ -d "${INSTALL_DIR}/references" ]; then
  17. REF_COUNT=$(find "${INSTALL_DIR}/references" -name "*.md" | wc -l | tr -d ' ')
  18. echo "✅ ApocData Skill ${VERSION} installed successfully!"
  19. echo " Entry: ${INSTALL_DIR}/SKILL.md"
  20. echo " References: ${REF_COUNT} files in ${INSTALL_DIR}/references/"
  21. echo ""
  22. echo "🔄 Restart Claude Code to activate the skill."
  23. else
  24. echo "❌ Installation failed. Please check your network and try again."
  25. exit 1
  26. fi

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.