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.
Badge for your README
Markdown
[](/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
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)
- ---
- name: apocdata
- 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."
- ---
- # 天启至数 ApocData — A 股数据服务
- > **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`)、
- > 类型(`category`)、重要性(`importance`)、情感倾向(`sentiment`),条条可溯源(`url`);
- > 并覆盖行情、财务、资金流、龙虎榜、宏观等 45+ 数据接口。
- > 免费体验额度开箱即用,注册解锁更高额度与更多能力。
- > 支持 WorkBuddy / Codex / Hermes / DeepSeek / Kimi / 千问 / 智谱清言等所有 Agent。
- ## 安装
- ```bash
- # v2.0.5 多文件结构(推荐)
- 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
- ```
- 重启 Claude Code 后自动生效。
- ---
- ## 基础用法
- 所有接口均为 HTTP GET,用 curl 直接调用:
- ```bash
- BASE="https://www.apocdata.com/api/blade-dataplatform/open/data"
- # 查单只股票行情
- curl -s "$BASE/quote?symbol=000001"
- # 查股票基本信息(含 PE/PB/市值)
- curl -s "$BASE/stock?symbol=000001"
- ```
- ### OpenAPI 3 接入(GPT Actions / Coze / Dify / n8n / Zapier)
- | 端点 | 用途 |
- |---|---|
- | `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 |
- > 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。
- 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。
- ---
- ## 场景速查(按用户意图找接口组合)
- > 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。
- | 用户意图 | 推荐调用顺序 | 关键说明 |
- |---|---|---|
- | 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%+ |
- | 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 |
- | **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 |
- | 估值评估 / 「贵不贵」 | `stock` → `financial` → `daily?limit=30` | 看 PE/PB/PEG,结合近期走势判断 |
- | 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 |
- | 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 |
- | 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 |
- | 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 |
- | 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 |
- | 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 |
- | 可转债套利 | `convertible-bonds` → `cb-price-chg` → `quote`(正股) | 用 stkCode 反查正股可转债 |
- | 找游资偏好的票 | `hot-money` → `hot-money-detail` → `dragon-tiger` | 当日游资明细 + 历史席位 |
- | 退市/风险排查 | `st` → `share-float` → `holders` → `announcements` | st 返回 null 即非 ST |
- | 业绩超预期追踪 | `express` → `financial` → `survey` → `announcements` | express 是季报前的先行指标 |
- | 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 |
- ---
- ## 接口分组总览
- > 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。
- | 组别 | 主题 | 接口数 | 参考文件 |
- |---|---|---|---|
- | A | 行情与估值 | 10 | `references/group-a-quote.md` |
- | B | 财务与基本面 | 8 | `references/group-b-financial.md` |
- | C | 资金博弈 | 7 | `references/group-c-capital.md` |
- | D | 涨跌停与情绪 | 4 | `references/group-d-limitup.md` |
- | E | 事件与信息 | 3(活跃 2) | `references/group-e-events.md` |
- | F | 板块/概念 | 4 | `references/group-f-sector.md` |
- | G | 可转债 | 2 | `references/group-g-convertible.md` |
- | H | 量化与技术 | 2 | `references/group-h-quant.md` |
- | I | 宏观 | 3 | `references/group-i-macro.md` |
- | J | 工具 | 1 | `references/group-j-tools.md` |
- | K | Agent 增强 | 2 | `references/group-k-agent.md` |
- ---
- ## 参考文件导航
- 根据用户需求,读取对应的参考文件获取完整接口细节:
- ### 全局规则(优先读取)
- | 参考文件 | 何时读取 |
- |---------|---------|
- | `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 |
- | `references/safety-rules.md` | 生成任何金融分析输出前(强制行为规则) |
- ### 接口字典(按主题按需加载)
- | 参考文件 | 何时读取 |
- |---------|---------|
- | `references/group-a-quote.md` | 查行情、估值、排行、指数、搜索股票、ST 状态 |
- | `references/group-b-financial.md` | 查财务报表、分红、股东、回购、大宗交易、限售解禁 |
- | `references/group-c-capital.md` | 查资金流、北向资金、两融、龙虎榜、游资 |
- | `references/group-d-limitup.md` | 查涨跌停、连板天梯、板块资金流、筹码分布 |
- | `references/group-e-events.md` | 查公告、机构调研(新闻已下线) |
- | `references/group-f-sector.md` | 查概念板块(东方财富)、行业板块(同花顺)、成分股 |
- | `references/group-g-convertible.md` | 查可转债列表、转股价变动 |
- | `references/group-h-quant.md` | 查量化因子注册表、个股技术面因子 |
- | `references/group-i-macro.md` | 查 GDP/CPI/PPI/PMI 宏观数据 |
- | `references/group-j-tools.md` | 查交易日历 |
- | `references/group-k-agent.md` | 用 profile/full 综合画像、factor-categories 因子分类 |
- ### 示例与场景
- | 参考文件 | 何时读取 |
- |---------|---------|
- | `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) |
- ---
- ## 调用工作流
- 1. **收到用户意图** → 先查上方「场景速查表」确定接口组合
- 2. **首次调用前** → 读取 `references/boundaries.md` 了解 limit 上限和参数易错点
- 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`
- 4. **生成分析输出前** → 读取 `references/safety-rules.md` 遵守强制行为规则
- 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
- ---
- ## 关键约束速记(调任何接口前先扫一眼)
- ### limit 上限(超限静默截断,不报错)
- | 接口 | 上限 | 接口 | 上限 |
- |---|---|---|---|
- | `daily` | 30 | `quotes` | 10 只 |
- | `macro` | 12 | `ranking`/`limit-list`/`dragon-tiger` 等 | 50 |
- | `announcements` | 30 | `calendar` | 跨度 ≤ 366 天(**超范围会报错**) |
- ### 参数易错点
- - **枚举参数优先用英文**:`sector-flow?type=industry/concept/region`
- - **中文关键字必须 URL 编码**:用 `curl -G --data-urlencode "q=年报"`
- - **symbol vs tsCode**:A 股 `symbol=000001`(6 位);指数 `tsCode=000300.SH`;可转债 `stkCode=688535.SH`
- - **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
- - **错误响应**:HTTP 400 + `success=false` + `X-Tdc-Error-Code` header;先检查状态再读 data
- - **不存在 symbol**:返回 `RESOURCE_NOT_FOUND`,先用 `stocks` 搜索确认
- - **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
- > 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`。
- ---
- ## 注意事项
- - 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
- - symbol 统一 **6 位数字代码**;指数/可转债用带后缀的 `tsCode`
- - 单次请求超时建议 10 秒;复杂画像优先**并发**调用
- - **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
- - **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
- - **token 紧张时**:用 `?fields=` 裁剪 + `?format=compact` 紧凑模式,可省 60-90% token
- - **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
- - 输出分析必须标注数据时效(`trade_date` / `delayed_minutes` / Freshness header)
- - 数据来源:天启云(ApocData Cloud),公告 T+0 08:00,北向 20:00
- ---
- ## 金融输出安全约束(摘要)
- > 完整规则见 `references/safety-rules.md`。以下为 6 条强制规则摘要:
- 1. **数据时效透明** — 每次输出必须显示 `trade_date` / `delayed_minutes`
- 2. **数据来源分层** — 区分原始数据、AI 摘要、模型推断
- 3. **异常数据约束** — `success=false` 或关键字段缺失时停止确定性结论
- 4. **交叉验证** — 关键数据至少两个来源确认
- 5. **禁止买卖指令** — 严禁"买入/卖出/必涨/稳赚"等确定性表述
- 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)
- # 天启至数 ApocData — A股数据服务 (ApocData A-Share Data Skill)
- <p align="center">
- <b>English</b> |
- <a href="./README.zh-CN.md">简体中文</a>
- </p>
- <p align="center">
- <img src="https://img.shields.io/badge/endpoints-45-green" alt="45 endpoints"/>
- <img src="https://img.shields.io/badge/MCP-46_tools-blue" alt="MCP 46 tools"/>
- <img src="https://img.shields.io/badge/free_tier-available-brightgreen" alt="Free tier available"/>
- <img src="https://img.shields.io/badge/license-Apache_2.0-blue" alt="License"/>
- </p>
- > ## Let AI read A-share announcements
- >
- > **The A-share announcements and fundamentals database built for AI · parsed · structured · traceable**
- > 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.
- The [`SKILL.md`](./SKILL.md) in this repository is a capability card that can
- be loaded directly into AI agents, letting LLMs query A-share market data
- and complete research tasks without any SDK.
- ---
- ## Quick Try
- Copy-paste and run, no config needed:
- ```bash
- curl -s "https://www.apocdata.com/api/blade-dataplatform/open/data/quote?symbol=600519"
- ```
- <details>
- <summary>Click to expand sample response</summary>
- ```json
- {
- "code": 200, "success": true,
- "data": {
- "symbol": "600519", "name": "Kweichow Moutai",
- "close": 1528.00, "pct_chg": -0.52,
- "volume": 2856321, "delayed_minutes": 15
- }
- }
- ```
- *Actual response has more fields; above is a simplified example.*
- </details>
- ---
- ## Announcement Parsing — from PDF to structured data
- 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.
- Every announcement carries:
- - **AI summary** (`summary`) — the key facts extracted, no need to read the full document
- - **Category** (`category`) — earnings, dividend, buyback, share increase/decrease, litigation and more, filterable programmatically
- - **Importance level** (`importance`) — locate the announcements that actually matter
- - **Sentiment** (`sentiment`) — positive / negative / neutral, to help judge the direction of impact
- - **Source link** (`url`) — every conclusion traces back to the original announcement
- Also returned: `title`, `ann_date`, `publish_time`, `keywords`, `source`, and
- `content` (full Markdown body, on `includeContent=true`).
- Covers all-market announcements, including Stock Connect constituents, ST and delisting-risk securities.
- ---
- ## Why ApocData?
- | | **ApocData** | 数据源A | 数据源B | 数据源C |
- |---|---|---|---|---|
- | Announcement parsing | **Structured + AI summary + sentiment** | Raw text | Raw text | Raw text |
- | Access | **Free tier, no registration** | Paid token | Python env + install | Application approval |
- | Setup steps | **0** | 3+ (register → token → config) | 2+ (pip + deps) | Manual review |
- | AI Agent native | **Skill + MCP** | Plugin (legacy) | Not supported | Not supported |
- | curl one-liner | **Direct** | Need SDK | Need SDK | Need SDK |
- | A-share endpoints | **45** | 100+ (paywalled) | 100+ (free) | 200+ (paid) |
- | MCP support | **46 tools** | None | None | None |
- *Comparison based on publicly available info as of 2026-08.*
- ---
- ## Core Capabilities
- - **Announcement parsing** — all-market announcements parsed by AI into structured fields
- (`title` / `category` / `importance` / `ann_date` / `summary` / `sentiment` / `url`), directly
- usable for reasoning and traceable to the source document (mainstream data sources mostly ship
- announcements as raw text)
- - **Full-dimension coverage** — quotes, financials, valuation, capital flows, limit-up review,
- dragon-tiger lists, sectors & concepts, convertible bonds, macro indicators and trading
- calendar: 11 groups, 45+ endpoints, one consistent definition set
- - **Multiple integration paths** — Skill package (one-command install), MCP server (46 tools),
- plain HTTP endpoints (direct curl), covering every mainstream AI ecosystem
- - **Traceable** — every data point traces back to the original announcement, so AI conclusions
- can be checked
- ---
- ## Table of Contents
- - [Announcement Parsing](#announcement-parsing--from-pdf-to-structured-data)
- - [Why ApocData?](#why-apocdata)
- - [Core Capabilities](#core-capabilities)
- - [Overview](#overview)
- - [Use Cases](#use-cases)
- - [Data Service Platform](#data-service-platform)
- - [Installation](#installation)
- - [Project Structure](#project-structure)
- - [Basic Usage](#basic-usage)
- - [Endpoint Overview](#endpoint-overview)
- - [Editions & Capabilities](#editions--capabilities)
- - [Notes & Compliance](#notes--compliance)
- ---
- ## Overview
- ApocData is the A-share announcements and data layer built for AI: parsed,
- structured, traceable. Announcement parsing is the core — every announcement
- becomes structured data an agent can reason over directly — and around it sits
- full-dimension coverage of quotes, financials, capital flows, dragon-tiger
- lists, quantitative factors and macro indicators, designed for AI agents,
- quantitative research, investment content, and institutional applications.
- ---
- ## Use Cases
- - *"What are the key points in Kweichow Moutai's recent earnings flash?"* → key
- figures extracted as structured fields, traceable to the original announcement
- - *"Analyse the valuation of 688017 — how does it compare with its peers?"* →
- PE/PB/market cap aggregated with financial metrics and the last 30 sessions
- - *"Which ST stocks published material announcements in the past 30 days?"* →
- ranked by risk level, each with an AI summary and a source link
- - *"Which sectors has northbound capital been flowing into?"* → Stock Connect
- plus sector capital flows, with the top inflow sectors summarised automatically
- ---
- ## Data Service Platform
- **Platform URL:** <https://www.apocdata.com>
- The data service platform is the unified entry point for ApocData. It provides:
- - **Open API (free tier)** — This is what the Skill connects to. A free trial
- quota is callable straight away, ideal for quick validation and lightweight usage.
- - **OpenAPI documentation & SDKs** — Python / TypeScript supported.
- - **Registered & Professional editions (with API key)** — Higher quotas, deeper history,
- lower latency, and richer data fields. See [Editions & Capabilities](#editions--capabilities).
- > The base URL used by this Skill: `https://www.apocdata.com/api/blade-dataplatform/open/data`
- ---
- ## Installation
- ### Quick Install (recommended)
- ```bash
- 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)
- ```json
- {
- "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
- ```bash
- 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
- ```
- ---
- ## Project Structure
- This Skill uses a **multi-file structure** for progressive loading — the entry
- `SKILL.md` is a slim router (~180 lines), and detailed endpoint specs are
- loaded on demand from the `references/` directory:
- ```
- ├── SKILL.md # Entry point (slim router, ~180 lines)
- ├── README.md # This file (human-facing docs)
- ├── CHANGELOG.md # Version history
- ├── references/ # On-demand reference docs (loaded per topic)
- │ ├── boundaries.md # Interface boundaries, headers, error codes, cache, freshness
- │ ├── group-a-quote.md # A. Quotes & Valuation (10 endpoints)
- │ ├── group-b-financial.md # B. Financials & Fundamentals (8 endpoints)
- │ ├── group-c-capital.md # C. Capital Flow (7 endpoints)
- │ ├── group-d-limitup.md # D. Limit-up & Sentiment (4 endpoints)
- │ ├── group-e-events.md # E. Events & Information (3 endpoints)
- │ ├── group-f-sector.md # F. Sectors & Concepts (4 endpoints)
- │ ├── group-g-convertible.md # G. Convertible Bonds (2 endpoints)
- │ ├── group-h-quant.md # H. Quant & Technical (2 endpoints)
- │ ├── group-i-macro.md # I. Macro (3 endpoints)
- │ ├── group-j-tools.md # J. Tools (1 endpoint)
- │ ├── group-k-agent.md # K. Agent Enhanced (2 endpoints)
- │ ├── examples.md # Multi-endpoint analysis examples (5 scenarios)
- │ └── safety-rules.md # Financial output safety constraints (6 rules)
- └── scripts/
- └── install.sh # One-line install script
- ```
- **Why multi-file?** A simple query like "what's the price of Moutai" only needs
- the entry SKILL.md + one reference file (~4K tokens), instead of loading the
- entire 47KB monolith (~15K tokens). This reduces token consumption by 70%+.
- ---
- ## Basic Usage
- All endpoints are HTTP GET, called with `curl`:
- ```bash
- BASE="https://www.apocdata.com/api/blade-dataplatform/open/data"
- # Get real-time quote
- curl -s "$BASE/quote?symbol=000001"
- # Get stock info (PE/PB/market cap)
- curl -s "$BASE/stock?symbol=000001"
- # Get comprehensive profile (8 dimensions in one call)
- curl -s "$BASE/profile/full?symbol=688017"
- ```
- ---
- ## Endpoint Overview
- | Group | Topic | Endpoints |
- |-------|-------|-----------|
- | A | Quotes & Valuation | 10 |
- | B | Financials & Fundamentals | 8 |
- | C | Capital Flow | 7 |
- | D | Limit-up & Sentiment | 4 |
- | E | Events & Information | 2 (+ 1 deprecated) |
- | F | Sectors & Concepts | 4 |
- | G | Convertible Bonds | 2 |
- | H | Quant & Technical | 2 |
- | I | Macro | 3 |
- | J | Tools | 1 |
- | K | Agent Enhanced | 2 |
- | **Total** | | **45 active** (+ 1 deprecated) |
- ---
- ## Editions & Capabilities
- ApocData is organized into four editions to match different use cases.
- All editions share the same API contract; capabilities are filtered by
- edition whitelist. **This Skill defaults to the free-tier open endpoints.
- Register to unlock higher quotas and more data capabilities.**
- ### Edition Lineup
- | SKU | Edition | Target Users |
- | ----- | ------------ | ----------------------------------------------------- |
- | FREE | Free | Individuals / AI agent demos |
- | PRO | Professional | Investment research / content creators |
- | QUANT | Quant | Quantitative research teams |
- | ENT | Enterprise | Institutional embedding / private deployment |
- ### Capability Comparison (selected)
- | Capability | Free | Pro | Quant | Enterprise |
- | ------------------ | ----------- | -------------- | ------- | ---------------- |
- | Daily calls | 2,000 | 50,000 | 300,000 | Custom |
- | QPS limit | 2 | 10 | 30 | Custom |
- | Snapshot latency | 15 min | 1 min | ≤ 30s | Custom (≤ 10s) |
- | Daily K depth | 30 days | 5 yrs + adj. | Full | Full |
- | Quant factors | — | 20 | Full | Full + custom |
- | MCP Tools | 8 | 14 | 18 | 18+ custom |
- | Availability SLO | best-effort | 99.0% | 99.5% | 99.9% (contract) |
- | Support | Community | Email 48h | Email 24h | Dedicated channel + phone |
- ---
- ## Endpoint Verification
- > **Last verified:** 2026-08-12 12:21 CST
- | Check | Result |
- |---|---|
- | Core endpoints tested | 12/12 -> HTTP 200
- | Total active endpoints | 45 (across 11 groups) |
- | Avg latency | ~217ms
- | Deprecated | `/news` (HTTP 410, documented in group-e) |
- Verified endpoints: `quote`, `stock`, `daily`, `financial`, `moneyflow`, `hsgt`,
- `limit-list`, `announcements`, `concepts`, `macro/latest`, `calendar`, `profile/full`.
- Full 45-endpoint coverage is validated via the scenario quick-reference table in `SKILL.md`.
- ---
- ## Notes & Compliance
- - Free tier: callable without registration, suited to quick validation and light usage
- - Registered users: higher quotas and more data capabilities (see the platform editions page)
- - All endpoints are **read-only**
- - Data source: ApocData Cloud (天启云), synced with A-share market data
- - Free tier quotes have a ~15-minute delay (see `delayed_minutes` in response)
- - Announcements: T+0 at 08:00; Northbound capital: 20:00
- - This Skill is for **research assistance only** — not investment advice
- - Financial output safety constraints are enforced via `references/safety-rules.md`
- ---
- ## Get Started
- Free tier, callable without registration; registered users unlock higher quotas
- and more data capabilities.
- [Try free →](https://www.apocdata.com) · [Register →](https://www.apocdata.com/register) · [Star on Gitee →](https://gitee.com/apocdata/ApocData-skill)
- ---
- ## License
- See [LICENSE](./LICENSE) for details.
scripts/install.sh · Bundled script · 31 lines · 1 finding marked
- #!/usr/bin/env bash
- # ApocData Skill — one-line installer
- # 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
- set -euo pipefail
- VERSION="${APOCDATA_VERSION:-v2.0.5}"
- REPO="apocdata/ApocData-skill"
- INSTALL_DIR="${HOME}/.claude/skills/apocdata"
- echo "🔧 Installing ApocData Skill ${VERSION}..."
- # Create target directory
- mkdir -p "${INSTALL_DIR}"
- # Download and extract
- echo "📦 Downloading from Gitee..."
- curl -sL "https://gitee.com/${REPO}/repository/archive/${VERSION}.tar.gz" \
- | tar xz -C "${INSTALL_DIR}" --strip-components=1
- # Verify
- if [ -f "${INSTALL_DIR}/SKILL.md" ] && [ -d "${INSTALL_DIR}/references" ]; then
- REF_COUNT=$(find "${INSTALL_DIR}/references" -name "*.md" | wc -l | tr -d ' ')
- echo "✅ ApocData Skill ${VERSION} installed successfully!"
- echo " Entry: ${INSTALL_DIR}/SKILL.md"
- echo " References: ${REF_COUNT} files in ${INSTALL_DIR}/references/"
- echo ""
- echo "🔄 Restart Claude Code to activate the skill."
- else
- echo "❌ Installation failed. Please check your network and try again."
- exit 1
- fi
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.