Apocdata logo

Apocdata

Organization
ApocData
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.

Overview

PublisherApocData
RepositoryApocData-skill
Skill nameapocdata
Stars
102
Forks
1
Bundled files
24
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 24 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by ApocData on GitHub. Read the source before you install it.

Installation

Install the Apocdata AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/ApocData/ApocData-skill/tree/main
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ApocData/ApocData-skill.git \
  .claude/skills/apocdata
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Apocdata in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Apocdata on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Apocdata is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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.jsonOpenAPI 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-detaildate 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 → announcementsst 返回 null 即非 ST
业绩超预期追踪express → financial → survey → announcementsexpress 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10references/group-a-quote.md
B财务与基本面8references/group-b-financial.md
C资金博弈7references/group-c-capital.md
D涨跌停与情绪4references/group-d-limitup.md
E事件与信息3(活跃 2)references/group-e-events.md
F板块/概念4references/group-f-sector.md
G可转债2references/group-g-convertible.md
H量化与技术2references/group-h-quant.md
I宏观3references/group-i-macro.md
J工具1references/group-j-tools.md
KAgent 增强2references/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
daily30quotes10 只
macro12ranking/limit-list/dragon-tiger 等50
announcements30calendar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"

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Apocdata AI skill do?

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,...

Why use Apocdata on TypingMind?

Because you install it once and use it with any model. Apocdata is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Apocdata in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ApocData/ApocData-skill/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Apocdata?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Apocdata?

As many as you like. As long as a model supports skills, you can use Apocdata with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Apocdata AI skill free?

Yes. It is published on GitHub by ApocData under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇