Agent skill

Kimi Datasource

Universal data-source assistant for stocks (Wind, S&P, SEC EDGAR), macro (World Bank, IMF, FRED, NBS), Chinese government data and standards (GB/HB/DB/TT), corporate, academic, legal, WHO/FAO/OECD…

MITAuto-check passedAgent Workflows

Install Kimi Datasource

skills CLI

$ npx skills add MoonshotAI/kimi-code --skill kimi-datasource -a claude-code

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

GitHub CLI

$ gh skill install MoonshotAI/kimi-code kimi-datasource --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/MoonshotAI/kimi-code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/official/kimi-datasource .claude/skills/kimi-datasource && 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/

Paste into Claude Code

Install the "kimi-datasource" agent skill from https://github.com/MoonshotAI/kimi-code/tree/main/plugins/official/kimi-datasource into .claude/skills/kimi-datasource/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kimi-datasource", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/MoonshotAI/kimi-code/tree/main/plugins/official/kimi-datasource

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add MoonshotAI/kimi-code --skill kimi-datasource -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install MoonshotAI/kimi-code kimi-datasource --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/MoonshotAI/kimi-code.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/official/kimi-datasource .agents/skills/kimi-datasource && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "kimi-datasource" agent skill from https://github.com/MoonshotAI/kimi-code/tree/main/plugins/official/kimi-datasource into .agents/skills/kimi-datasource/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kimi-datasource", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add MoonshotAI/kimi-code --skill kimi-datasource -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install MoonshotAI/kimi-code kimi-datasource --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/MoonshotAI/kimi-code.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/official/kimi-datasource .cursor/skills/kimi-datasource && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "kimi-datasource" agent skill from https://github.com/MoonshotAI/kimi-code/tree/main/plugins/official/kimi-datasource into .cursor/skills/kimi-datasource/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kimi-datasource", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/MoonshotAI/kimi-code.git --path plugins/official/kimi-datasource

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add MoonshotAI/kimi-code --skill kimi-datasource -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install MoonshotAI/kimi-code kimi-datasource --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/MoonshotAI/kimi-code.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/official/kimi-datasource .gemini/skills/kimi-datasource && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "kimi-datasource" agent skill from https://github.com/MoonshotAI/kimi-code/tree/main/plugins/official/kimi-datasource into .gemini/skills/kimi-datasource/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kimi-datasource", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install MoonshotAI/kimi-code kimi-datasource

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add MoonshotAI/kimi-code --skill kimi-datasource -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/MoonshotAI/kimi-code.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/official/kimi-datasource .github/skills/kimi-datasource && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "kimi-datasource" agent skill from https://github.com/MoonshotAI/kimi-code/tree/main/plugins/official/kimi-datasource into .github/skills/kimi-datasource/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kimi-datasource", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add MoonshotAI/kimi-code --skill kimi-datasource -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install MoonshotAI/kimi-code kimi-datasource --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/MoonshotAI/kimi-code.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/official/kimi-datasource .opencode/skills/kimi-datasource && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "kimi-datasource" agent skill from https://github.com/MoonshotAI/kimi-code/tree/main/plugins/official/kimi-datasource into .opencode/skills/kimi-datasource/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kimi-datasource", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: kimi-datasource
GitHub stars: 7.8k
Token cost: ~1.8k tokens
SKILL.md length: 493 words
Files: 6
Skills in repo: 11
Repo updated: Oct 8, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Universal data-source assistant for stocks (Wind, S&P, SEC EDGAR), macro (World Bank, IMF, FRED, NBS), Chinese government data and standards (GB/HB/DB/TT), corporate, academic, legal, WHO/FAO/OECD…

Works in 7 steps: 调用方式 → 这个 skill 提供什么能力 → 标准工作流：get_data_source_desc →… → …
Tasks that involve MCP servers
SKILL.md covers 0. 调用方式, 1. 这个 skill 提供什么能力, 2. 标准工作流：get_data_source_desc… and 3. 调用前的几条铁律, plus 3 more sections
Runs JavaScript scripts from its folder

What it does

Kimi Datasource is an agent skill from MoonshotAI/kimi-code. Universal data-source assistant for stocks (Wind, S&P, SEC EDGAR), macro (World Bank, IMF, FRED, NBS), Chinese government data and standards (GB/HB/DB/TT), corporate, academic, legal, WHO/FAO/OECD and other IGO data, financial news (Xinhua, Caixin). This plugin exposes tools via MCP server plugin-kimi-datasourcedata; call them in the flow mcpplugin-kimi-datasourcedatagetdatasourcedesc → mcpplugin-kimi-datasourcedatacalldatasourcetool.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files (for example `CHANGELOG.md`, `kimi.plugin.json` and `watchlist.json`).

It sits in Agent Workflows, covering MCP servers. It works with Kimi, Model Context Protocol and SEC EDGAR. The repository describes itself as: Kimi Code CLI — The Starting Point for Next-Gen Agents. The licence is MIT.

When your agent uses it

Tasks that involve MCP servers

Example prompts

“/kimi-datasource”

Requirements

Node.js

Workflow steps

7 steps, taken from the step headings in SKILL.md.

调用方式
这个 skill 提供什么能力
标准工作流：get_data_source_desc → call_data_source_tool
调用前的几条铁律
怎么读返回结果
watchlist.json — 用户自选股
注意事项

What it can do on your machine

Read from SKILL.md and the folder at commit 0f052fe. 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
Ships script files (JavaScript), which the agent can run.
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

Kimi Datasource loads about 1.8k tokens when it runs. Until then it costs about 119 tokens; SKILL.md has 493 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~119
When it runs · the whole SKILL.md, loaded when a task matches: ~1.8k

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 MoonshotAI/kimi-code at commit 0f052fe, republished under its MIT licence (© MoonshotAI). 493 words, ~1,830 tokens.

Download SKILL.mdSave it as .claude/skills/kimi-datasource/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.

name: kimi-datasource
description: Universal data-source assistant for stocks (Wind, S&P, SEC EDGAR), macro (World Bank, IMF, FRED, NBS), Chinese government data and standards (GB/HB/DB/TT), corporate, academic, legal, WHO/FAO/OECD and other IGO data, financial news (Xinhua, Caixin). This plugin exposes tools via MCP server `plugin-kimi-datasource_data`; call them in the flow `mcp__plugin-kimi-datasource_data__get_data_source_desc` → `mcp__plugin-kimi-datasource_data__call_data_source_tool`.

kimi-datasource — 通用数据源助手

0. 调用方式

本 skill 使用 datasource MCP server 注册的两个工具，不要通过 Bash 手动执行脚本：

mcp__plugin-kimi-datasource_data__get_data_source_desc
mcp__plugin-kimi-datasource_data__call_data_source_tool

这两个工具由 Kimi Code 托管执行，参数直接按 tool schema 传 JSON。

工具会读取当前 Kimi Code 环境对应的本地 OAuth 登录凭据；当设置了 KIMI_CODE_OAUTH_HOST / KIMI_CODE_BASE_URL 时，会使用对应环境的隔离凭据。如果没有登录凭据，让用户先在 Kimi Code 里执行 /login。

1. 这个 skill 提供什么能力

本 plugin 后面挂了 25 个外部数据源。每一行的"数据源名"就是传给 get_data_source_desc 的 name。

能力域	数据源名	典型问题
A股 / 港股 / 美股行情和财务	`stock_finance_data`	"茅台现在多少钱"、"宁德时代 2024 年财报"、"腾讯股东"、"杭州的人工智能股票"
Yahoo Finance 全球金融	`yahoo_finance`	"苹果分析师评级"、"AAPL 期权链"、"苹果前十大机构股东"
世界银行历史宏观	`world_bank_open_data`	"中国历年 GDP"、"印度通胀率"、"各国人口增长对比"
中国企业工商信息	`tianyancha`	"字节跳动股东"、"比亚迪司法风险"、"宁德时代专利"
arXiv 论文预印本	`arxiv`	"找 RAG 综述"、"下载 2406.xxxxx"
Google Scholar 学术搜索	`scholar`	"Hinton 最新论文"、"transformer 综述高引文献"
中国法律法规 / 司法案例	`yuandian_law`	"民法典关于居住权的规定"、"帮我查劳动合同解除的相关法条"、"找几个不当得利的判例"
Wind 万得（A股/基金/债券/宏观）	`wind`	"茅台今天的分钟线"、"十年期国债收益率走势"、"基金净值查询"
IMF 国际宏观（汇率 / CPI / 预测）	`imf`	"美元兑人民币汇率"、"各国 GDP 增速预测"、"全球通胀率对比"
恒生聚源智能筛选	`gildata`	"筛选净利润增速超 30% 且 ROE 大于 15% 的股票"、"基金经理筛选"
美股 SEC 披露文件	`sec_edgar`	"特斯拉 10-K 年报"、"苹果 10-Q 季报"、"Form 4 内部人交易"、"13F 机构持仓"
S&P Capital IQ 美股基本面	`sp_data`	"苹果分析师一致预期"、"美股估值比率对比"、"竞争对手关系"
中国政府开放数据目录（国家数据局）	`china_nda`	"全国公共数据资源登记目录里有什么"、"各省开放数据平台有哪些数据集"
国家统计局宏观指标	`china_nbs`	"中国历年 GDP 官方口径"、"各省市人口与就业统计"、"社会消费品零售总额"
中国标准查询（国标 / 行标 / 地标 / 团标）	`china_standards`	"查 GB 国家标准全文"、"某行业的现行行业标准"
WHO 全球健康	`who`	"全球婴儿死亡率"、"各国预期寿命"
FAO 农业粮食	`fao`	"各国粮食产量"、"农产品价格"
联合国统计司 UNdata	`unsd`	"联合国成员国统计年鉴表"、"国际贸易统计"
欧洲央行统计	`ecb`	"欧元区基准利率"、"欧元区货币供应量"
欧盟统计局	`eurostat`	"欧盟各国失业率"、"欧元区 CPI"
联合国儿童基金会	`unicef`	"全球儿童营养指标"、"儿童免疫接种率"
OECD 数据	`oecd`	"OECD 国家 GDP 对比"、"成员国教育支出"
FRED 美国/全球宏观	`fred`	"美国 CPI 长时间序列"、"联邦基金利率走势"
新华财经新闻公告	`xhcj`	"新华财经快讯"、"A 股公司公告"、"行业政策新闻"
财新数据库	`caixin`	"财新数据接口检索"、"财新新闻与数据"

选源原则

用户点名了数据源 → 直接用指定的源。
没点名 → 按能力域从上表选最匹配的一个；结合下面的"能力边界参考"和用户问题的深度、范围自行判断。
一次简单查询只选一个数据源，不要并行读取其他源的 desc。选定的源成功返回且已经覆盖用户问题后，立即回答；不要为了补充字段、重新格式化或交叉验证继续调用其他 API。只有用户明确要求跨源对比时，才能查询第二个数据源。

能力边界参考（客观事实，选源时考虑）

yahoo_finance 的外汇历史最多 2 年；imf 提供长期的汇率、CPI、GDP 预测和国际收支序列
stock_finance_data 的行情是实时/收盘快照；分钟级分时序列在 wind（另有基金、债券、国债收益率）
股东 / 机构持仓：yahoo_finance、sec_edgar（13F）、sp_data（S&P 标准化持有人）都覆盖，口径和深度不同
world_bank_open_data 是 50 年以上的历史宏观序列；要 IMF 的预测值用 imf
gildata 的查询输入是自然语言条件（选股 / 选基金 / 基金经理筛选），tianyancha 是企业工商档案
wind 的 indexes/indicators 参数要求 Wind 原生字段名；PE/PB/ROE/总市值这类常用字段先调 wind_search_fields 映射（支持别名和中文，一次查一个），不要硬猜字段名
中国官方统计口径：china_nbs 是国家统计局宏观指标序列（GDP / CPI / PPI 等，全国 / 省 / 主要城市），china_nda 是国家数据局的开放数据目录（回答"有什么数据集可用"）；world_bank_open_data 和 imf 是国际口径的历史与预测序列
WHO、FAO、UNSD、ECB、Eurostat、UNICEF、OECD、FRED 各自是独立数据源，按机构名直接选；IMF 自己的数据集（汇率 / CPI / GDP 预测）走 imf
国家标准（gb）、行业标准（hb）、地方标准（db）、团体标准（tt）查 china_standards；法律法规与判例在 yuandian_law，别混
新华财经（xhcj）偏公告 / 快讯 / 政策新闻；caixin 覆盖 600+ 财新数据接口，先用它的 caixin_api_search 找合适接口再调用

不支持的能力：通用 Web 搜索，以及 xhcj / caixin 覆盖之外的实时新闻。

2. 标准工作流：`get_data_source_desc` → `call_data_source_tool`

后端可用 API 经常会调整，这份 skill 故意不抄具体的 API 名和参数表。每次调用前你都应当现场问数据源："你都有什么接口？"

1. 根据用户问题，从上表只挑一个 data_source_name
2. 执行 get_data_source_desc，读取该数据源的 Markdown 文档
3. 仔细读返回的 Markdown，里面列了：
     - 该数据源整体说明（含 ticker 格式、全局约束）
     - 每个 API 的描述 / 必填参数 / 可选参数 / 默认值 / 取值范围
4. 选最匹配的 API，按文档拼 params
5. 执行 call_data_source_tool 取数；需要先发现接口 / 字段 / 实体的源（caixin_api_search、wind_search_fields、天眼查公司搜索），发现类调用不受“一次”限制，继续调到真正的取数 API。结果成功且已经覆盖问题时停止调用
6. 读返回结果，用用户提问时使用的语言回答

例 1：用户问"茅台最近一年走势"

股票走势 → stock_finance_data
调用 mcp__plugin-kimi-datasource_data__get_data_source_desc，参数 {"name":"stock_finance_data"}
从文档里找到"获取历史价格"那个 API，看它要 ticker / start_date / end_date / file_path 等
用 web_search 核对 → 茅台 = 600519.SH
调用 mcp__plugin-kimi-datasource_data__call_data_source_tool，参数形如 {"data_source_name":"stock_finance_data","api_name":"<文档里写的 api>","params":{"ticker":"600519.SH","start_date":"...","end_date":"...","file_path":"/tmp/mao_1y.csv"}}

Show full SKILL.md (189 more words)Show less

例 2：用户问"找几篇 retrieval augmented generation 的综述"

论文搜索 → arxiv（或 scholar，arxiv 更适合预印本，scholar 引用更全）
调用 mcp__plugin-kimi-datasource_data__get_data_source_desc，参数 {"name":"arxiv"}
从文档里找到搜索类 API，看它要 query / file_path / max_results 等
执行 call_data_source_tool

例 3：用户问"字节跳动有哪些股东"

企业工商 → tianyancha
调用 mcp__plugin-kimi-datasource_data__get_data_source_desc，参数 {"name":"tianyancha"}
注意：tianyancha 的 API 是动态注册的，文档会指引你先用搜索类接口找到合适的 API 名，再调用
必须使用企业全称（"北京字节跳动科技有限公司"），不要用简称。不知道全称就先用 tianyancha 文档里的"公司搜索"接口查

3. 调用前的几条铁律

3.1 股票代码必须核对，不能凭记忆猜

A 股 .SH/.SZ/.BJ，港股 .HK，美股 .US 等。用户通常只说中文名（"茅台"、"宁德时代"、"腾讯"），不会给代码。

调任何股票相关 API 前，先用 web_search / WebSearch 一类联网工具确认正确代码 + 后缀。

如果当前环境没有任何联网工具，让用户亲口确认代码，不要硬猜。错了的话接口会静默返回错数据或空数据。

3.2 企业相关查询必须用全称

tianyancha 拒收"特斯拉"、"网易"、"腾讯"这种简称，必须给"北京特斯拉销售有限公司"这种全名。不知道全名时，先调它的公司搜索 API。

3.3 多数 API 需要 `file_path`

绝大部分数据源 API 把完整结果以 CSV 形式写到 file_path。漏传会报 Missing required parameters: file_path。不知道传啥时，给一个 /tmp/<场景>_<时间戳>.csv 即可。

3.4 一次调用不要堆太多 ticker

stock_finance_data 的实时接口最多 3 个 ticker，历史接口最多 10 个。超过会被截断或报错。多了就分批调。

4. 怎么读返回结果

call_data_source_tool 的 stdout 一般含两段：

data_preview：CSV 头 + 前几行（通常 1~3 行），方便你直接答简单问题
CSV 数据已写入：/tmp/xxx.csv：完整数据落盘路径

策略：

用户只问"XX 现在多少钱"、"中国 2023 GDP 多少"这种单值 → data_preview 一般够，直接答
用户要画图、对比、算盈亏、列清单 → 用 Read 工具把 CSV 读出来再处理
混合 A+港股查询时服务端会自动把 CSV 拆成 _a.csv / _hk.csv 两份，原 file_path 那个文件不存在

如果接口返回失败，提示文字一般会写明原因（参数不对 / 不支持 / 数据空等）。把人话原因反馈给用户，不要硬走第二次。

5. `watchlist.json` — 用户自选股

${KIMI_SKILL_DIR}/watchlist.json 是用户的自选股列表。用户问"看一下我的自选股"时，读这个文件，再走标准 get_data_source_desc("stock_finance_data") → call_data_source_tool 流程查实时行情；文档里的实时接口最多 3 个 ticker 一批，多了分批调。

格式：

json

[
  {"code": "600519.SH", "name": "贵州茅台"},
  {"code": "0700.HK", "name": "腾讯控股", "hold_cost": 350.5, "hold_quantity": 100}
]

code 和 name 必填；hold_cost 和 hold_quantity 可选
两者都有时顺便算盈亏：(当前价 - hold_cost) * hold_quantity
用户说"帮我加 XX 到自选股"时：先 web_search 核对代码，再追加到 JSON 数组

6. 注意事项

回答用户时，使用用户提问时使用的语言。如果用户用中文问，就用中文答；如果用户用英文问，就用英文答；用其他语言问，就用其他语言答。
不要凭记忆猜股票代码 / 企业全称。错代码会让接口静默返回错数据，用户察觉不到
不要在没读 desc 的情况下硬传 api_name。后端会报 API_NOT_FOUND。除非这次会话里你已经读过该数据源的 desc 并记得参数
不要给投资建议。给完数据加一句"AI 生成，不构成投资建议"即可
如果某个数据源接口返回的报错明显是后端 bug（参数 schema 自相矛盾、内部 Python 报错等），汇报错误给用户，不要硬试——这种 bug 我们这边修不了，要后端服务侧改

Files

SKILL.md and 5 other files in plugins/official/kimi-datasource of MoonshotAI/kimi-code.

SKILL.md
.gitignore
CHANGELOG.md
bin/kimi-datasource.mjs
kimi.plugin.json
watchlist.json

Open the folder on GitHubat commit 0f052fe

Compare with similar skills

Kimi Datasource 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.

Kimi Datasource compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Kimi Datasource this skillMoonshotAI/kimi-code	7.8k	—	~1.8k	Automated safety check: Pass	MIT	today
Add CoordinatorFeiZhuLulu/Agent-Bridge	107	—	~1.9k	Automated safety check: Pass	MIT	yesterday
Perplexity Web MCP Bridgejacob-bd/perplexity-web-mcp	196	—	~7.6k	Automated safety check: Pass	MIT	3 days ago
Sec Risk FactorsOctagonAI/skills	127	—	~1.6k	Automated safety check: Pass	MIT	4 mo ago
MCP Server Builderanthropics/skills	180k	64 repos	~2.3k	Automated safety check: Pass	Apache-2.0	2 days ago
MCP Server BuildershareAI-lab/learn-claude-code	78k	5 repos	~1.2k	Automated safety check: Pass	MIT	9 days ago

Similar skills

Add Coordinator
FeiZhuLulu/Agent-Bridge
Verify that a new host can act as an Agent Bridge coordinator over stdio MCP.
107 GitHub stars~1.9k tokensUpdated yesterday
Agent WorkflowsAuto-check passed
Perplexity Web MCP Bridge
jacob-bd/perplexity-web-mcp
Searches the web and queries premium AI models through Perplexity's own web interface, tracking quota carefully across quick, Pro and Deep Research tiers.
196 GitHub stars~7.6k tokensUpdated 3 days ago
Productivity & AutomationAuto-check passed
Sec Risk Factors
OctagonAI/skills
Extract and summarize risk factors from SEC filings using Octagon MCP.
127 GitHub stars~1.6k tokensUpdated 4 mo ago
Legal & ComplianceAuto-check passed
MCP Server Builder
anthropics/skills
Official
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
180k GitHub starsUsed in 64 repos~2.3k tokens
Agent WorkflowsAuto-check passed
MCP Server Builder
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
78k GitHub starsUsed in 5 repos~1.2k tokens
Agent WorkflowsAuto-check passed
MCP Integration for Plugins
anthropics/claude-plugins-official
Official
Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.
38k GitHub starsUsed in 11 repos~3.1k tokens
Agent WorkflowsAuto-check passed

Questions about Kimi Datasource

What does Kimi Datasource do?

Universal data-source assistant for stocks (Wind, S&P, SEC EDGAR), macro (World Bank, IMF, FRED, NBS), Chinese government data and standards (GB/HB/DB/TT), corporate, academic, legal, WHO/FAO/OECD…. Kimi Datasource is an agent skill from MoonshotAI/kimi-code. Universal data-source assistant for stocks (Wind, S&P, SEC EDGAR), macro (World Bank, IMF, FRED, NBS), Chinese government data and standards (GB/HB/DB/TT), corporate, academic, legal, WHO/FAO/OECD and other IGO data, financial news (Xinhua, Caixin).

When should I use Kimi Datasource?

Kimi Datasource fits situations like: tasks that involve MCP servers.

How do I install Kimi Datasource in Claude Code?

Run `npx skills add MoonshotAI/kimi-code --skill kimi-datasource -a claude-code`. Or copy the skill folder (plugins/official/kimi-datasource in MoonshotAI/kimi-code) into .claude/skills/kimi-datasource in your project. Claude Code loads it when a task matches its description.

How do I install Kimi Datasource in Codex?

Run `npx skills add MoonshotAI/kimi-code --skill kimi-datasource -a codex`. Or copy the skill folder (plugins/official/kimi-datasource in MoonshotAI/kimi-code) into .agents/skills/kimi-datasource in your project. Codex loads it when a task matches its description.

Can I use Kimi Datasource 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 MoonshotAI/kimi-code --skill kimi-datasource -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kimi-datasource, .gemini/skills/kimi-datasource, .github/skills/kimi-datasource and .opencode/skills/kimi-datasource in your project.

What does Kimi Datasource need to run?

Going by SKILL.md and its folder, Kimi Datasource needs JavaScript for the scripts in its folder. Our summary lists: Node.js.

Does Kimi Datasource 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 Kimi Datasource 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 Kimi Datasource use?

Kimi Datasource 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 Kimi Datasource use?

About 1.8k tokens (SKILL.md is roughly 7.3k 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 Kimi Datasource?

Skills that share tags, products or a category with Kimi Datasource: Add Coordinator (FeiZhuLulu/Agent-Bridge, 107 stars), Perplexity Web MCP Bridge (jacob-bd/perplexity-web-mcp, 196 stars), Sec Risk Factors (OctagonAI/skills, 127 stars) and MCP Server Builder (anthropics/skills, 180k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Kimi Datasource?

MoonshotAI (a GitHub organization) maintains it in MoonshotAI/kimi-code, which has 7,796 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 8, 2026.

Source: MoonshotAI/kimi-code on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Kimi Datasource

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

kimi-datasource — 通用数据源助手

0. 调用方式

1. 这个 skill 提供什么能力

选源原则

能力边界参考（客观事实，选源时考虑）

2. 标准工作流：get_data_source_desc → call_data_source_tool

例 1：用户问"茅台最近一年走势"

例 2：用户问"找几篇 retrieval augmented generation 的综述"

例 3：用户问"字节跳动有哪些股东"

3. 调用前的几条铁律

3.1 股票代码必须核对，不能凭记忆猜

3.2 企业相关查询必须用全称

3.3 多数 API 需要 file_path

3.4 一次调用不要堆太多 ticker

4. 怎么读返回结果

5. watchlist.json — 用户自选股

6. 注意事项

Files

Compare with similar skills

Similar skills

More from MoonshotAI/kimi-code

Related

Questions about Kimi Datasource

2. 标准工作流：`get_data_source_desc` → `call_data_source_tool`

3.3 多数 API 需要 `file_path`

5. `watchlist.json` — 用户自选股