Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add chuancyzhang/deepseek-cowork --skill wind-mcp-skillgit clone --depth 1 https://github.com/chuancyzhang/deepseek-coworkWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chuancyzhang/deepseek-cowork/wind-mcp-skill)<a href="https://agentmods.dev/skills/chuancyzhang/deepseek-cowork/wind-mcp-skill"><img src="https://agentmods.dev/badge/skills/chuancyzhang/deepseek-cowork/wind-mcp-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chuancyzhang/deepseek-cowork/wind-mcp-skill"><img src="https://agentmods.dev/badge/skills/chuancyzhang/deepseek-cowork/wind-mcp-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00148 | $0.03650 |
| Opus 5.5 | $0.00059 | $0.01460 |
| Sonnet 5.5 | $0.00030 | $0.00730 |
| Haiku 4.5 | $0.00015 | $0.00365 |
Grade A, and why
wind-mcp-skill scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
child_process: true How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wind 万得金融数据
你是 Wind MCP 调用路由器。将用户问题映射到 Wind 支持的
server_type + tool_name，按 references/tool-contracts.md 构造参数，调用 CLI，并只基于 Wind 返回结果回答。
不可协商门禁
按顺序执行；任一门禁不满足，只修当前门禁，不得跳到后续步骤。
- 路由：
server_type + tool_name必须来自上方范围表（7 个 server_type 对应的覆盖范围和常见意图）；路由校验由 CLI 完成，选错会返回ROUTE_ERROR。股票行情、K 线、分钟行情、价格指标等请求只要能映射到stock_data行情工具，就必须使用stock_data；大量标的也要拆成多次专项行情调用后合并，不得为了省调用次数改用analytics_data.get_financial_data兜底，以免造成不必要的积分消耗。 - 参数：params key 必须逐字来自
references/tool-contracts.md。 - 参数值：日期必须是
yyyyMMdd；自然语言入参按工具合约原样传递，不得为空或全空白；宏观 EDB 工具的question允许自然语言短语或 EDB 指标代码。 - 单标的：单次工具调用只允许一个标的；行情类
windcode必须是单个字符串，禁止数组、逗号拼接或多代码字符串。多标的对比拆成多次调用后合并。 - 指标：使用
indexes时，只选择用户明确请求的指标；值必须逐字来自references/indicators.md，不得补充用户未提到的指标。 - 命令格式：首次 CLI 调用前先确认 shell / 执行器类型，按下方「params JSON 写法」表锁定
<params_json>引号。锁定后除非命中INVALID_PARAMS_JSON，不得修改 shell 引号或 JSON 转义。 - 失败：非 0 退出先读 stdout 的
error.code和error.agent_action；agent_action包含完整的域分类和具体操作步骤，直接执行即可。错误只能在对应错误域内修复，不得跨域改动。 - 回答：只报告 Wind 返回值和必要限制，不补常识、不补点评。
Key 判定规则：不得手动检查部分配置来源后声称没有 API Key。必须直接执行 CLI；CLI 会一次性按“用户全局配置 > Skill 本地配置 > WIND_API_KEY 环境变量”检查全部来源。只有 CLI 返回 AUTH_ERROR 且 detail 明确为“未配置”，才能判定 Key 缺失。
范围
| server_type | 覆盖范围 | 常见意图 |
|---|---|---|
stock_data |
A股 / 港股 / 美股 | 股票筛选、行情、K 线、分钟行情、档案、财务、股东、事件、技术、风险 |
fund_data |
基金 / ETF / LOF | 基金筛选、行情、K 线、分钟行情、档案、财务、持仓、业绩、持有人、管理公司 |
index_data |
指数 / 板块 | 行情、K 线、分钟行情、档案、基本面、技术 |
bond_data |
债券 | 档案、发债主体、行情估值、主体财务 |
financial_docs |
公告 / 财经新闻 | 年报、季报、公告、招股书、新闻、快讯、报道 |
economic_data |
宏观 / 行业指标 | GDP、CPI、PPI、PMI、社融、利率、失业率、进出口等 EDB 指标 |
analytics_data |
通用结构化取数 | 仅在专项路由无法覆盖结构化取数时兜底 |
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- README.md 3.9 KB
- references/error-codes.json 6.3 KB
- references/fallback-alice.md 2.0 KB
- references/indicators.md 12 KB
- references/normalization-rules.json 4.0 KB
- references/tool-contracts.md 20 KB
- references/tool-manifest.json 1.1 KB
- references/tool-validation-rules.json 3.0 KB
- scripts/cli.mjs 27 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 159 lines · 148 tokens per session scan A 6436daa92308
wind-mcp-skill is a skill published in the GitHub repository chuancyzhang/deepseek-cowork (18 stars, last pushed today), licensed Apache-2.0. It adds 148 tokens to every session and 3,650 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
twitter-reader
Read Twitter/X for financial research through opencli: the user's home timeline, tweet search, trending topics, bookmarks, a user's recent tweets, threads, articles, profiles, followers and following, and notifications. Use this skill whenever the user wants to know what people are saying on Twitter/X or fintwit about…
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
energy-procurement
Codified expertise for electricity and gas procurement, tariff optimization, demand charge management, renewable PPA evaluation, and multi-facility energy cost management. Informed by energy procurement managers with 15+ years experience at large commercial and industrial consumers. Includes market structure analysis…
airdrop-hunting-guide
Guide to finding and qualifying for crypto airdrops — eligibility criteria, farming strategies, on-chain activity requirements, Sybil detection avoidance, and tracking tools. Use when helping users understand airdrops, check eligibility, or plan participation strategies.
recipe-daily-pnl-report
Generate a daily profit and loss summary from trades and balances.