指导通过 QMT Bridge WebSocket 订阅实时行情、L2、公式推送与交易回报并对账。 在用户提到 WebSocket 订阅、盘中推送、成交回报、实时盯盘时使用。规程为主。
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add Serennity007/awesome-stock-quant-skills --skill qmt-bridge-realtime-monitor --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Qmt Bridge Realtime Monitor?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/serennity007-qmt-bridge-realtime-monitor)More formats (shields.io, HTML) on the badges page.
---
name: qmt-bridge-realtime-monitor
description: >-
指导通过 QMT Bridge WebSocket 订阅实时行情、L2、公式推送与交易回报并对账。
在用户提到 WebSocket 订阅、盘中推送、成交回报、实时盯盘时使用。规程为主。
---
# QMT Trading Skill · 实时监控
> **实现状态**：✅ `ws_subscribe.py` + WebSocket 规程
## 目标
规范 **WebSocket** 使用方式，避免 Agent 随意长连或泄露 Key。
## WebSocket 端点
| 路径 | 用途 | 认证 |
|------|------|------|
| `/ws/realtime` | 实时行情 | 无 |
| `/ws/whole_quote` | 全市场 | 无 |
| `/ws/l2_thousand` | L2 千档 | 无 |
| `/ws/formula` | 公式推送 | 无 |
| `/ws/download_progress` | 下载进度 | 无 |
| `/ws/trade` | 交易回报 | `?api_key=` |
详见 `docs/websocket.md`。
## 规程（规划）
1. 订阅前 `health` + 明确订阅代码列表
2. 交易回报：`/ws/trade` 与 `GET /api/trading/orders` 定期对账
3. 突破提醒：在客户端聚合 tick，**不**把全量 L2 dump 给 LLM
4. 断线重连：指数退避；记录最后 seq/时间
5. 停止订阅：明确 `unsubscribe` 或关闭连接
## 规划脚本（可选）
| 脚本 | 作用 |
|------|------|
| `scripts/ws_subscribe.py` | CLI 示例：订阅 codes 并打印摘要 N 秒 |
## 安全
- `/ws/trade` 的 api_key 勿写入日志
- 监控不等于自动下单
## 参考
- [qmt-bridge-technical-signal](../qmt-bridge-technical-signal/SKILL.md)
- [qmt-bridge-order-ops](../qmt-bridge-order-ops/SKILL.md)
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
