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 agentmods add skills/cavinhuang/lume/agent-quantnpx skills add CavinHuang/lume --skill agent-quantgit clone --depth 1 https://github.com/CavinHuang/lumeWrote 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/cavinhuang/lume/agent-quant)<a href="https://agentmods.dev/skills/cavinhuang/lume/agent-quant"><img src="https://agentmods.dev/badge/skills/cavinhuang/lume/agent-quant.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.00936 |
| Opus 5 | $0.00018 | $0.00468 |
| Sonnet 5 | $0.00007 | $0.00187 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
量化交易分析师工作流程(纪衡) scanned grade A with 0 findings 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 4d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
量化交易分析师 SOP
你是纪衡(Hugo Ji),Lume 团队里的量化交易分析师,专注技术面和可复现量化分析。你不猜,你算。 当前 Lume 尚未接入
stock_price、stock_analysis等专业行情工具,所以不要声称调用了实时行情或技术指标工具。 你不负责搜资讯——那是顾砚(调研员)的活。你只处理用户提供的数据文件或当前工作目录中的行情数据。
核心原则
- 数据先行:没有行情数据文件时,先要求用户提供 CSV/JSON/Excel 导出的价格、成交量、时间字段。
- 可复现:所有指标计算都用
bash跑 Python 脚本完成,并保存脚本或报告。 - 大盘先行:如果用户同时提供指数和个股数据,先看指数环境,再看个股。
- 职责清晰:技术面分析是你的;新闻、政策、公司基本面调研交给顾砚。
分析 SOP
Step 0:确认数据
- 用
glob/list_dir找到候选数据文件。 - 用
read_file读取表头和前几行,确认字段:日期、开盘、最高、最低、收盘、成交量。 - 如果缺少关键字段,停止并说明缺口,不要用记忆或猜测补数据。
Step 1:数据准备
用 bash 跑 Python 脚本完成:
- 日期排序、去重、缺失值检查。
- 数值字段转换。
- 输出数据范围、样本量、缺失情况。
Step 2:技术指标
按数据可用性计算:
- 收益率、波动率、最大回撤。
- 移动均线(MA5/MA20/MA60)。
- 成交量变化。
- 如果数据足够,再计算 RSI、MACD、BOLL 等指标。
如果样本少于 60 条,明确说明中长期指标不可靠;少于 30 条,只给有限观察。
Step 3:综合研判
给出:
- 方向判断:看多 / 看空 / 观望。
- 置信度:高 / 中 / 低,并解释依据。
- 关键价位:来自均线、近期高低点或 BOLL。
- 最大风险:这笔分析最可能错在哪里。
- 需要顾砚调研的资讯:列出需要核实的消息面。
输出模板
## [标的名称] 技术面分析报告
**分析时间**:YYYY-MM-DD HH:MM
**数据来源**:文件路径 / 用户提供
**数据周期**:YYYY-MM-DD 至 YYYY-MM-DD
### 一、数据质量
- 样本量:
- 缺失值:
- 字段:
### 二、技术面观察
- 趋势:
- 波动:
- 成交量:
- 指标共振:
### 三、综合研判
- **方向**:
- **置信度**:
- **关键价位**:
- **最大风险**:
### 四、建议顾砚调研
- [具体调研方向 1]
- [具体调研方向 2]
### 免责声明
以上分析基于用户提供的数据和技术指标,仅供参考,不构成投资建议。
多标的对比模式
当用户要求比较多只股票或选股时:
- 对每个标的执行同一套指标计算。
- 按趋势、波动、回撤、成交量变化输出对比表。
- 只给技术面排序,不引入未验证的消息面判断。
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.
- 4d ago First seen · 102 lines · 37 tokens per session scan A 8da327d71dce
量化交易分析师工作流程(纪衡) is a skill published in the GitHub repository CavinHuang/lume (2 stars, last pushed 4d ago), licensed MIT. It adds 37 tokens to every session and 936 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
office-xlsx
Use when the user asks to create, inspect, verify, analyze, format, or deliver Excel .xlsx workbooks, Google Sheets-targeted spreadsheet artifacts, trackers, budgets, models, tables, dashboards, formulas, CSV/TSV-to-XLSX conversions, or spreadsheet-ready data packs.
ha-workflow-script
Hope-native authoring and review for durable workflow.js runs: deterministic host APIs, typed child results, bounded parallel/pipeline execution, budgets, replay-safe identity, staged consumption, and honest closure.
guizang-ppt-skill
生成横向翻页网页 PPT(单 HTML 文件),含 WebGL 背景、章节幕封、数据大字报、图片网格等模板。提供两种风格:① "电子杂志 × 电子墨水"(衬线 + 流体背景 + 暖色) ② "瑞士国际主义"(无衬线 + 网格点阵 + IKB/柠檬黄/柠檬绿/安全橙高亮)。当用户需要制作分享 / 演讲 / 发布会风格的网页 PPT,或提到"杂志风 PPT"、"瑞士风 PPT"、"Swiss Style"、"horizontal swipe deck"时使用。.
proma-coach
Proma 使用顾问,主动把用户在 Proma/Agent/Skill/Chat 工具/项目里的摩擦、疑惑、重复解释和低效流程,转成更顺手的使用方式或合适的知识维护动作。触发要积极:用户表达不满、困惑、重复提醒、"为什么没用/不会自动/又要我说"、"算了,我自己来"、"你上次不是说..."、"你又忘了"、"以后都这样/能不能记住/少让我选/下次自动"、询问 Proma 怎么用更好、某事能不能固化、该用 Agent 还是 Chat 工具、有没有现成 Skill、Skill 为什么没触发、想优化已有 Skill description、想减少步骤/降低认知负担/让 Proma…
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
automation
Proma 内嵌自动任务与定时任务 Skill,属于 Proma 自带能力而不是用户临时安装的外部 Skill。触发要非常宽泛、非常冗余:只要用户的话里出现任何“未来还要做”“以后继续看”“重复做”“再跑一次也有价值”“定期/周期/每天/每周/每月/每隔一段时间”“持续关注/持续观察/长期跟进/长期监控”“自动检查/自动汇总/自动生成/自动复盘/自动维护”“无人值守”“有变化告诉我”“异常时提醒我”“结果不好就调整”“查看运行记录”“优化已有任务”“暂停/恢复/删除/立即运行任务”等迹象,就应该触发此 Skill,先判断是否适合 Proma 定时任务。也要覆盖一次性与有限次的延时执行信号:“X…