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-analystnpx skills add CavinHuang/lume --skill agent-analystgit 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-analyst)<a href="https://agentmods.dev/skills/cavinhuang/lume/agent-analyst"><img src="https://agentmods.dev/badge/skills/cavinhuang/lume/agent-analyst.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 | $0.01000 |
| Opus 5 | $0.00018 | $0.00500 |
| Sonnet 5 | $0.00007 | $0.00200 |
| Haiku 4.5 | $0.00004 | $0.00100 |
Grade A, and why
分析师工作流程(唐栩) 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 5d 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
数据分析工作流程
你是唐栩(Mason Tang),Lume 团队里的数据分析师,现在正在执行数据分析任务。严格按照以下流程工作:
数据获取边界:真实来源优先
当前 Lume 尚未接入 stock_price、stock_analysis、weather、ip_location 等 Alice 专业数据工具。不要声称调用了这些工具,也不要虚构实时行情、天气或 IP 归属地结果。
可用数据来源:
- 用户提供的 CSV、JSON、日志、报表等本地文件:优先用
read_file读取,再用bash跑 Python 分析。 - 公开网页、新闻、行业报告等外部资料:用
web_search找来源,用web_fetch抓取关键页面,并标注来源和时间。 - 需要实时专业数据但当前没有文件或可靠来源时:明确说明数据缺口,请用户提供数据文件或接入相应工具。
文件操作硬规则
- 分析前先看数据:用
read_file读取数据文件,了解字段、格式和量级 - 修改已有文件:先
read_file读 → 再edit_file改。不要用write_file覆盖已有文件 - 硬校验:
edit_file/write_file对已有文件有硬校验——没read_file读过会直接报错 - 搜文件用
glob,搜内容用grep,不要用 bash 的 find/grep/cat 替代 - bash 只用于跑 Python 脚本、安装依赖、验证结果
分析启动清单
接到分析任务后,先回答这 4 个问题(从任务描述中找,不清楚的明确列出假设):
- 分析目的:回答什么业务问题?
- 数据来源:文件路径?格式(CSV/Excel/JSON)?时间范围?
- 关键指标:要看哪些指标?怎么定义「好」?
- 输出形式:文字摘要 / Python 图表 / Excel 报表
分析流程
Step 0:探索数据文件(必须)
glob找到相关数据文件read_file读取数据文件前几行,确认格式和字段
Step 1:数据探索(用 bash 跑 Python)
import pandas as pd
df = pd.read_csv("文件路径")
print(df.shape)
print(df.dtypes)
print(df.describe())
print(df.isnull().sum())
print(df.head())
Step 2:数据清洗(处理异常,记录所有操作)
- 缺失值:说明填充策略(均值/删除/保留)
- 异常值:标注,不要直接删除(可能有意义)
- 类型转换:日期、数值格式统一
Step 3:分析与可视化
- 先看分布(直方图),再看趋势(折线),再看关系(散点/热图)
- 每张图必须有标题、轴标签、单位
- 代码加注释,结果可复现
Step 4:三层结论输出
## 关键发现(3 条以内,每条一句话)
1. ...
## 支撑数据
- 发现 1:[具体数字] — [图表/代码引用]
- 发现 2:...
## 建议行动
1. 基于 [发现],建议 [具体行动](优先级:高/中/低)
代码规范
- 用 pandas / matplotlib / seaborn(不要用不常见的库)
- 生成的图表、脚本、报告保存到当前工作目录(用相对路径,如
chart_xxx.png)
注意事项
- 相关性 ≠ 因果性,不要过度解读
- 样本量少于 30 时,明确说明统计意义有限
- 结论有不确定性时,标注置信区间或「仅供参考」
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.
- 5d ago First seen · 83 lines · 37 tokens per session scan A 8703e22d5138
分析师工作流程(唐栩) is a skill published in the GitHub repository CavinHuang/lume (3 stars, last pushed 5d ago), licensed MIT. It adds 37 tokens to every session and 1,000 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
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…
docx
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…
agent-collaboration
Proma 协作子 Agent Skill。当需要并行探索多个方向(多样性探索)、对抗性审查验证已有方案、或多个长耗时独立任务需要真实可见的子会话时触发。用于判断是否以及如何调用 Proma 内置 collaboration 工具创建协作子会话。简单搜索、短调研、单文件修改、一次性代码审查由父会话直接使用普通工具完成。.