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/coderzzy/agent-fund-analysis-skill/fund_analysisnpx skills add coderzzy/agent-fund-analysis-skill --skill fund_analysisgit clone --depth 1 https://github.com/coderzzy/agent-fund-analysis-skillWhat 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 | $0.00039 | $0.03127 |
| Opus 5 | $0.00019 | $0.01563 |
| Sonnet 5 | $0.00008 | $0.00625 |
| Haiku 4.5 | $0.00004 | $0.00313 |
Grade A, and why
fund_analysis 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
基金分析 Skill
功能描述
此 skill 用于从天天基金网获取基金历史数据，通过 Python 脚本进行深度数据分析，最终生成包含可视化图表、数据表格和 Agent 解读的 PPT 风格的 HTML 分析报告。
分析维度：
- 净值走势可视化
- 多周期净值统计分析（1个月、半年、1年、3年、成立以来）
- 压力指标分析（支撑/压力位识别）
- 不同间隔周期涨跌幅分析（1天、3天、1周、1月、半年、1年）
- 收益反转周期分析
- 月度收益分布
触发条件
当用户输入以下或类似表达时触发：
- "帮我分析基金"
- "分析基金"
- "基金分析"
- 包含基金代码（如 012805）
执行流程
Step 1: 创建输出目录
mkdir -p ./output_fund/{基金代码}/raw
mkdir -p ./output_fund/{基金代码}/analysis
mkdir -p ./output_fund/{基金代码}/report
Step 2: 获取基金数据
- 从用户输入中提取基金代码（6位数字）
- 构建请求 URL：
https://fund.eastmoney.com/pingzhongdata/{基金代码}.js?v={时间戳}- 时间戳格式：年月日时分秒，如 20260410022145
- 发送 HTTP GET 请求获取数据
- 将返回的 JS 数据保存到
./output_fund/{基金代码}/raw/{基金代码}_raw.js
Step 3: 解析数据
返回的 JS 文件包含以下关键变量：
基金基本信息
| 变量名 | 说明 | 示例值 |
|---|---|---|
fS_name |
基金名称 | "广发恒生科技ETF联接(QDII)C" |
fS_code |
基金代码 | "012805" |
fund_sourceRate |
原费率 | "0.00" |
fund_Rate |
现费率 | "0.00" |
fund_minsg |
最小申购金额 | "10" |
收益率数据
| 变量名 | 说明 | 示例值 |
|---|---|---|
syl_1n |
近一年收益率(%) | "-4.23" |
syl_6y |
近6月收益率(%) | "-27.71" |
syl_3y |
近3月收益率(%) | "-16.73" |
syl_1y |
近1月收益率(%) | "-3.08" |
净值走势数据
| 变量名 | 说明 | 数据格式 |
|---|---|---|
Data_netWorthTrend |
单位净值走势 | [{"x":时间戳,"y":净值,"equityReturn":回报率,"unitMoney":派送金},...] |
Data_acWorthTrend |
累计净值走势 | [[时间戳,累计净值],...] |
Data_grandTotal |
累计收益率走势 | [[时间戳,收益率],...] |
Step 4: 数据分析（Python脚本）
使用 Python 脚本进行深度数据分析：
python scripts/fund_analyzer.py \
--code {基金代码} \
--input ./output_fund/{基金代码}/raw/{基金代码}_raw.js \
--output ./output_fund/{基金代码}/report/report_{基金代码}.html \
--json-output ./output_fund/{基金代码}/analysis/analysis_{基金代码}.json
分析维度
-
净值走势可视化
- 绘制累计净值总体走势曲线
- 支持鼠标悬停查看具体日期和数值
- 支持缩放查看不同时间段
-
多周期净值统计分析
周期 说明 1个月 最近30天的净值统计 半年 最近180天的净值统计 1年 最近365天的净值统计 3年 最近1095天的净值统计 成立以来 全部历史净值统计 每个周期计算：
- 平均值、中位数
- 最高值、最低值
- 标准差（波动程度）
- 统计区间起止日期
What ships with it
1 file 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.
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.
- 2d ago First seen · 257 lines · 39 tokens per session scan A 277538dada99
fund_analysis is a skill published in the GitHub repository coderzzy/agent-fund-analysis-skill (5 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 3,127 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.