quant-buddy-view

quant-buddy-view is a skill for Claude Code, Codex from pseudo-longinus/quant-buddy-skills. It costs 319 tokens per session (24,634 once invoked), scanned A, original, MIT.

A workflow for publishing verified quantitative data and formulas as public, shareable web dashboards that fetch current data. Quantitative data means numerical information used for analysis, such as market measures.

In plain words
What is it for?
Creating, updating, publishing, checking, and reusing Quant Buddy dashboards or templates, including interpreting an existing dashboard and handling its runtime data.
Why use it?
It turns validated analysis into a reusable public page instead of leaving the results in a one-time query or backtest.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/static_page.py interpret '{"url":"用户提供的页面 URL"}'.

Good fit Creating, updating, publishing, checking, and reusing Quant Buddy dashboards or templates, including interpreting an existing dashboard and handling its runtime data.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/pseudo-longinus/quant-buddy-skills
agentmods
npx agentmods add skills/pseudo-longinus/quant-buddy-skills/quant-buddy-view

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for quant-buddy-view

README.md
[![agentmods](https://agentmods.dev/badge/skills/pseudo-longinus/quant-buddy-skills/quant-buddy-view/github.svg)](https://agentmods.dev/skills/pseudo-longinus/quant-buddy-skills/quant-buddy-view)
Your own site
<a href="https://agentmods.dev/skills/pseudo-longinus/quant-buddy-skills/quant-buddy-view"><img src="https://agentmods.dev/badge/skills/pseudo-longinus/quant-buddy-skills/quant-buddy-view/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.

agentmods 80×15 button for quant-buddy-view

Your own site · 80×15
<a href="https://agentmods.dev/skills/pseudo-longinus/quant-buddy-skills/quant-buddy-view"><img src="https://agentmods.dev/badge/skills/pseudo-longinus/quant-buddy-skills/quant-buddy-view.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 319 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 24,634 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 227
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 229
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 231
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00319 $0.24634
Opus 5.5 $0.00128 $0.09854
Sonnet 5.5 $0.00064 $0.04927
Haiku 4.5 $0.00032 $0.02463

Measured yesterday against content hash 70607aa775e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

quant-buddy-view 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 yesterday.

The scan reads SKILL.md. This mod also ships 17 executable files (assets/data-kernel.js, assets/data-labels.js, assets/prose-bindings.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/quant-buddy-view/SKILL.md · 530 lines

How it starts

The opening of the file, as written. The whole thing — 530 lines — stays where its author put it; the contents beside it link to each section on GitHub.

页面研究合同(WebAgent 正式投研)

制作活页时,必须先参考用户提问的背景、关键矛盾点和潜在需求,再决定模块结构与信息层级,搜索到的背景信息要落到页面中。

  • 页面开头说明“本页回答什么问题、核心矛盾是什么”,不要直接进入数据表。
  • 外部背景信息必须带来源与发布日期,并与 QBS 数据分区展示;查无实据时写明缺口。
  • 复杂研究页先给维度清单,标注“已有数据 / 待补采 / 缺数据”,再展开各模块。
  • 搜索、分析、建模、建页形成一条链:搜索结果要转化为结论、页面模块和数据需求。
  • 用户明确要求纯文字时不要建页;最终回复不超过 1200 字,不使用多级标题,不附页面链接。
  • 页面构建最多重试 2 次;第 2 次验证失败后降级到最简可交付版本,保留已验证数据和结论,不得无限循环。
  • 快速通道页面(new_asset_page)必须在页面末尾附两个轻量模块:「背景与关注点」(3 句以内,有可靠来源带链接与日期,无来源则如实写外部语境缺失)和「边界与风险」(1–2 句,说明不构成投资建议与主要不确定性)。

页面构建策略(两类页面,两条路径)

路径一:研究分析页 → 用 upload 路径(自由 HTML 创作)

适用于:个股分析、行业研究、深度报告、对比分析、策略研究、供需因子分析等需要叙事结构和丰富视觉的场景。

  • Agent 直接用 HTML + CSS + JS 写完整页面,自由设计布局和视觉,不受面板系统约束
  • 在 HTML 中嵌入 Data Grant(grant_id + signature)或 Formula Package(package_id + signature)实现实时数据绑定
  • 可使用 Chart.js、ECharts 等前端库画交互式图表(折线、柱状、雷达、热力图等)
  • 设计原则:
    • 首屏决策:最重要的结论和最关键的数字必须在首屏可见,大字号高亮
    • 图文交替:标题 → 结论 → 图表 → 白话解读 → 图表 → 白话解读,避免连续 5 个表格
    • 每个图表配 1–2 句"怎么读这组数据"
    • 核心数字用大字号(≥28px)+ 高亮色;辅助信息用小字号灰色
    • 320px 不留横向滚动
    • 页面开头 2 句话说明"本页回答什么问题、核心结论是什么"
  • 构建流程:先用 QBS 获取并验证数据 → 在本地写完整 HTML(含数据绑定标签)→ 用 upload 上传 → publish_verified 发布

路径二:数据面板页 → 用 new_page 路径(标准面板系统)

适用于:实时看板、排行榜、监控系统、多模块数据并排展示等标准化场景。

  • Agent 提供数据面板(panels),build_dashboard 统一渲染卡片/表格布局
  • 适合数据模块多、更新频繁、不需要复杂叙事的场景
  • compose_page 降为备选:仅在需要复用已有复杂交互组件时使用,最多 1 次

路径选择规则

  • 用户要求"分析""研究""报告""对比""怎么看" → 路径一(upload)
  • 用户要求"看板""监控""排行榜""实时数据" → 路径二(new_page)
  • 不确定时,默认路径一(upload),因为研究分析是最常见的场景
  • new_asset_page(个股快页)仍走固定快速通道,不受此规则影响

多资产对比表格格式

  • 多资产对比时,表格必须用"透视格式":指标名为行、资产名为列并排展示。
  • 禁止使用 API 原始返回的长表格式(每行=标的+指标+值);如原始数据是窄表,必须转为宽表后再渲染。
  • 大额金额自动缩写为"亿元"或"万元",保留两位小数;百分比保留两位小数带 %。
  • 差异列用 +/− 前缀标明方向;末尾可选加"差异对比"列,展示两值之差。

筛选零结果降级

  • 筛选结果为 0 只时,自动按预设顺序放宽非核心条件(如市值从 100 亿降至 50 亿再降至 30 亿),每次只放宽一个条件,最多 3 次。
  • 放宽条件必须在页面上标注"已放宽:市值从 100 亿降至 50 亿"。
  • 交付非 0 名单按综合得分排序,不按代码排序。仍为 0 则交付空结果并解释原因。

港股与美股页面最低质量标准

  • 港股/美股页面必须至少包含 2 张图表(如估值走势、区间表现、财务趋势),不得只用表格交付。
  • 即使 QBS 港股维度比 A 股少,也要用已有数据画图(如 PE(TTM) 近一年走势、近 20/60/250 日区间表现柱图);数据不足时画已有部分并标注缺口。
  • 港股/美股页面必须绑定至少 1 个实时数据模块(如最新行情 Data Grant),不能全部为静态快照。
  • 港股/美股的图表标题和轴标签必须标注货币单位(港元/美元),不得与 A 股人民币混用。

Read the full file on GitHub · 530 lines

Files

What ships with it

60 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.

Changes

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.

  1. yesterday Changed · +71 lines 70607aa775e6
  2. 3d ago Changed 7ba272aed440
  3. 8d ago Changed 49d4751142af
  4. 9d ago Changed deb3dc817aa1
  5. 10d ago Changed · +5 lines e52d4924dbe1
  6. 11d ago Changed cc0aebe45638
  7. 12d ago Changed · +2 lines 16c7b3bc32d3
  8. 14d ago Changed · +5 lines 2ea52fc32744
  9. 16d ago Changed · +3 lines c2cbd83e5a77
  10. 17d ago First seen · 444 lines · 319 tokens per session scan A 5b9cc6a90dcc

Subscribe to this mod's changes

quant-buddy-view is a skill published in the GitHub repository pseudo-longinus/quant-buddy-skills (195 stars, last pushed 2d ago), licensed MIT. It adds 319 tokens to every session and 24,634 once invoked, about $0.0013 per session on Opus 5.5. 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 2026-08-30.

Related

Other skills, from other repositories

alpha-evaluate

A multi-step workflow for testing an investment factor, meaning a measurable stock signal, against market data. It examines predictive relationship, grouped returns, risk-adjusted results, consistency, and robustness.

VernonOY/alpha-skills · 74 tokens

alpha-backtest

A strategy backtesting workflow that tests factor-based stock portfolios on historical data. Backtesting means simulating how a strategy would have performed in the past.

VernonOY/alpha-skills · 56 tokens

alpha-mine

An automated process for proposing and testing stock-market formulas, called factors, that combine price or trading data with mathematical operations. It screens the candidates using measures such as IC, which compares a factor with later returns.

VernonOY/alpha-skills · 73 tokens

alpha-autopilot

An automated research loop for investment factors, which are measurable signals used to select or compare stocks. It finds candidates, tests them, records successful ones, monitors active factors, and retires those that weaken.

VernonOY/alpha-skills · 85 tokens

alpha-library

A manager for a quantitative-finance factor library, where factors are measurable signals used to study or select investments. It stores a registry of factors in a SQLite database and supports several stock markets through data adapters.

VernonOY/alpha-skills · 55 tokens

alpha-monitor

A monitoring tool for investment factors, which are measurable signals used to select or rank stocks. It checks whether active factors are losing effectiveness or showing health problems across supported stock markets.

VernonOY/alpha-skills · 56 tokens