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 skills add agentscope-ai/QwenPaw-Data --skill bi-dashboard-generationgit clone --depth 1 https://github.com/agentscope-ai/QwenPaw-DataWrote 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/agentscope-ai/qwenpaw-data/bi-dashboard-generation)<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw-data/bi-dashboard-generation"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw-data/bi-dashboard-generation/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.
<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw-data/bi-dashboard-generation"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw-data/bi-dashboard-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00094 | $0.01145 |
| Opus 5.5 | $0.00038 | $0.00458 |
| Sonnet 5.5 | $0.00019 | $0.00229 |
| Haiku 4.5 | $0.00009 | $0.00114 |
Grade A, and why
bi-dashboard-generation 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 2mo 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
bi-dashboard-generation
根据分析产出的数据，构建交互式 HTML 看板。Agent 拥有完全的设计自由度——自主决定布局结构、可视化类型、筛选器位置——只需遵循 references/theme.md 中的主题规范确保视觉一致性。
交付物为单个可离线打开的 HTML 文件。
核心原则
- 摘要优先：默认视图在读者交互前就能回答核心问题
- 图表主导：用最简单的图表回答读者的问题，表格用于查阅而非主要叙事
- 灵活筛选：筛选器可以出现在任何合适的位置（顶部、侧边、卡片内、表格内），按需添加
前置检查
- 分析主题明确，核心问题已定义
- 数据文件（CSV）已生成且可访问
- 明确看板的受众和主要用途（状态监控 / 运营回顾 / 分析探索）
参考
resources/demo.html了解完整看板的产出样式。
执行步骤
1：定义看板简报
- 受众与目标：谁看这个看板？需要监控、理解还是行动于什么？
- 核心问题：默认视图应回答什么问题？
- 指标范围：需要展示哪些指标？考虑覆盖面：
- 规模（用户量、访问量）、价值（收入、转化率）、质量（成功率、时延）
- 变动（趋势、环比）、构成（占比、分布）、漏斗（步骤转化）
- 筛选维度：读者可能按哪些维度探索？
- 看板标题
2：数据准备
- 列出所有需要展示的数据文件及其完整路径
- 逐文件读取，确认字段、行数、维度
- 保留文件路径，后续步骤用于数据来源标注
3：设计信息层级与布局
基于实际数据内容，从摘要到细节分层，具体布局完全自由：
- 英雄指标：最核心的 KPI，直接回答"现在怎么样"
- 趋势/变动：核心指标的时间走势
- 诊断/拆解：按维度下钻，回答"为什么"
- 明细：详细数据，支持查阅
筛选器设计：
- 只在能实质更新视图时才添加
- 位置不限——可以在顶部全局、在卡片内局部、甚至嵌入表格
- 少量高价值筛选器优于密集面板
4：选择可视化类型
根据数据要回答的问题选择最合适的图表：
| 问题类型 | 推荐可视化 |
|---|---|
| 当前状态 | KPI 卡片 |
| 趋势变化 | 折线图 |
| 各部分占比 | 饼图/环形图 |
| 排名对比 | 条形图 |
| 转化流失 | 漏斗图 |
| 逐行细节 | 表格 |
| 两变量关系 | 散点图 |
原则：用最简单的图表回答问题；一份数据只用一种展示形式。
5：构建 HTML 看板
直接输出完整的 HTML 文件，遵循 references/theme.md 中的主题规范：
- 引入基础资源（Tailwind CSS、ECharts、Bootstrap Icons）
- 将 CSV 数据转为 JSON 变量嵌入 HTML，供 ECharts 渲染使用；每份数据在对应卡片底部标注来源链接：
<p class="text-xs text-gray-400 mt-2">数据来源：<a href="path/to/filename.csv" class="hover:underline text-blue-400" target="_blank">filename.csv</a></p> - 使用主题规范中的组件模式构建页面
- 编写筛选器联动的 JS 逻辑
- 保存为单个 HTML 文件
6：自检
- 默认视图在交互前回答核心问题
- 图表类型与数据特征匹配
- 筛选器正常工作，筛选后无数据时有空状态提示
- 所有数字来自数据文件，不得编造
- 每个展示区域底部有数据来源链接，且为可点击的
<a href>指向实际文件路径 - HTML 可离线打开，无外部运行时依赖（CDN 资源除外）
What ships with it
2 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.
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.
- 2mo ago First seen · 95 lines · 94 tokens per session scan A cd3300242a8f
bi-dashboard-generation is a skill published in the GitHub repository agentscope-ai/QwenPaw-Data (196 stars, last pushed 7d ago), licensed Apache-2.0. It adds 94 tokens to every session and 1,145 once invoked, about $0.0004 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.
bi-dashboard-generation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bi-dashboard-generationagentscope-ai/QwenPaw-Data | Skill | 196 | 7d ago | Apache-2.0 | A | 94 | Claude Code, Codex |
| open-sourcebrowser-use/browser-use | Skill | 121k | today | MIT | A | 101 | Claude Code |
| mem0-tourmem0ai/mem0 | Skill | 69k | 6d ago | Apache-2.0 | A | 47 | Claude Code, Codex |
| pausemem0ai/mem0 | Skill | 69k | 6d ago | Apache-2.0 | A | 30 | Claude Code |
| mem0-test-integrationmem0ai/mem0 | Skill | 69k | 6d ago | Apache-2.0 | A | 207 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | 6d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| horizonThysrael/Horizon | Skill | 14k | today | MIT | A | 95 | Claude Code, Codex |