Agent skill

Bi Report Generation

by agentscope-ai in agentscope-ai/QwenPaw-Data

将 BI 数据分析结果组织成可视化 HTML 报告。当分析完成、需要生成报告时调用. An agent skill from agentscope-ai/QwenPaw-Data.

Apache-2.0Auto-check passedDocuments & Office

Install Bi Report Generation

skills CLI
$ npx skills add agentscope-ai/QwenPaw-Data --skill bi-report-generation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install agentscope-ai/QwenPaw-Data bi-report-generation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw-Data.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/qwenpaw-data-skills/skills/atomic/bi-report-generation .claude/skills/bi-report-generation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
bi-report-generation
GitHub stars
127
Token cost
~1.2k tokens
SKILL.md length
233 words
Files
4 (incl. scripts, references)
Skills in repo
29
Repo updated
First seen
Licence
Apache-2.0

At a glance

将 BI 数据分析结果组织成可视化 HTML 报告。当分析完成、需要生成报告时调用. An agent skill from agentscope-ai/QwenPaw-Data.

  • Works in 4 steps: 根据分析路径选择展示方式:每个主题的第一张卡片必须是数据概况卡,展示核心指标整体情… → 选择图表类型:按 references/layout-spec.md §1… → 列出每个主题需要读取的数据文件。 → …
  • Documents & Office work in your project
  • SKILL.md covers 前置检查 and 执行步骤
  • Runs Python scripts from its folder; calls python

What it does

Bi Report Generation is an agent skill from agentscope-ai/QwenPaw-Data. 将 BI 数据分析结果组织成可视化 HTML 报告。当分析完成、需要生成报告时调用。

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `references/layout-spec.md` and `scripts/report_builder.py`).

It sits in Documents & Office. The repository describes itself as: Agentic enterprise data analytics: governed facts (DataBridge), reusable methodology (Skill-Hub), and controllable execution (Host). The licence is Apache-2.0.

When your agent uses it

  • Documents & Office work in your project

Example prompts

  • “/bi-report-generation”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. 根据分析路径选择展示方式:每个主题的第一张卡片必须是数据概况卡,展示核心指标整体情况作为背景,再按分析路径展开后续内容
  2. 选择图表类型:按 references/layout-spec.md §1 中的图表类型表匹配,命中即停;标注"✦ 支持切换"的场景需同时生成图表和表格视图(详见步骤 3)。
  3. 列出每个主题需要读取的数据文件。
  4. 多主题场景下,额外确定报告的总标题(概括报告整体范围)和总摘要(提炼各主题核心结论,形成跨主题的综合性洞察,将放在报告顶部的摘要区块)。

What it can do on your machine

Read from SKILL.md and the folder at commit e0bae36. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Bi Report Generation loads about 1.2k tokens when it runs, and up to ~4.1k if it reads all its reference files. Until then it costs about 16 tokens; SKILL.md has 233 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~16
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from agentscope-ai/QwenPaw-Data at commit e0bae36, republished under its Apache-2.0 licence (© agentscope-ai). 233 words, ~1,155 tokens.

Download SKILL.mdSave it as .claude/skills/bi-report-generation/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
bi-report-generation
description
将 BI 数据分析结果组织成可视化 HTML 报告。当分析完成、需要生成报告时调用。

bi-report-generation

将分析结论和数据文件转化为读者友好的 HTML 报告。支持单主题和多主题场景。

报告生成遵循三个核心原则:

  • 准确:报告中的所有数字和结论必须来自分析产出的数据文件,不得编造或推测数据
  • 紧凑:充分利用页面空间,优先将数据块并排布局,减少纵向滚动
  • 高密度:每张卡片尽量承载多个相关结论,避免一个指标独占一张卡片

前置检查

开始前确认以下事项已就绪,任一缺失应先完成前置分析流程:

  • 分析主题明确(可能包含多个子主题)
  • 各主题的分析步骤已执行完毕,结论已产出
  • 支撑结论的数据文件已生成且可访问

执行步骤

1:展示布局规划

基于已完成的分析过程,梳理各主题涉及的关键指标、分析维度和数据特征,为每个主题规划展示形式:

  1. 根据分析路径选择展示方式:每个主题的第一张卡片必须是数据概况卡,展示核心指标整体情况作为背景,再按分析路径展开后续内容:

    分析路径展示方式
    基础数据观测KPI 卡展示核心数字,表格/图表展示数据细节
    下钻/拆解/归因按照「现象 → 归因 → 数据佐证」展示完整分析路径
    归因类分析(含外部事件)数据概况卡 → 按关键数据点或异常区间分块,每块附触发原因 + 具体动作描述的归因列表
  2. 选择图表类型:按 references/layout-spec.md §1 中的图表类型表匹配,命中即停;标注"✦ 支持切换"的场景需同时生成图表和表格视图(详见步骤 3)。

  3. 列出每个主题需要读取的数据文件。

  4. 多主题场景下,额外确定报告的总标题(概括报告整体范围)和总摘要(提炼各主题核心结论,形成跨主题的综合性洞察,将放在报告顶部的摘要区块)。

对每个主题,依次执行步骤 2 和步骤 3:

2:数据准备

根据步骤 1 确定的文件列表,读取该主题所需数据:

  1. 读取数据文件
  2. 列筛选:数据表可能包含与当前主题不直接相关的列,只保留相关列用于展示,剔除无关列
3:生成 HTML 卡片

根据步骤 1 的布局规划,为该主题生成独立的 HTML 卡片:

  • 卡片需包含标题、摘要、数据展示(表/图/KPI)、现象描述、分析解读和数据来源。

  • 生成卡片时需严格遵循 references/layout-spec.md 中的排版规范。

  • 图片一律用 ECharts 在 HTML 中动态绘制:从数据文件读取数值,在卡片内初始化 ECharts 实例渲染图片。禁止引用分析过程中已生成的 PNG/JPG 等静态图片(不得使用 <img> 标签嵌入图片路径、base64 或外链图片来展示图片)。

  • 标注"✦ 支持切换"的场景必须实现图表/表格双视图:图表容器顶部右侧放"图表"/"表格"切换按钮,默认显示图表,点击切换到表格;表格视图数值列颜色规则与图表保持一致。

  • 图表高亮重点:趋势图和折线图必须用 markPoint / markLine 标注关键数据点(异常值、大幅增长、增长停滞等),图表正下方紧跟一行小字列出具体数值和简要说明。

  • 分块归因分析:归因类卡片按数据重点分块展示,每块对应一个关键数据点或异常区间,块内归因列表中每条归因需包含:触发原因 + 具体动作描述,禁止只写原因不写动作。

  • 卡片写入 sections_{xxx}.json 文件(使用唯一标识区分不同报告)。每条 section 的字段说明:

    字段类型说明
    titlestring卡片标题
    iconstring(可选)Bootstrap Icon 类名,如 bi-graph-up-arrow
    typestring(可选)填 "timeline" 表示时间线 section,渲染在 tab 区域外部且始终可见;不填则为普通可切换卡片
    html_fragmentstring卡片内容 HTML
    json
    [
      {
        "title": "访问趋势分析",
        "icon": "bi-graph-up-arrow",
        "html_fragment": "<div class='bg-white rounded-xl shadow-md p-6'>...</div>"
      },
      {
        "title": "业务事件时间线",
        "type": "timeline",
        "icon": "bi-calendar-event",
        "html_fragment": "<div class='bi-timeline'>...</div>"
      }
    ]
  • 时间线 section(可选):如果分析过程中涉及业务事件(促销活动、模型上线、策略变更等),在所有普通卡片之后追加一条 "type": "timeline" 的 section。时间线的 html_fragment 使用以下结构:

    • 外层容器:<div class="bi-timeline">
    • 每个事件:<div class="bi-tl-item {类型class}"><div class="bi-tl-date">{日期}</div><div class="bi-tl-title">{事件名}</div><div class="bi-tl-desc">{描述}</div></div>
    • 事件类型 class:tl-major(异常/突发)、tl-promo(促销/活动)、tl-product(产品发布/功能变更)、不加 class(常规事件)
    • 事件按时间升序排列,时间线 section 不参与 tab 切换,始终在报告底部可见
4:生成完整报告

所有主题卡片生成后,调用 scripts/report_builder.py 将各 JSON 文件拼接成完整的 HTML 报告。

参数:

参数说明
--sections主题卡片 JSON 文件路径,支持多个(必填)
--output / -o输出报告文件路径,HTML 格式(必填)
--report-title报告总标题(多主题场景使用)
--overall-summary跨主题核心结论摘要(多主题场景使用)

调用示例:

bash
# 多主题
python scripts/report_builder.py \
    --sections sections_001.json sections_002.json \
    --output report_v1.html \
    --report-title "XXX 产品 2025 年 12 月数据分析报告" \
    --overall-summary "<p>跨主题核心结论摘要...</p>"

# 单主题(不传 report-title 和 overall-summary,让主题卡片直接展示)
python scripts/report_builder.py \
    --sections sections_001.json \
    --output report_v1.html

输出命名遵循 runtime-guide §1.5 交付物版本化:首份报告输出 report_v1.html, 报告被重做时(口径修正、用户反馈驱动、依赖数据重算)输出 report_v2.html、 report_v3.html…,不原地覆盖已有版本。步骤 5 自检失败后的修正属于同一版本内的 局部修正,可复用当前版本号。

5:生成后自检

报告生成后,必须逐项检查以下内容,任一项不通过则修正后重新生成:

布局与内容:

  • 每个主题的第一张卡片为数据概况卡,展示整体指标背景
  • 每个数据展示单元(图表、表格、或一组二级维度下拆数据)都配有独立的「现象」和「分析」
  • 多个数据单元(图表、表格等)优先用 grid 并排展示,充分利用页面空间,避免大面积空白
  • 表格宽度与列数匹配(如 2-6 列的表格不应独占全宽),具体规则见 references/layout-spec.md

图表类型:

  • 转化漏斗场景使用漏斗图,各环节标注转化率和绝对流失量
  • 趋势/折线图已用 markPoint / markLine 标注关键数据点,图表正下方有具体数值小字说明
  • 占比场景使用饼图/环形图,超 6 类已合并为「其他」
  • 多指标综合评估使用雷达图,维度已归一化
  • 表格视图的数值列已按颜色标注规范渲染
  • 所有图片均通过 ECharts 在页面内动态渲染,未引用任何 PNG/JPG 等静态图片文件
  • 长表格保持完整,不折叠、不拆分;超过 10 行的表格用滚动容器包裹,数据完整可滚动
  • 图表高度按数据点数量设置:≤5 个用 200px,6-12 个用 280px,13+ 个用 340px

归因分析:

  • 归因类卡片按数据重点分块,每块对应一个关键数据点或异常区间
  • 每条归因包含触发原因 + 具体动作描述,无只写原因不写动作的归因条目

时间线:

  • 分析中涉及业务事件时,已在 sections.json 末尾追加 "type": "timeline" 的 section
  • 时间线事件按时间升序排列,事件类型与性质匹配
  • 时间线为独立 section 条目,不在普通 tab 卡片内

数据准确性:

  • 所有数字来自读取的数据文件,不得编造或推测
  • 每个展示区域标注数据来源链接

© agentscope-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts, references) in packages/qwenpaw-data-skills/skills/atomic/bi-report-generation of agentscope-ai/QwenPaw-Data.

  • SKILL.md
  • references/layout-spec.md
  • resources/skeleton_template.html
  • scripts/report_builder.py

Open the folder on GitHubat commit e0bae36

Compare with similar skills

Bi Report Generation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Bi Report Generation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bi Report Generation this skillagentscope-ai/QwenPaw-Data127—~1.2kAutomated safety check: PassApache-2.0
Markdown Article FormatterJimLiu/baoyu-skills27k6 repos~3.5kAutomated safety check: PassMIT
MarkitdownImCa0/just-laws78114 repos~3.2kAutomated safety check: NotesMIT
Obsidian MarkdownAtmosphere/atmosphere3.8k20 repos~1.3kAutomated safety check: PassApache-2.0
DOCXrvdbreemen/OTGW-firmware20733 repos~4.3kAutomated safety check: PassProprietary
Word Document Reader and WriterHKUDS/DeepTutor41k—~2.5kAutomated safety check: PassApache-2.0

Similar skills

  • Markdown Article Formatter

    JimLiu/baoyu-skills

    Reformats plain text or Markdown articles with frontmatter, a title, a summary, headings, bold, lists and code blocks, and saves a separate formatted copy.

    27k GitHub starsUsed in 6 repos~3.5k tokens
    Documents & OfficeAuto-check passed
  • Markitdown

    ImCa0/just-laws

    Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.

    781 GitHub starsUsed in 14 repos~3.2k tokens
    Documents & OfficeAuto-check: notes
  • Obsidian Markdown

    Atmosphere/atmosphere

    Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax.

    3.8k GitHub starsUsed in 20 repos~1.3k tokens
    Documents & OfficeAuto-check passed
  • DOCX

    rvdbreemen/OTGW-firmware

    A skill your agent uses whenever the user wants to create, read, edit, or manipulate Word documents (.docx files).

    207 GitHub starsUsed in 33 repos~4.3k tokens
    Documents & OfficeAuto-check passed
  • Reads, creates and edits Word .docx files with python-docx, and drops to raw OOXML for tracked changes, comments and byte-exact edits.

    41k GitHub stars~2.5k tokensUpdated 2 days ago
    Documents & OfficeAuto-check passed
  • Crossposting

    wasp-lang/wasp

    Crosspost Wasp blog articles (MDX) to DEV.to and Medium. An agent skill from wasp-lang/wasp.

    19k GitHub stars~1.1k tokensUpdated yesterday
    Documents & OfficeAuto-check passed

More from agentscope-ai/QwenPaw-Data

All 29 skills in this repo
  • Fetch Data

    agentscope-ai/QwenPaw-Data

    取数 / 查数据 / 拉数据 / 跑 SQL。把自然语言取数需求转为 SQL,经数据湖仓执行后返回查询结果供下游分析。任何需要业务数据的任务在工作区缺少对应文件时都必须先调用此技能——覆盖 BI 业务分析、留存 / 转化 / 同期群分析、数据探索 EDA、统计建模、定量计算、元数据查询、数据查询。命中任一即触发:(1) 直接索要指标或记录,如「DAU 多少」「上月销售额」「3…

    127 GitHub stars~2.5k tokensUpdated 5 days ago
    Auto-check passed
  • Bi Adaptive Threshold

    agentscope-ai/QwenPaw-Data

    通过量化历史数据的自然波动幅度,自适应计算判定阈值。当需要从数据本身确定阈值(如波动阈值、影响度阈值等)、而非使用固定值时调用。仅适用于日/周粒度阈值确定。

    127 GitHub stars~726 tokensUpdated 5 days ago
    Auto-check passed
  • Bi Anomaly Detection

    agentscope-ai/QwenPaw-Data

    基于阈值检测时间序列中的显著异常波动点。当需要找出指标异常波动日期、识别数据异动时调用. An agent skill from agentscope-ai/QwenPaw-Data.

    127 GitHub stars~637 tokensUpdated 5 days ago
    Auto-check passed
  • Bi Attribution Analysis

    agentscope-ai/QwenPaw-Data

    计算各维度(组)值对指标变动的贡献度,支持可加型量值指标和加权平均型/率值指标。当需要计算贡献度、解释指标"为什么涨/跌"时调用。

    127 GitHub stars~1.2k tokensUpdated 5 days ago
    Auto-check passed
  • Bi Causal Attribution

    agentscope-ai/QwenPaw-Data

    从运营周报、活动文档、对话输入或文档工具 API 中提取业务事件,与指标异常时间窗口对齐,生成有证据支撑的因果归因假设并排序。当已知指标存在异常波动、需要从外部文档证据中解释"为什么"时调用。

    127 GitHub stars~1.3k tokensUpdated 5 days ago
    Auto-check passed
  • Bi Clustering

    agentscope-ai/QwenPaw-Data

    对用户、产品等业务对象做分群:用波士顿矩阵法做象限分群,或用分层聚类、K-means、DBSCAN 等聚类技术分群。当需要做客群/产品分群、象限策略、画像或密度型子结构发现时调用。触发条件:当对话中出现“分群”、“分类”、“聚类”、“不同类型”、“不同场景”等体现分群分析词语时触发。

    127 GitHub stars~1.6k tokensUpdated 5 days ago
    Auto-check passed

Questions about Bi Report Generation

What does Bi Report Generation do?

将 BI 数据分析结果组织成可视化 HTML 报告。当分析完成、需要生成报告时调用. An agent skill from agentscope-ai/QwenPaw-Data. Bi Report Generation is an agent skill from agentscope-ai/QwenPaw-Data.

When should I use Bi Report Generation?

Bi Report Generation fits situations like: documents & Office work in your project.

How do I install Bi Report Generation in Claude Code?

Run `npx skills add agentscope-ai/QwenPaw-Data --skill bi-report-generation -a claude-code`. Or copy the skill folder (packages/qwenpaw-data-skills/skills/atomic/bi-report-generation in agentscope-ai/QwenPaw-Data) into .claude/skills/bi-report-generation in your project. Claude Code loads it when a task matches its description.

How do I install Bi Report Generation in Codex?

Run `npx skills add agentscope-ai/QwenPaw-Data --skill bi-report-generation -a codex`. Or copy the skill folder (packages/qwenpaw-data-skills/skills/atomic/bi-report-generation in agentscope-ai/QwenPaw-Data) into .agents/skills/bi-report-generation in your project. Codex loads it when a task matches its description.

Can I use Bi Report Generation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agentscope-ai/QwenPaw-Data --skill bi-report-generation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bi-report-generation, .gemini/skills/bi-report-generation, .github/skills/bi-report-generation and .opencode/skills/bi-report-generation in your project.

What does Bi Report Generation need to run?

Going by SKILL.md and its folder, Bi Report Generation needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Bi Report Generation access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Bi Report Generation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Bi Report Generation use?

Bi Report Generation is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Bi Report Generation use?

About 1.2k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3k tokens, read only when the agent opens those files.

What are the alternatives to Bi Report Generation?

Skills that share tags, products or a category with Bi Report Generation: Markdown Article Formatter (JimLiu/baoyu-skills, 27k stars), Markitdown (ImCa0/just-laws, 781 stars), Obsidian Markdown (Atmosphere/atmosphere, 3.8k stars) and DOCX (rvdbreemen/OTGW-firmware, 207 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bi Report Generation?

agentscope-ai (a GitHub organization) maintains it in agentscope-ai/QwenPaw-Data, which has 127 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on October 5, 2026.

Source: agentscope-ai/QwenPaw-Data on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.