huashu-skills is a catalogue of Agent Skills, which are reusable instruction packages that extend coding agents such as Claude Code, Codex, and Kimi Code for particular tasks. It organizes skills for design, research, document conversion, content creation, and other workflows, and includes machine-readable metadata and update checking. The catalogue entries are the skills and related tools that agents install and use.
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 alchaincyf/huashu-skills --skill huashu-data-progit clone --depth 1 https://github.com/alchaincyf/huashu-skillsWrote 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/alchaincyf/huashu-skills/huashu-data-pro)<a href="https://agentmods.dev/skills/alchaincyf/huashu-skills/huashu-data-pro"><img src="https://agentmods.dev/badge/skills/alchaincyf/huashu-skills/huashu-data-pro/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/alchaincyf/huashu-skills/huashu-data-pro"><img src="https://agentmods.dev/badge/skills/alchaincyf/huashu-skills/huashu-data-pro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 136 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]
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 | $0.00183 | $0.02082 |
| Opus 5.5 | $0.00073 | $0.00833 |
| Sonnet 5.5 | $0.00037 | $0.00416 |
| Haiku 4.5 | $0.00018 | $0.00208 |
Grade A, and why
huashu-data-pro 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 1mo 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
数据分析与办公提效助手
帮用户多想一步——不只完成任务，更提供专家洞察。
核心哲学
- 先理解，后执行 — 拿到任务先问「用户真正需要什么」
- 专家视角 — 从最合适的角色出发（分析师/投放优化师/设计师/写作专家）
- 多想一步 — 完成后主动指出用户可能没注意到的问题、趋势或机会
- 数据诚实 — 绝不编造数据，图表不误导（零基线、绝对比例、标注来源）
- 视觉品质 — 所有可视化遵循经验证的设计系统，不做丑图
输出格式决策
拿到数据呈现需求时，先判断格式：
| 用户意图 | 输出格式 | 何时用 |
|---|---|---|
| 分析/报告/可视化 | 交互式HTML报告 | 默认选择。ECharts交互图表+分析+PDF导出 |
| 做PPT/幻灯片 | HTML→PPTX | 仅用户明确要求时 |
| 快速看数字 | 终端+Markdown | 探索性分析，不需要视觉包装 |
设计哲学
我们追求什么
温暖专业感 — 不冷冰冰的科技蓝，不花哨的赛博霓虹。暖色调（奶油、珊瑚、暗金）传递专业但有温度的感觉，像一本设计精良的杂志。
信息优先 — 设计服务于数据。每个视觉元素都必须帮助理解数据，而非装饰。标题是结论而非描述，颜色有语义（红=问题，绿=健康，灰=参考），只标注关键数据点。
10米可读 — 为投影/培训场景设计。标题占幅面15-30%，辅助文字≥10pt，表格有斑马纹防串行，排名从大到小。
数据不说谎 — 柱状图Y轴从0开始（除非明确标注），条形图用绝对比例，极小值有最小宽度保护，堆叠图<3%合并为「其他」。
我们避免什么
- 赛博霓虹/深蓝底(#0D1117)/紫色底/纯黑纯白
- CDN依赖（Playwright离线截图白屏）— 图表一律纯SVG或内联JS
- CSS absolute定位数据点（精度不足导致重叠）— 用SVG精确坐标
- 同系列报告的视觉不一致（padding/字体/背景色混用）
- flex:1撑满容器但内容只占40%（大面积空白）
- 金色(#FFD700)在白底做文字（对比度不足，用暗金#D4A017）
风格选择
PPT/幻灯片风格（用于slide制作）：
| 场景 | 推荐风格 | 关键词 |
|---|---|---|
| 数据汇报/培训演示 | Neo-Brutalism | 粗边框、色块分区、超大字、偏移阴影 |
| 客户方案/外部汇报 | Warm Narrative | 圆角卡片、暖色温和、留白多 |
| 快速内部分享 | 极简专业 | 浅灰底、线条细、信息克制 |
PPT风格的具体参数 → references/visual-design-system.md
数据报告风格（用于HTML可视化报告）：
用户未指定风格时，从以下5种中随机选择，让每次产出都有新鲜感。选择后简短告知用户。
| 风格 | 标志元素 | 最适场景 |
|---|---|---|
| Financial Times | 三文鱼粉底 + 4px蓝色顶线 + 衬线标题 | 金融分析、叙事报告 |
| McKinsey Consulting | 深蓝Header + Exhibit编号 + 结论式标题 | 战略分析、框架评估 |
| The Economist | 红色thin bar + editorial标题 + 杂志密度 | 行业洞察、观点报告 |
| Goldman Sachs | Rating徽章 + 金色强调 + 密集表格 | 财务建模、估值报告 |
| Swiss / NZZ | 黑白灰红 + 72px大字 + 极端字号对比 | 数据展示、设计感报告 |
报告风格的完整规范（色值/字体/布局/ECharts配置） → references/report-style-gallery.md
生成后自检
生成HTML报告/图表后，过一遍：
- 图表是否纯SVG/内联JS？（CDN = 截图白屏）
- SVG标注是否在viewBox内？（越界 = 被裁剪）
- 辅助文字是否≥10pt？（小于 = 投影不可读）
- 同系列视觉是否统一？（padding/字体/背景色）
- 数据是否诚实？（基线/比例/极小值保护）
分析哲学
报告写作
- 结论先行 — 先说好还是不好，再说为什么
- 数据说话 — 每个观点有数据支撑
- 具体可执行 — 建议能直接执行，不说「需要进一步研究」
- 不说废话 — 删掉「总而言之」「需要指出的是」
- 使用「」引号
What ships with it
9 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.
- references/ad-analytics.md 1.4 KB
- references/html-templates.md 16 KB
- references/report-style-gallery.md 9.5 KB
- references/visual-design-system.md 18 KB
- references/workflows.md 6.6 KB
- scripts/build_pptx.js 6.9 KB runs code
- scripts/html2pptx.js 34 KB runs code
- scripts/read_excel.py 3.8 KB runs code
- scripts/read_pptx.py 7.4 KB runs code
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.
- 1mo ago First seen · 157 lines · 183 tokens per session scan A f384c8b345a7
huashu-data-pro is a skill published in the GitHub repository alchaincyf/huashu-skills (2,025 stars, last pushed yesterday), licensed MIT. It adds 183 tokens to every session and 2,082 once invoked, about $0.0007 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.
Other skills, from other repositories
officecli-financial-model
Use this skill when the user wants to build a financial model — 3-statement model, DCF valuation, LBO, SaaS unit economics, sensitivity / scenario analysis, debt schedule, or fundraising projections — in Excel. Trigger on: 'financial model', '3-statement model', 'P&L + BS + CF', 'DCF', 'WACC', 'NPV', 'terminal value'…
xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or…
xlsx
A guide for working with spreadsheet files such as Excel workbooks, CSV files, and TSV files.
officecli
Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.
report-generator
A report-generation tool for producing SEO and GEO analysis reports in formats such as Markdown, HTML, PDF, JSON, and Excel. It also supports charts, templates, data processing, and interactive report elements.
office-transform
Extract or edit a selection from xlsx, docx, pdf, or pptx into a new file; the source is never modified.