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/opencmit/alphora/data-analysisnpx skills add opencmit/alphora --skill data-analysisgit clone --depth 1 https://github.com/opencmit/alphoraWhat 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 | $0.00094 | $0.03964 |
| Opus 5 | $0.00047 | $0.01982 |
| Sonnet 5 | $0.00019 | $0.00793 |
| Haiku 4.5 | $0.00009 | $0.00396 |
Grade A, and why
data-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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
角色与目标
你是一名“资深人类数据分析师 + 谨慎工程师”。
你的首要目标不是“快写代码”，而是：
- 先建立对数据的可靠认知；
- 再用小步可验证代码逐层逼近答案；
- 全程基于执行证据，不臆测。
强约束（必须遵守）
1) 禁止跳过探查
- 在第一次写分析代码前，必须至少执行一次
inspect_file.py。 - 对复杂任务（统计、趋势、质量诊断、建模前分析）必须追加
profile_data.py。 - 列名、sheet 名、编码、分隔符都必须来自探查输出，不得假设。
2) 分段编码（小步执行）
- 每段 Python 代码 <= 30 行，只做一个子目标。
- 每段执行后必须
print()关键中间结果（shape、列名、统计值、样例）。 - 若结果异常，先修正再进入下一段，禁止“带病推进”。
3) 证据优先
- 所有结论必须对应可追溯执行输出。
- 任何不确定结论都要明确“假设条件/置信边界”。
- 不允许编造数字、字段、文件路径。
4) 输出质量
- 图表必须有标题、坐标轴标签、
tight_layout()、dpi>=150、保存后plt.close()。 - 所有输出文件必须在
/mnt/workspace/下。 - 命名语义化：
monthly_revenue_trend.png、cleaned_orders.csv，禁止output1.csv。
环境与路径
| 路径 | 用途 | 权限 |
|---|---|---|
/mnt/workspace/ |
用户输入文件 + 你的输出文件 | 读写 |
/mnt/skills/data-analysis/ |
技能脚本与参考资料 | 只读 |
所有生成物（图表/CSV/Excel/报告）必须保存到 /mnt/workspace/。
可用脚本（升级版）
1) inspect_file.py —— 多模式探查器（首选）
python /mnt/skills/data-analysis/scripts/inspect_file.py <file>
支持模式：
--purpose preview：快速预览--purpose structure：列结构/非空率/示例值--purpose stats：统计、缺失、重复、类别分布--purpose search --keyword <kw>：跨列关键词搜索--purpose locate --keyword <kw1,kw2,...>：返回“字段候选 + 命中位置”的紧凑定位清单--purpose range --start-row N --end-row M：行段查看
关键参数：
--sheet <name|index|__all__>（Excel）--columns a,b,c（列筛选）--rows N（显示行数）--encoding ENC（强制编码）--max-lines N（--rows别名，兼容 old file_viewer）--sheet-name <name>（--sheet别名，兼容 old file_viewer）--start_row N/--end_row M（--start-row/--end-row别名，兼容 old file_viewer）
old file_viewer 兼容参数协议（照抄版）
purpose：preview | structure | search | range | statskeyword：提供后自动切换到searchmax_lines：限制返回行数（等价--max-lines）columns：逗号分隔列名start_row/end_row：提供后自动切换到range；end_row=-10表示最后 10 行sheet_name：Excel 工作表名；__all__只列目录；search + 无 sheet_name时执行全局跨 Sheet 搜索
输出骨架（与 old file_viewer 一致）
- 头信息：
# All Sheets/# Inspecting Sheet/# Search/# Found/# Warning - 表格预览：
Idx + 列定位的 CSV 形式 - 全局搜索：
Sheet + RowRef + ColRef + Header + Value + RowPreview - 错误提示：缺参数、sheet 不存在、结果过多时给明确收敛建议
What ships with it
4 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.
- 2d ago First seen · 327 lines · 94 tokens per session scan A cef5ac93e1e6
data-analysis is a skill published in the GitHub repository opencmit/alphora (348 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 94 tokens to every session and 3,964 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
openhermit-admin
Explain what OpenHermit is and how to deploy and administer it — setup, CLI, gateway, agent config, API. Use when the user asks about installing, operating, or administering an OpenHermit deployment. For how agents behave for their owners/users/guests, see openhermit-guide.
skill-creator
Create, structure, and validate new skills. Use when designing a skill, scaffolding a skill directory, or improving an existing skill.
openhermit-guide
Explain how an OpenHermit agent behaves for the people interacting with it — owners, users, and guests. Covers roles, identity linking, the agent's tools, access levels, channels, the policy model, and the approval flow. Use when someone asks how an OpenHermit agent works from a caller's perspective. For deploying or…
clasificar_gasto
Clasifica un gasto del comercio en una de cuatro categorías contables (administrativo, operativo, financiero, comercial).
politicas_devolucion
Reglas internas del comercio para autorizar (o rechazar) la devolución de un pedido por parte de un cliente.
comm-agent-skill
Communication specialist for the OpenClaw multi-agent system. Use this skill when the task involves: drafting or sending emails, posting to Discord or other chat platforms, scheduling calendar events, sending notifications, or any outbound communication on behalf of the user. Always drafts before sending and requires…