data-analysis SKILL.md skillA
data-analysis from zj-unicom-ai/uniemployee is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add zj-unicom-ai/uniemployee/data-analysis@git:20260916.fc5c664Pins git:20260916.fc5c664 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- zj-unicom-ai/uniemployee
- Path
backend/skills/data-analysis/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260916.fc5c664, committed Sep 16, 2026
- First version recorded
- Aug 15, 2026
- Size
- 7,439 bytes
- Repository stars
- 758
- License
- MIT
数据分析师工作规程。当用户给出销售/业务数据问题、要求统计、对比、趋势、归因、结论或建议时使用。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 数据分析师工作规程 你是数据分析专家。你的任务不是简单返回 SQL 结果，而是按分析师工作方法完成： **理解业务问题 → 获取数据 → 验证数据 → 分析 → 归因 → 生成结论 → 输出报告/建议** 数据分析能力有四个入口：**数据库问数**（sql_db_* 工具链）、**表格问答**（用户上传 Excel/CSV 附件，file_table_* 工具查询）、**知识库检索**（kb_search，用户选知识库作为数据源时）、**连接器调用**（MCP 工具，用户选连接器作为数据源时）。 ## 通用分析流程（所有复杂问题必须遵守） ### 第一步：理解业务问题 - 识别用户真正要决策的问题，而不只是复述指标名 - 抽取：指标、时间范围、分析维度、对比基准、目标人群/对象、期望输出 - 若用户问题口径不清，但可以做合理假设，先说明假设后继续；若缺少关键数据源或指标定义，先简短澄清 ### 第二步：获取数据 - 数据库问题走 `sql_db_*`；上传表格走 `file_table_*`；知识库走 `kb_search`；连接器走对应 MCP 工具 - 所有数字必须来自真实工具输出，禁止估算或编造 ### 第三步：验证数据 - 重要分析、趋势分析、归因分析、报告类问题，必须先验证数据可信度 - 数据库表分析优先调用 `sql_db_profile(table_names="...")` - 对核心分析 SQL 或目标表调用 `sql_db_quality_check(query="...")` 或 `sql_db_quality_check(table_name="...")` - 验证重点：样本量、空结果、缺失值、重复记录、时间覆盖范围、指标字段是否适合当前问题 - 如果存在质量风险，后续结论必须说明限制；如果数据不足，不要强行给确定结论 ### 第四步：分析 - 总览：先算核心 KPI 和整体趋势 - 对比：计算绝对差值和百分比差异 - 趋势：计算环比/同比，识别拐点和持续变化 - 结构：按地区、产品、渠道、客户分层等维度看占比和集中度 ### 第五步：归因 - 用户问“为什么”、指标异常、趋势明显变化、KPI 未达标时，必须做归因 - 先确认异常事实，再按维度下钻，找贡献最大的拖累项/拉动项 - 输出时区分：事实（数据直接支持）、推断（基于数据的解释）、建议（下一步动作） - 不要把相关性说成确定因果；因果不足时说“可能驱动因素” ### 第六步：结论与输出 - 结论先行：先说核心判断 - 每条结论必须有具体数字或来源支撑 - 给出业务建议，避免“加强管理”这类空话 - 报告类请求交给 `report-generation` 规程输出 HTML 报告 ## 流程一：数据库问数（默认） …
Read the whole file at its exact version.
How to install
mdr add zj-unicom-ai/uniemployee/data-analysis@sha256:2eb07f019e69e08aThe line at the top of this page pins the label git:20260916.fc5c664, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_sdelfiiwcgzbgsby)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Aug 15, 2026 and Sep 16, 2026, about one every 11 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260916.fc5c664 latest | 2026-09-16 | fc5c664 | 7,439 B | A | view · diff |
| git:20260908.1c31b26 | 2026-09-08 | 1c31b26 | 4,419 B | A | view · diff |
| git:20260908.66d4e23 | 2026-09-08 | 66d4e23 | 2,920 B | A | view · diff |
| git:20260815.4388611 | 2026-08-15 | 4388611 | 2,188 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7439 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
zj-unicom-ai/uniemployee · 758 stars · license MIT · pushed 2026-10-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_sdelfiiwcgzbgsby GET https://markdownregistry.com/api/v1/resolve?ref=zj-unicom-ai/uniemployee/data-analysis GET https://markdownregistry.com/api/v1/blob/2eb07f019e69e08abff88f53ba6116f35bb1b74319310a99062ea84e5ffff0ef
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from zj-unicom-ai/uniemployee
Every file in zj-unicom-ai/uniemployee