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 zj-unicom-ai/UniEmployee --skill data-analysisgit clone --depth 1 https://github.com/zj-unicom-ai/UniEmployeeWrote 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/zj-unicom-ai/uniemployee/data-analysis)<a href="https://agentmods.dev/skills/zj-unicom-ai/uniemployee/data-analysis"><img src="https://agentmods.dev/badge/skills/zj-unicom-ai/uniemployee/data-analysis/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/zj-unicom-ai/uniemployee/data-analysis"><img src="https://agentmods.dev/badge/skills/zj-unicom-ai/uniemployee/data-analysis.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 | $0.00037 | $0.01994 |
| Opus 5.5 | $0.00015 | $0.00798 |
| Sonnet 5.5 | $0.00007 | $0.00399 |
| Haiku 4.5 | $0.00004 | $0.00199 |
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 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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）
用户问题未涉及上传附件时，一律走 SQL 工具链。
第一步：检索表结构（必须先调用）
- 调用
sql_db_smart_search(user_query="用户问题")获取最相关的表结构 - datasource_id 可不传，会话会自动注入当前选中的数据源
- 工具用 BM25 检索最相关的表，表数 ≤ 20 时返回全量
第二步：获取表关系（多表查询时）
- 调用
sql_db_table_relationship(table_names="表名1,表名2")获取外键关联
第三步：分析前验证
- 单点问数可跳过画像，但复杂分析、趋势、归因、报告必须调用
sql_db_profile或sql_db_quality_check - 核心 SQL 执行后，如结果用于重要结论，应调用
sql_db_quality_check(query="核心 SQL")检查样本量和缺失风险
第四步：编写并执行 SQL
- 只允许 SELECT 查询，禁止 INSERT/UPDATE/DELETE/DROP 等
- 结果限制 100 行
- 可先用
sql_db_query_checker(query)检查语法 - 用
sql_db_query(query)执行（datasource_id 可不传）
第五步：分析结果
- 如涉及客户/订单/产品等实体，可调用
ontology_find_entities关联本体 - 生成数据摘要、归因判断、质量限制和业务建议
流程二：表格问答（用户上传 Excel/CSV 附件时）
用户消息中出现「表格附件已自动注册为可查询数据表」时，走本流程：
第一步：了解表结构
- 消息里已列出注册表名/字段/行数；需要更多细节时调用
file_table_list() - 表名/字段名含中文或特殊字符时，SQL 中用双引号包裹
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 Changed · +49 lines · +7 tokens per session 2eb07f019e69
- 1mo ago Changed · +57 lines 86131ba7a310
- 1mo ago First seen · 40 lines · 30 tokens per session scan A 3b8140cfbcc4
data-analysis is a skill published in the GitHub repository zj-unicom-ai/UniEmployee (578 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 1,994 once invoked, about $0.0001 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
action-contract-execution-feedback-loop
A specification method for making a business action into a tool an AI agent can call safely. It defines the action’s inputs, outputs, permissions, preconditions, expected effects, error handling, and audit information.
fact-reason-action-business-loop
A method for connecting observed facts, business rules, and permitted actions into one traceable loop. It records what happened, explains why a conclusion follows, defines allowed actions, and captures the results.
five-ring-ontology-engineering-lifecycle
A five-stage method for planning an enterprise ontology, a structured model of the concepts and relationships used across a business, from source material through ongoing use.
ontology-ai-application-pattern-selection
A method for choosing how an AI system should handle a business problem after deciding that an ontology—a structured map of concepts and relationships—is suitable. It compares patterns such as workflow automation, decision support, knowledge answering, collaboration, and continuous planning.
ontology-ai-scenario-fit-and-spike
A method for deciding whether an ontology is suitable for an enterprise AI scenario and testing that choice with a small end-to-end sample. An ontology is a structured model of concepts, rules, and relationships.
ontology-constraint-and-knowledge-injection
A method for deciding how an ontology’s knowledge should reach an AI model: directly in its instructions, through RAG, or through fine-tuning. RAG retrieves relevant information at answer time; fine-tuning changes the model using training examples.