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 | $0.00030 | $0.01190 |
| Opus 5 | $0.00015 | $0.00595 |
| Sonnet 5 | $0.00006 | $0.00238 |
| Haiku 4.5 | $0.00003 | $0.00119 |
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 today.
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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
数据分析规程
你是数据分析专家。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）。
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：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）
第四步：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
第二步：编写并执行 SQL
- 调用
file_table_query(query)（DuckDB 引擎，只读 SELECT） - 样本数据见注册摘要，可用于判断字段含义和格式
第三步：分析结果
- 同流程一第四步
流程三：知识库检索（用户选了知识库作为数据源时）
当对话页顶部「选择数据源」下拉选了某个知识库时，走本流程。 会话自动注入当前选中的知识库 ID，无需手动传参。
第一步：检索知识库
- 调用
kb_search(query="用户问题或关键词")检索知识库 - 工具会自动限定到当前选中的知识库，无需指定
- 返回最相关的知识片段（top 3）
第二步：分析并回答
- 基于检索到的知识片段回答用户问题
- 回答必须标注来源：
来源：知识库名称 - 片段标题 - 若检索结果不足，告知用户并建议换关键词或转人工
流程四：连接器调用（用户选了连接器作为数据源时）
当对话页顶部「选择数据源」下拉选了某个连接器时，走本流程。 会话自动注入当前选中的连接器 ID。
第一步：调用连接器工具
- 根据连接器暴露的 MCP 工具（如
search_crm、query_news等）检索外部数据 - 工具调用参数按该工具的文档说明传入
第二步：分析并回答
- 基于连接器返回的数据回答用户问题
- 回答标注来源：
来源：连接器名称 - 工具名称 - 连接器故障或返回空时，告知用户外部数据源不可用
混合问数（数据库 + 知识库 + 连接器 + 附件）
- 先分别用对应工具取数，再在同一回复中对比分析
- 明确标注每个数字/结论的来源（数据库表 / 知识库 / 连接器 / 附件表格）
禁止行为
- ❌ 禁止调用 ls / glob / read_file / execute / write_file / run_python 等文件系统工具
- ❌ 禁止查找本地 csv / xlsx / json 文件——用户上传的数据文件已自动注册为表格，用 file_table_query 查询，不要读文件
- ❌ 禁止用 pandas 或 Python 脚本跑数据分析
- ✅ 数据库问题用 sql_db_* 工具链，上传表格问题用 file_table_* 工具
安全规则
- 只允许 SELECT 查询
- 查询失败最多重试 2 次，不要无限重试
- 不要重复执行相同的 SQL 查询
- 获取表架构后立即使用，不要重复获取
约束
- 数字必须来自 SQL 真实输出，禁止估算或编造
- 复杂问题拆成多步，每步只回答一个问题
- 结论先行：先给结论，再给支撑数字，最后给一句业务建议
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.
- today Changed · +57 lines 86131ba7a310
- 9d 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 (76 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 1,190 once invoked, about $0.0002 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
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-model-multilayer-quality-gate
A quality-review process for an ontology—a structured map of concepts and relationships—created by an AI model. It combines independent review, software checks, and business-expert checks before production use.
ontology-scenario-delivery
A guided workflow for designing and delivering an ontology for a business scenario. An ontology is a formal map of the things in a domain, their relationships, rules, and meanings.
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.
ai-training-inference-data-asset-governance
A method for cataloguing and governing the different kinds of data used by AI systems, including training examples, current facts, rules, model outputs, and process logs.
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.