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 report-generationgit 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/report-generation)<a href="https://agentmods.dev/skills/zj-unicom-ai/uniemployee/report-generation"><img src="https://agentmods.dev/badge/skills/zj-unicom-ai/uniemployee/report-generation/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/report-generation"><img src="https://agentmods.dev/badge/skills/zj-unicom-ai/uniemployee/report-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00095 | $0.06461 |
| Opus 5 | $0.00048 | $0.03231 |
| Sonnet 5 | $0.00019 | $0.01292 |
| Haiku 4.5 | $0.00010 | $0.00646 |
Grade A, and why
report-generation 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 — 545 lines — stays where its author put it; the contents beside it link to each section on GitHub.
报告生成技能
⚠️ 输出方式红线（最高优先级，违反即失败）
报告 HTML 必须作为助手消息文本的一部分，直接输出到对话窗口——用 <!-- REPORT_HTML_START --> 和 <!-- REPORT_HTML_END --> 分隔符独占行包裹完整 HTML，让前端用 iframe srcdoc 渲染并提供下载/新窗口打开按钮，用户在对话里即可点击查看。
严禁调用以下任何文件系统工具把报告写到磁盘：
- ❌
write_file/edit_file/delete—— 不要把 HTML 内容写到workspace/data/或任何路径 - ❌
execute—— 不要用 shell 命令（echo > file.html、cat <<EOF > ...）落盘 - ❌
ls/glob/read_file—— 不要去探查或读取本地已存在的 html 文件
也禁止在回复里告诉用户"报告已保存到 /xxx/yyy.html"或类似路径——你无权写文件，写不出来也不要假装写了。前端只会从对话文本里提取分隔符包裹的 HTML 段来渲染，写到磁盘的 HTML 用户看不到也打不开。
正确输出长这样（节选）：
根据查询结果，为您生成《2024 月度销售趋势报告》：
<!-- REPORT_HTML_START -->
<!DOCTYPE html>
<html lang="zh-CN">
... 完整 HTML（含 ECharts CDN + CSS + 数据 + 初始化脚本）...
</html>
<!-- REPORT_HTML_END -->
报告已生成完毕，包含 KPI 卡片 4 个、图表 3 个...
何时使用
用户提出以下任意诉求时启用本技能：
- 显式关键词：报告、分析报告、可视化报告、趋势报告、统计报告、月报、周报、季度复盘、专题分析
- 隐式诉求：用户希望"总结、汇总、复盘、对比、看趋势、看分布、看排名、给老板看"等需要结构化呈现的场景
普通单点问数（用户只想知道一个具体数字、一条 SQL 结果）走 data-analysis 规程，不要误用本技能。
不可违反的约束
- HTML 必须用分隔符
<!-- REPORT_HTML_START -->和<!-- REPORT_HTML_END -->独占行包裹后，作为消息文本直接输出——见顶部红线块，禁止write_file/edit_file/execute落盘，禁止谎称"已保存到某路径" - 查询完数据后必须立即生成报告，禁止中途停顿、问用户"要不要继续"
- 本技能是流程指令文档，按步骤一次性走完，不要说"调用技能"然后停下
- 报告中的所有数字必须来自 SQL 真实输出，禁止估算、编造、四舍五入到"看起来合理"的整数
- 遵守 xiaoshu 的安全规则：只允许 SELECT，结果限制 100 行，查询失败最多重试 2 次
- HTML 单文件自包含：所有 CSS/JS 内联，除 ECharts CDN 外无外部依赖
- 不使用 emoji 作为图标（报告正文中允许 ↑↓→← 等方向符号）
工作流程（7 步，必须全部完成）
第 1 步：理解需求
从用户诉求中提取并默念（不必输出）：
- 报告主题：销售、用户、产品、运营、财务、客诉等
- 关键指标：总量、增长率、排名、占比、转化率、复购率等
- 分析维度：时间、地区、品类、渠道、客户分群等
- 时间范围：最近一周/月/季度/年，或具体日期段
- 决策视角：报告读者是老板、运营、销售负责人——决定结论的颗粒度
第 2 步：检索表结构
调用 sql_db_smart_search(user_query="用户报告诉求原话") 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
- 根据 user_query 语义判断需要哪些表，通常 3-8 张
若涉及多表 JOIN，再调用：
sql_db_table_schema(table_names="表1,表2")获取字段详情sql_db_table_relationship(table_names="表1,表2")获取外键关联
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 · 545 lines · 95 tokens per session scan A 740130a3ce3e
report-generation is a skill published in the GitHub repository zj-unicom-ai/UniEmployee (86 stars, last pushed yesterday), licensed MIT. It adds 95 tokens to every session and 6,461 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 2026-09-09.
Other skills, from other repositories
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.
ontology-golden-case-testing
A testing method for an ontology, which is a structured model of business concepts and rules. It starts with real business questions and expected answers, then adds boundary, missing-data, conflict, permission, and regression tests.
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.