Wanwu is an enterprise platform for building AI agents, workflows, retrieval-augmented applications, and managing models in multi-tenant environments. It is designed for developers and enterprise teams delivering AI applications and integrations. The catalogue entries provide skills and agents for using the platform.
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/unicomai/wanwu/smart-data-analysisnpx skills add UnicomAI/wanwu --skill smart-data-analysisgit clone --depth 1 https://github.com/UnicomAI/wanwuWrote 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/unicomai/wanwu/smart-data-analysis)<a href="https://agentmods.dev/skills/unicomai/wanwu/smart-data-analysis"><img src="https://agentmods.dev/badge/skills/unicomai/wanwu/smart-data-analysis.svg" alt="Measured on agentmods" 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 | $0.00167 | $0.06821 |
| Opus 5 | $0.00084 | $0.03410 |
| Sonnet 5 | $0.00033 | $0.01364 |
| Haiku 4.5 | $0.00017 | $0.00682 |
Grade A, and why
smart-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 yesterday.
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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smart Data Analysis(总编排)
本 skill 是 数据分析员工角色的总入口:在本体数据技能栈中,所有数据相关问题必须先经过本 skill,完成 KN 与上下文对齐、意图路由 后,再委派至 找表 或 问数(或其它数据子 skill),禁止在未做编排判断时直接跳到 smart-search-tables、smart-ask-data 或零散工具调用。
Never 由本 skill 直接执行 ontology CLI;所有 CLI 调用(包括为选 KN 取候选元数据的 bkn list/get,与问数分支的 bkn object-type get / dataview query --sql 等)均委托 ontology-core 执行。
调用链:
smart-data-analysis(顶层意图 + LLM 决策:选 KN / 生成 SQL)
├─ ontology-core(直接委托:bkn list/get 等用于自身决策)
└─ smart-search-tables 或 smart-ask-data(子流程)
└─ ontology-core(子流程的 CLI 委托)
总入口原则(必须遵守)
- 先编排,后执行:识别用户问题是否属于「数据域」(资产/表/视图/指标/SQL/图表/职责/元数据/多 KN 等);若是,先走本节下方「编排总流程」与「路由识别」,再打开对应子 skill 或工具链。
- 单一前门:同一轮对话中新增的数据子任务,仍应 回到本 skill 的编排逻辑 决定是延续当前分支还是切换找表/问数。
- 按最终意图路由:先判断用户最终想要的是“定位数据资产(表/视图)”还是“拿到数据结果(指标/明细/统计/图表)”。前者走找表;后者走问数,必要时在问数分支内先找表再生成 SQL。
- 交接清晰:转入 smart-search-tables 或 smart-ask-data 时,在内部上下文中保留已解析的
kn_id_*、时间口径,避免子 skill 重复猜 KN。 - 非数据问题:与数据无关时 不必 强行套用本 skill;若用户一句话里混有数据与非数据,数据部分仍按上述原则经本 skill 编排(可分段回答)。
- 禁止交叉兜底:本轮路由为 问数 时,若问数走不通,禁止改走 找表 分支代替交付;路由为 找表 时,若找表走不通,禁止改走 问数 分支代替交付。两种情况下均应 直接输出走不通的原因(缺 KN、无命中、平台错误等)及用户侧可采取的修复条件。细则见下方「分支走不通时的处理(禁止交叉兜底)」。
知识网络声明(KN id 单一来源)
KN id 在下表中直接声明,由本 skill 路由时透传到下游(smart-ask-data / smart-search-tables)。下游 skill 不 自行选 KN、不 调 bkn list/get 枚举或决策。
| 分支 | 用途 | KN ID |
|---|---|---|
| 找表 | 表/视图实例检索(必填) | <填入KN id> |
| 找表 | 部门职责检索(可选) | <填入KN id> |
| 问数 | SQL 取数(必填) | <填入KN id> |
约束:
- 维护者一次性通过 ontology-core 调
bkn list取得平台可用 KN id 后,直接编辑本表填入;运行时不再做 KN 列举或选择。 - 若占位仍为
<填入...>:进入对应分支时直接告知用户"未在 smart-data-analysis/SKILL.md 中配置对应 KN",不得用其它 KN 凑数。 - 用户明确说「用 XX 知识网络问数 / 找表」→ 仅当该 id 等于上表已声明值时采用;否则提示用户先把该 KN 添加到本表再用。
与其它技能的分工
| 能力 | 本 skill(编排) | 专用 skill(执行细节) |
|---|---|---|
| 路由、kn 切换、上下文注入 | ✅ 主责 | 配合 |
| KN id 声明 + 透传到下游 | ✅ 主责(见上方「知识网络声明」表) | 接收注入,不自行选 KN |
| 找表 / 定位 / 职责 / 澄清 | 定义路由与交接 | smart-search-tables/SKILL.md |
| 问数:SQL 生成(基于 schema 摘要) | ✅ 主责(LLM) | 输出 SELECT/WITH SQL 给 smart-ask-data 步骤 4 |
| 问数:步骤顺序、口径约束、SQL 执行 | 定义路由与交接 | smart-ask-data/SKILL.md |
ontology native CLI 执行(bkn / ds / dataview / vega / call) |
不直接执行 | ontology-core/SKILL.md |
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.
- yesterday Changed · +23 lines 94d765cad289
- 2d ago First seen · 262 lines · 167 tokens per session scan A a7b864980e16
smart-data-analysis is a skill published in the GitHub repository UnicomAI/wanwu (2,458 stars, last pushed yesterday), licensed Apache-2.0. It adds 167 tokens to every session and 6,821 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
qdrant
Vector search engine for production RAG systems.
chroma
Embedding database for RAG and semantic search.
pinecone
Managed vector DB for production RAG and search.
vector-db
Vector database expert for embeddings, similarity search, RAG patterns, and indexing strategies.
usage
Wren Engine CLI workflow guide for AI agents. Answer data questions end-to-end using the wren CLI: gather schema context, recall past queries, write SQL through the MDL semantic layer, execute, and learn from confirmed results. Use when: user asks a data question, requests a report or analysis, asks about metrics…
dlt-connector
Connect SaaS data (HubSpot, Stripe, Salesforce, GitHub, Slack, etc.) to Wren Engine for SQL analysis. Guides the user through the full flow: install dlt, pick a SaaS source, set up credentials, run the data pipeline into DuckDB, then auto-generate a Wren semantic project from the loaded data. Use this skill whenever…