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 skills add UnicomAI/wanwu --skill smart-ask-datagit 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-ask-data)<a href="https://agentmods.dev/skills/unicomai/wanwu/smart-ask-data"><img src="https://agentmods.dev/badge/skills/unicomai/wanwu/smart-ask-data/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/unicomai/wanwu/smart-ask-data"><img src="https://agentmods.dev/badge/skills/unicomai/wanwu/smart-ask-data.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 | $0.00092 | $0.02493 |
| Opus 5 | $0.00046 | $0.01247 |
| Sonnet 5 | $0.00018 | $0.00499 |
| Haiku 4.5 | $0.00009 | $0.00249 |
Grade A, and why
smart-ask-data 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 5d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smart Ask Data（问数）
本 skill 定义 固定先后顺序 的问数工具链，完全由 ontology native 子命令（bkn / dataview / ds）实现。
在数据分析员工体系中，本 skill 必须由 smart-data-analysis 总入口完成意图、选 KN、生成 SQL 等 LLM 决策后再进入执行；CLI 实际执行由 ontology-core 承担。
调用方式（统一 ontology 命令；委托 ontology-core 执行）
本 skill 涉及的所有数据/Schema 访问 必须 通过 ontology native 子命令发起。
Never 由本 skill 直接执行 ontology CLI；所有 CLI 执行均委托 ontology-core 完成。调用链固定：
smart-data-analysis（顶层意图 + LLM 决策：选 KN、生成 SQL）
└─ smart-ask-data（本 skill：描述要调的命令形态 + 顺序 + 约束）
└─ ontology-core（实际执行 ontology 命令，返回结果）
子技能依赖
| 子技能 | 角色 | 返回 | 约束 |
|---|---|---|---|
| smart-data-analysis | 顶层意图路由、KN 选择、SQL 生成 | 进入本 skill 的上下文（kn_id / 生成的 SQL / accountId 等） |
Never 跳过 smart-data-analysis 直接接管流程 |
| ontology-core | smart-ask-data 的 CLI 委托 | 命令执行结果与回执 | Never 跳过 smart-ask-data 直接接管流程 |
委托给 ontology-core 的命令形态
本 skill 仅 描述 下列命令形态供 ontology-core 执行；本文档与 references 中 不出现 真实执行入口。
ontology --user-id <accountId> <command> [options]
具体 4 个步骤对应到 native 子命令（详见各 reference）：
| 步骤 | native 子命令 | 用途 |
|---|---|---|
| 1. 找 KN | bkn get <kn-id> |
取详情供 LLM 选择 |
| 2. 取字段与 dataview-id | bkn object-type list <kn-id> / bkn object-type get <kn-id> <ot-id> |
拿字段 + 后端 dataview-id |
| 3. 执行 SQL | dataview query <dataview-id> --sql "..." |
LLM 生成的 SELECT/WITH SQL（mdl-uniquery） |
| —（简单单表） | bkn object-type query <kn-id> <ot-id> '<filter-json>' |
不需要 SQL 时的实例过滤 + 分页 |
--user-id <accountId>：必传（顶层选项，写在子命令之前；发送为x-account-id；详见 ontology-core SKILL）。- 网关（
--base-url/ONTOLOGY_BASE_URL）由 ontology-core 侧承担，本 skill 不出现该参数。 - 本部署
ontologyCLI 无须 token；本 skill 命令体内 不出现--token/auth.token/Authorization。 -bd bd_public：默认即bd_public，可省。
必读 references（按步骤）
| 步骤 | 说明 | Reference |
|---|---|---|
| 1 | 知识网络选择（条件执行） | references/kn-resolve.md |
| 2 | Schema 发现：候选对象类与字段 | references/schema-discovery.md |
| 3 | SQL 生成（编排层 LLM）+ 执行 | references/sql-execute.md |
| — | 端到端顺序示例 | references/tool-examples.md |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago Changed · +10 lines c5d23c7e5eaf
- 6d ago First seen · 133 lines · 92 tokens per session scan A 72662fdd02dc
smart-ask-data is a skill published in the GitHub repository UnicomAI/wanwu (2,461 stars, last pushed 6d ago), licensed Apache-2.0. It adds 92 tokens to every session and 2,493 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 2026-09-03.
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…