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 bkn-creatorgit 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/bkn-creator)<a href="https://agentmods.dev/skills/unicomai/wanwu/bkn-creator"><img src="https://agentmods.dev/badge/skills/unicomai/wanwu/bkn-creator/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/bkn-creator"><img src="https://agentmods.dev/badge/skills/unicomai/wanwu/bkn-creator.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 | $0.00221 | $0.01463 |
| Opus 5 | $0.00111 | $0.00732 |
| Sonnet 5 | $0.00044 | $0.00293 |
| Haiku 4.5 | $0.00022 | $0.00146 |
Grade A, and why
bkn-creator 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 6d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BKN 编排器（CRUD + 渐进式）
角色定位：流程编排器 + 生命周期管理器。
Never 直接执行 ontology CLI；所有执行均委托子技能完成。
职能矩阵（谁做什么）
| 组件 | 输入 | 输出 | 禁止事项 |
|---|---|---|---|
| bkn-creator | 用户意图、上下文、各子流程结果 | 阶段推进决策、确认门禁、最终回执 | Never 直接执行 CLI；Never 绕过确认门禁 |
| ontology-core | bkn-creator 的 CLI 委托 | 命令执行结果与回执 | Never 跳过 bkn-creator 直接接管流程 |
| create-bkn | 已确认的建模清单 | 标准 .bkn 文件树 |
Never 改写流程门禁 |
| bkn-modeling-advisor | 模糊业务意图、领域上下文 | 结构化建模清单 | Never 直接推进阶段三/四/五 |
流程路由（第一层）
| 意图 | 关键词 | 路由目标 |
|---|---|---|
| 新增（Create） | 创建、新建、建立、搭建、本体建模 | ./FLOW_CREATE.md |
| 提取（Extract） | 提取对象类、提取关系类、抽取实体关系、对象关系梳理 | ./FLOW_EXTRACT_TYPES.md |
| 查找（Read） | 查询、搜索、列出、有哪些、看看 | ./FLOW_READ.md |
| 更新（Update） | 修改、编辑、更新、调整、改一下 | ./FLOW_UPDATE.md |
| 删除（Delete） | 删除、清除、移除、去掉 | ./FLOW_DELETE.md |
MUST 回显流程路由识别结果并等待用户确认后进入对应流程。意图不明确时先澄清。
MUST 在"流程路由确认（验证阶段）"通过前，Never 进入任何 FLOW_* 的阶段化执行与对用户阶段回显（包括"阶段一/Step 1"等内容）。
渐进式执行协议（第二层）
所有 CRUD 流程统一遵循：
discover -> preview -> confirm -> execute -> verify -> report
完整确认语义、门禁规则、全局硬约束见：./COMMON_RULES.md。
子流程调用规则（第三层）
仅当"流程路由确认"通过后，才可读取并执行对应 FLOW_*.md 的阶段内容。
- 新增：读取
./FLOW_CREATE.md - 提取：读取
./FLOW_EXTRACT_TYPES.md - 查找：读取
./FLOW_READ.md - 更新：读取
./FLOW_UPDATE.md - 删除：读取
./FLOW_DELETE.md
顶层约束（路由阶段即生效）
以下约束在加载任何 FLOW_*.md 之前即生效；细则统一以 ./COMMON_RULES.md 为准：
- MUST：流程路由确认未通过时，仅允许输出“流程路由识别结果 + 确认请求”
- MUST：任何写操作必须先完成确认步骤
- MUST：凡需执行 CLI，统一委托
../ontology-core/SKILL.md - MUST：对用户输出使用专业文本，不使用 emoji
统一目录与回执（顶层强制）
目录、落盘、归档回执规则统一以 ./COMMON_RULES.md 与 ./FLOW_CREATE.md 为准，不在本文件重复定义。
流程衔接
- 提取流程（Extract）的结果可作为新增流程（Create）的快速输入：若用户在完成提取后希望创建知识网络，可将提取清单直接带入新增流程，跳过阶段一的重复提取，从清单确认（A2/B2/C1）开始
- 查找流程（Read）完成后，若用户希望修改或删除结果，可直接发起流程路由切换到更新或删除流程
- 跨流程切换时仍需经过流程路由确认门禁
失败回退
- 输入不足：一次只追问最高优先级字段，不批量追问
- 工具调用失败：停在当前阶段，向用户报错并等待指令，Never 自动重试或跳过
- 结果不确定：标注低置信度，不得自动推进到下一阶段
示例
正例：新增流程
用户："根据这份 PRD 创建知识网络"
执行：流程路由识别为新增 -> 路由 FLOW_CREATE -> 按门禁逐阶段推进。
What ships with it
13 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.
- COMMON_RULES.md 12 KB
- FLOW_CREATE.md 27 KB
- FLOW_DELETE.md 3.1 KB
- FLOW_EXTRACT_TYPES.md 6.5 KB
- FLOW_READ.md 3.4 KB
- FLOW_UPDATE.md 3.3 KB
- references/bkn_report_template.html 9.1 KB
- references/common/generic_extraction.md 3.5 KB
- references/crm_sales/domain_crm_sales.md 2.6 KB
- references/DOMAIN_ROUTING.md 5.1 KB
- references/project_delivery/domain_project_delivery.md 2.6 KB
- references/supply_chain/domain_supply_chain.md 3.2 KB
- references/trigger-test-set.jsonl 1.9 KB
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.
- 6d ago First seen · 111 lines · 221 tokens per session scan A dfecea2a5bb2
bkn-creator is a skill published in the GitHub repository UnicomAI/wanwu (2,461 stars, last pushed 5d ago), licensed Apache-2.0. It adds 221 tokens to every session and 1,463 once invoked, about $0.0011 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
dify
Use when building LLM applications with visual workflow — RAG knowledge bases, AI agents, chatbots with drag-and-drop orchestration. Dify: open-source LLM app platform supporting 30+ models (OpenAI, Claude, DeepSeek, Ollama, Qwen, GLM) with Docker deployment.
ai-skills
Use when building LLM applications, RAG knowledge bases, AI agents, terminal coding agents, multi-model orchestration, plugin-based agent harnesses, or file translation. Index of 10 skills: Dify, Hermes Agent, OpenClaw, OpenCode, Pi, DocuTranslate, Oh-My-OpenAgent, Superpowers-zh, DeepSeek Harness, My OpenCode…
Web2Skill
Convert one public website URL or an explicit batch of public URLs into a reusable skill zip backed by rendered HTML snapshots and a bounded JSONL retrieval index. Use to discover a documentation directory from one URL, crawl a supplied URL set sequentially, generate a source profile, or package indexed web content as…
Book2Skill
Convert one or more TXT, Markdown, DOCX, or PDF documents into a reusable skill zip backed by normalized Markdown, extracted images, and a grounded JSONL knowledge index. Invoke this skill before inspecting task files, then execute its workflow directly without listing directories.
agent-orchestration-multi-agent-optimize
Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.
ai-agents-architect
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.