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 knowledge-basegit 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/knowledge-base)<a href="https://agentmods.dev/skills/unicomai/wanwu/knowledge-base"><img src="https://agentmods.dev/badge/skills/unicomai/wanwu/knowledge-base/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/knowledge-base"><img src="https://agentmods.dev/badge/skills/unicomai/wanwu/knowledge-base.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 7 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00000 | $0.04579 |
| Opus 5.5 | $0.00000 | $0.01832 |
| Sonnet 5.5 | $0.00000 | $0.00916 |
| Haiku 4.5 | $0.00000 | $0.00458 |
Grade C, and why
knowledge-base scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$TEMP_DIR" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
CONTENT_TYPE=$(curl -sI -L "<url>" | grep -i "^content-type:" | tail -1 | awk '{print $2}' | tr -d '\r') Copies of this mod
2 near-identical copies found in the catalogue:
- knowledge-base — 100% identical, 2 lines differ
- knowledge-base — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Base (知识库)
API base path: openapi/wiki/v1 — 完整数据结构和接口参数详见 references/api.md。
接口决策表
| 用户意图 | 调用接口 | 关键参数 |
|---|---|---|
| 上传文件到知识库 | check_repeated_names → create_media → COS Upload → add_knowledge |
media_type（按扩展名），knowledge_base_id，file_name，file_size |
| 上传文件到知识库的某个文件夹 | 先定位文件夹 → 同上（folder_id 传入目标文件夹 ID） |
见「文件夹操作」章节 |
| 添加网页/微信文章到知识库 | import_urls |
urls（1-10 个），knowledge_base_id，可选 folder_id（省略则根目录） |
| 添加笔记到知识库 | add_knowledge |
media_type=11，note_info.content_id=<note_id>，knowledge_base_id |
| 添加 URL（文件型）到知识库 | check_repeated_names → 下载文件 → 走"上传文件"流程 |
URL 指向 PDF/Word/PPT 等文件时，按文件方式处理 |
| 检查文件名是否重复 | check_repeated_names |
params[].name，params[].media_type，knowledge_base_id，folder_id |
| 获取知识库信息 | get_knowledge_base |
ids（1-20 个，不重复） |
| 浏览知识库内容列表 / 浏览文件夹 | get_knowledge_list |
knowledge_base_id，cursor，limit(1~50)，可选 folder_id |
| 在知识库中搜索（含文件和文件夹） | search_knowledge |
query，knowledge_base_id，cursor |
| 按关键词查找知识库（用户知道名字但不知道 ID） | search_knowledge_base |
query，cursor，limit(1~20) |
| 查看/了解自己有哪些知识库 | search_knowledge_base（query 传空字符串） |
query: ""，cursor，limit(1~20) |
| 添加内容但未指定目标知识库 | get_addable_knowledge_base_list → 展示列表让用户选择 |
cursor，limit(1~50) |
| 查看原文、分析原文、导出原文 | get_media_info |
media_id；导出/下载时在 URL 后追加 response-content-type + response-content-disposition 参数 |
What ships with it
3 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.
- 1mo ago First seen · 384 lines · 0 tokens per session scan C 39ee19712d79
knowledge-base is a skill published in the GitHub repository UnicomAI/wanwu (2,372 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,579 tokens. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
design-drawing-svg-md
Use when converting vector PDF engineering drawings (steel-structure shop drawings, A0 drawings, linework-only PDFs without a text layer) into LLM-consumable dual-carrier records — semantic Markdown reading thread plus layered SVG geometry archive linked by shared IDs and crosswalk.
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.
ai-engineer
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.
PDF files: create, read, merge, fill, OCR, edit text.
markitdown
Converts heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.
pdf-toolkit
Structured .pdf operations: extract text/tables, merge pages from multiple PDFs, split a PDF by page ranges, fill PDF form fields, and generate fresh PDFs from JSON. Trigger when the user wants programmatic PDF work without natural-language rewriting — examples: pull tables from a report, combine three PDFs, extract…