ima-skill

Name: ima-skill
Author: nexus-research-lab

78stars7forks

How to install ima-skill?

nexus-research-lab/nexus/ima-skill

$npx -y skills add nexus-research-lab/nexus --skill ima-skill

Installs into the current project.

Summary

统一的 IMA OpenAPI 技能，支持笔记管理和知识库操作。当用户提到知识库、资料库、笔记、备忘录、记事，或者想要上传文件、添加网页到知识库、搜索知识库内容、搜索/浏览/创建/编辑笔记时，使用此 skill。即使用户没有明确说"知识库"或"笔记"，只要意图涉及文件上传到知识库、网页收藏、知识搜索、个人文档存取（如"帮我记一下"、"搜一下知识库里有没有XX"），也应触发此 skill。

Files · 1

View on GitHub

SKILL.md

1	# ima-skill
2
3	Unified IMA OpenAPI skill. Currently supports: notes, knowledge-base.
4
5	## ⛔ MANDATORY RULES — read before ANY operation
6
7	1. UTF-8 encoding (notes writes only): Before calling `import_doc` or `append_doc`, ALL string fields (`content`, `title`) MUST be validated as legal UTF-8. Non-UTF-8 content causes irreversible garbled text. See [Detailed Rules](#detailed-utf-8-encoding-rules) for platform-specific methods.
8	2. File upload naming: `title` MUST equal `file_name` (with extension). Never rename, shorten, translate, or modify the original filename.
9	3. Unsupported file types: Reject immediately with a clear message. Do NOT ask user "do you still want to try?" Video files, Bilibili/YouTube URLs, and `file://` URLs are not supported — tell user to use IMA desktop client.
10	4. File upload integrity: Keep file content as-is during upload. No encoding conversion for binary files (PDF, images, Excel, etc.).
11	5. PowerShell 5.1 (all modules): If running in PowerShell, detect version before first API call. PS 5.1 silently converts request Body to GBK — must use UTF-8 byte array mode. See [Detailed Rules](#powershell-51-environment-detection).
12
13	## 模块决策表
14
15	\| 用户意图 \| 模块 \| 读取 \|
16	\| ------------------------------------------------------------------------------------------ \| -------------- \| ------------------------- \|
17	\| 搜索笔记、浏览笔记本、获取笔记内容、创建笔记、追加内容 \| notes \| `notes/SKILL.md` \|
18	\| 上传文件、添加网页链接、搜索知识库、浏览知识库内容、获取知识库信息、获取可添加的知识库列表 \| knowledge-base \| `knowledge-base/SKILL.md` \|
19	\| 查看原文、分析原文、导出原文（需要 media_id） \| knowledge-base \| `knowledge-base/SKILL.md` \|
20
21	### ⚠️ 易混淆场景
22
23	\| 用户说的 \| 实际意图 \| 正确路由 \|
24	\| -------------------------------------------------------- \| ------------------------ \| ----------------------------------------------------------- \|
25	\| "把这段内容添加到知识库XX里的笔记YY" \| 往已有笔记追加内容 \| notes — 先搜索笔记获取 `note_id`，再用 `append_doc` \|
26	\| "把这个写到XX笔记里"、"记到XX笔记" \| 往已有笔记追加内容 \| notes — `append_doc` \|
27	\| "把这篇笔记添加到知识库" \| 将笔记关联到知识库 \| knowledge-base — `add_knowledge` with `media_type=11` \|
28	\| "上传文件到知识库" \| 上传文件到知识库 \| knowledge-base — `create_media` → COS → `add_knowledge` \|
29	\| "新建一篇笔记记录这些内容" \| 创建新笔记 \| notes — `import_doc` \|
30	\| "帮我记一下"、"记录一下"、"保存为笔记"（未指定已有笔记） \| 意图不明确，需要确认 \| notes — 先询问用户是创建新笔记还是追加到哪篇已有笔记 \|
31	\| "添加到笔记里"（未指定具体哪篇） \| 意图不明确，需要确认 \| notes — 先询问用户是创建新笔记还是追加到哪篇已有笔记 \|
32
33	### ⚠️ 跨模块任务 — 必须读取两个子模块
34
35	某些意图跨越 notes 和 knowledge-base 两个模块。不要只读取一个子模块就开始执行，必须先读取两个模块的 SKILL.md 再按顺序操作。
36
37	\| 用户说的 \| 实际流程 \| 读取顺序 \|
38	\| ------------------------------------ \| --------------------------------------------- \| ------------------------------------------------------ \|
39	\| "把知识库里的XX内容记到笔记" \| KB 搜索/读取 → Notes 创建/追加 \| 先读 `knowledge-base/SKILL.md` → 再读 `notes/SKILL.md` \|
40	\| "查看原文"（知识库中的笔记类型媒体） \| KB `get_media_info` → Notes `get_doc_content` \| 先读 `knowledge-base/SKILL.md` → 再读 `notes/SKILL.md` \|
41	\| "把这篇笔记添加到知识库" \| Notes 搜索获取 note_id → KB `add_knowledge` \| 先读 `notes/SKILL.md` → 再读 `knowledge-base/SKILL.md` \|
42
43	规则：如果用户意图同时涉及「笔记」和「知识库」，或者 API 响应揭示需要另一个模块（如 `media_type=11` 表示笔记类型），必须读取两个子模块再继续。
44
45	核心判断规则：
46
47	- 目标是笔记的内容（读、写、追加）→ notes 模块
48	- 目标是

People who liked this also viewed

6 picks

Type

ima-skill

78stars7forks

View on GitHub

How to install ima-skill?

nexus-research-lab/nexus/ima-skill

$npx -y skills add nexus-research-lab/nexus --skill ima-skill

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# ima-skill
2
3	Unified IMA OpenAPI skill. Currently supports: notes, knowledge-base.
4
5	## ⛔ MANDATORY RULES — read before ANY operation
6
7	1. UTF-8 encoding (notes writes only): Before calling `import_doc` or `append_doc`, ALL string fields (`content`, `title`) MUST be validated as legal UTF-8. Non-UTF-8 content causes irreversible garbled text. See [Detailed Rules](#detailed-utf-8-encoding-rules) for platform-specific methods.
8	2. File upload naming: `title` MUST equal `file_name` (with extension). Never rename, shorten, translate, or modify the original filename.
9	3. Unsupported file types: Reject immediately with a clear message. Do NOT ask user "do you still want to try?" Video files, Bilibili/YouTube URLs, and `file://` URLs are not supported — tell user to use IMA desktop client.
10	4. File upload integrity: Keep file content as-is during upload. No encoding conversion for binary files (PDF, images, Excel, etc.).
11	5. PowerShell 5.1 (all modules): If running in PowerShell, detect version before first API call. PS 5.1 silently converts request Body to GBK — must use UTF-8 byte array mode. See [Detailed Rules](#powershell-51-environment-detection).
12
13	## 模块决策表
14
15	\| 用户意图 \| 模块 \| 读取 \|
16	\| ------------------------------------------------------------------------------------------ \| -------------- \| ------------------------- \|
17	\| 搜索笔记、浏览笔记本、获取笔记内容、创建笔记、追加内容 \| notes \| `notes/SKILL.md` \|
18	\| 上传文件、添加网页链接、搜索知识库、浏览知识库内容、获取知识库信息、获取可添加的知识库列表 \| knowledge-base \| `knowledge-base/SKILL.md` \|
19	\| 查看原文、分析原文、导出原文（需要 media_id） \| knowledge-base \| `knowledge-base/SKILL.md` \|
20
21	### ⚠️ 易混淆场景
22
23	\| 用户说的 \| 实际意图 \| 正确路由 \|
24	\| -------------------------------------------------------- \| ------------------------ \| ----------------------------------------------------------- \|
25	\| "把这段内容添加到知识库XX里的笔记YY" \| 往已有笔记追加内容 \| notes — 先搜索笔记获取 `note_id`，再用 `append_doc` \|
26	\| "把这个写到XX笔记里"、"记到XX笔记" \| 往已有笔记追加内容 \| notes — `append_doc` \|
27	\| "把这篇笔记添加到知识库" \| 将笔记关联到知识库 \| knowledge-base — `add_knowledge` with `media_type=11` \|
28	\| "上传文件到知识库" \| 上传文件到知识库 \| knowledge-base — `create_media` → COS → `add_knowledge` \|
29	\| "新建一篇笔记记录这些内容" \| 创建新笔记 \| notes — `import_doc` \|
30	\| "帮我记一下"、"记录一下"、"保存为笔记"（未指定已有笔记） \| 意图不明确，需要确认 \| notes — 先询问用户是创建新笔记还是追加到哪篇已有笔记 \|
31	\| "添加到笔记里"（未指定具体哪篇） \| 意图不明确，需要确认 \| notes — 先询问用户是创建新笔记还是追加到哪篇已有笔记 \|
32
33	### ⚠️ 跨模块任务 — 必须读取两个子模块
34
35	某些意图跨越 notes 和 knowledge-base 两个模块。不要只读取一个子模块就开始执行，必须先读取两个模块的 SKILL.md 再按顺序操作。
36
37	\| 用户说的 \| 实际流程 \| 读取顺序 \|
38	\| ------------------------------------ \| --------------------------------------------- \| ------------------------------------------------------ \|
39	\| "把知识库里的XX内容记到笔记" \| KB 搜索/读取 → Notes 创建/追加 \| 先读 `knowledge-base/SKILL.md` → 再读 `notes/SKILL.md` \|
40	\| "查看原文"（知识库中的笔记类型媒体） \| KB `get_media_info` → Notes `get_doc_content` \| 先读 `knowledge-base/SKILL.md` → 再读 `notes/SKILL.md` \|
41	\| "把这篇笔记添加到知识库" \| Notes 搜索获取 note_id → KB `add_knowledge` \| 先读 `notes/SKILL.md` → 再读 `knowledge-base/SKILL.md` \|
42
43	规则：如果用户意图同时涉及「笔记」和「知识库」，或者 API 响应揭示需要另一个模块（如 `media_type=11` 表示笔记类型），必须读取两个子模块再继续。
44
45	核心判断规则：
46
47	- 目标是笔记的内容（读、写、追加）→ notes 模块
48	- 目标是

People who liked this also viewed

6 picks

Type