MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
AnyShare 企业云盘技能。支持：搜索文件、上传/下载文件、分享链接读取、全文写作（生成大纲→确认→写正文）、Bot 智能问答。触发词：AnyShare、asmcp、文档库、文件管理、知识库、anyshare.aishu.cn 分享链接。
MITAuto-check passed
Install Anyshare MCP Skills
$ npx skills add LeoYeAI/openclaw-master-skills --skill anyshare-mcp-skills -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills anyshare-mcp-skills --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/anyshare-mcp-skills .claude/skills/anyshare-mcp-skills && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "anyshare-mcp-skills" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/anyshare-mcp-skills into .claude/skills/anyshare-mcp-skills/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "anyshare-mcp-skills", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/anyshare-mcp-skillsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill anyshare-mcp-skills -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills anyshare-mcp-skills --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/anyshare-mcp-skills .agents/skills/anyshare-mcp-skills && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "anyshare-mcp-skills" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/anyshare-mcp-skills into .agents/skills/anyshare-mcp-skills/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "anyshare-mcp-skills", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill anyshare-mcp-skills -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills anyshare-mcp-skills --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/anyshare-mcp-skills .cursor/skills/anyshare-mcp-skills && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "anyshare-mcp-skills" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/anyshare-mcp-skills into .cursor/skills/anyshare-mcp-skills/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "anyshare-mcp-skills", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/anyshare-mcp-skills--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill anyshare-mcp-skills -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills anyshare-mcp-skills --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/anyshare-mcp-skills .gemini/skills/anyshare-mcp-skills && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "anyshare-mcp-skills" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/anyshare-mcp-skills into .gemini/skills/anyshare-mcp-skills/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "anyshare-mcp-skills", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills anyshare-mcp-skillsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill anyshare-mcp-skills -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/anyshare-mcp-skills .github/skills/anyshare-mcp-skills && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "anyshare-mcp-skills" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/anyshare-mcp-skills into .github/skills/anyshare-mcp-skills/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "anyshare-mcp-skills", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill anyshare-mcp-skills -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills anyshare-mcp-skills --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/anyshare-mcp-skills .opencode/skills/anyshare-mcp-skills && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "anyshare-mcp-skills" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/anyshare-mcp-skills into .opencode/skills/anyshare-mcp-skills/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "anyshare-mcp-skills", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
anyshare-mcp-skills- GitHub stars
- 2.2k
- Token cost
- ~2.6k tokens
- SKILL.md length
- 632 words
- Files
- 10 (incl. references)
- Skills in repo
- 1,235
- Repo updated
- First seen
- Licence
- MIT
At a glance
AnyShare 企业云盘技能。支持：搜索文件、上传/下载文件、分享链接读取、全文写作（生成大纲→确认→写正文）、Bot 智能问答。触发词：AnyShare、asmcp、文档库、文件管理、知识库、anyshare.aishu.cn 分享链接。
- Works in 3 steps: 搜索结果中找 size = -1 且 basename 一致的项 → 对该 docid 先调 file_convert_path 展示目录… → 再调 folder_sub_objects 列出子文件
- SKILL.md covers ⚠️ 执行前必读, 🔄 完整执行流程, 📌 核心概念速查 and 🏛️ AnyShare…, plus 7 more sections
- Reaches anyshare.aishu.cn
What it does
Anyshare MCP Skills is an agent skill from LeoYeAI/openclaw-master-skills. AnyShare 企业云盘技能。支持：搜索文件、上传/下载文件、分享链接读取、全文写作（生成大纲→确认→写正文）、Bot 智能问答。触发词：AnyShare、asmcp、文档库、文件管理、知识库、anyshare.aishu.cn 分享链接。
Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including reference files (for example `SECURITY.md`, `_meta.json` and `mcp.json`).
It works with Model Context Protocol. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
Example prompts
- “/anyshare-mcp-skills”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- 搜索结果中找 size = -1 且 basename 一致的项
- 对该 docid 先调 file_convert_path 展示目录 namepath（C2）
- 再调 folder_sub_objects 列出子文件
What it can do on your machine
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are json and bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
anyshare.aishu.cn
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Anyshare MCP Skills loads about 2.6k tokens when it runs, and up to ~6.6k if it reads all its reference files. Until then it costs about 35 tokens; SKILL.md has 632 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 632 words, ~2,593 tokens.
Download SKILL.mdSave it as
.claude/skills/anyshare-mcp-skills/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.- name
- anyshare-mcp-skills
- description
- AnyShare 企业云盘技能。支持：搜索文件、上传/下载文件、分享链接读取、全文写作（生成大纲→确认→写正文）、Bot 智能问答。触发词：AnyShare、asmcp、文档库、文件管理、知识库、anyshare.aishu.cn 分享链接。
- homepage
- https://anyshare.aishu.cn
- metadata
- {"openclaw":{"category":"productivity","emoji":"📁","requires":{"bins":["agent-browser","mcporter"]},"openclawSkillsEntryFile":"openclaw.skill-entry.json"}}
AnyShare MCP 技能
首次使用本技能时，配置步骤的权威来源是 setup.md。 SKILL.md 只做摘要+跳转，配置细节以 setup.md 为准（避免两处表述漂移）。
⚠️ 执行前必读
强制前置阅读（按需必读，否则跳过）
| 操作 | 必须先读 | 为何 |
|---|---|---|
| 首次使用本技能（配置 asmcp.url） | setup.md 全章 | 配置步骤唯一权威来源；包含 mcporter.json 写入、daemon 重启、openclaw.json 合并、企业地址确认话术 |
| 执行任何认证 / auth_login 前 | references/auth.md 第 1~5 步 | 认证流程步骤编号、Cookie 提取方式、状态文件路径均以此为准 |
| 调用任何业务工具（file_search / upload / download 等）前 | references/tool-params.md 对应工具节 | 参数格式（key=value）、固定字段、禁止传参、不传参；与此处示例保持一致 |
| 进入场景四（全文写作）前 | 本 SKILL.md → 场景四 → C8 进门卡点 | 必须持 docid；未持则先走 file_search 或场景五 获取，禁止绕过（C8 违规） |
| 排障 / 401 / 认证失败 | references/troubleshooting.md | 错误码含义、常见现象与处理方式均在此 |
硬卡点表
| # | 规则 | 关联场景 |
|---|---|---|
| C1 | 搜索文件只用 file_search，禁止 RAG 类工具或目录树展开 | 场景一 |
| C2 | 展示搜索/列目录结果前，必须先调 file_convert_path 再输出（禁止跳过） | 场景一、场景五 |
| C3 | 上传/下载前，必须用户明确回复"是"确认 docid，禁止代选 | 场景二、场景三 |
| C4 | 大纲未确认前禁止调用 __大纲写作__1（大纲门闩） | 场景四 |
| C5 | source_ranges[].id 必须传 id（docid 最后一段），禁止传完整 docid | 场景四 |
| C6 | 禁止用 screenshot 解析分享链接的 item_id，以 agent-browser get url 为准 | 场景五 |
| C7 | item_id 禁止臆造，须从实际访问后的 URL 中解析 | 场景五 |
| C8 | 进入 chat_send（全文写作）前必须持有 docid。若尚无 docid，须先通过场景一（关键词搜索）或场景五（解析分享链接）获取，禁止自行判断"docid 不可用"而绕过本文档处理流程另起炉灶。 | 场景四 |
| C9 | 在场原则（System-Internal-Only）：持有 docid 后，所有后续操作（阅读、摘要、写作、导出）必须通过 AnyShare 工具完成，禁止下载到本地后跳出系统处理。C8 管"进入"，C9 管"离开"。 | 所有含 docid 的场景 |
🔄 完整执行流程
用户输入
│
▼
① 首次使用？── 是 ──→ 阅读 setup.md，执行 Step 1~4
│ → 向用户汇报 asmcp.url + 连通性
│ → 确认是否为**本企业**正式端点
否
▼
② 认证检查（自动）── 失败 ──→ 认证恢复（references/auth.md 第 1~6 步）──→ 重试验证
│ │
│ 通过 ◀────────────────────────────────────┘
▼
③ 意图识别
│
├─ 分享链接？── 是 ──→ 场景五（读取链接 → 获取 docid）
│
├─ 书写类诉求？（生成/撰写/改写/续写/润色/文章/报告/文案/大纲/材料）── 是 ──→ 确认全文写作？
│ │
│ 是 ◀─────────────────┘
│ ▼
│ ⚠️ C8 强制预检：
│ "是否已持有本次写作所需的 docid？"
│ 否 ──→ 场景一（关键词搜索）获取 docid
│ │ 或场景五（解析分享链接）获取 docid
│ │ 获取后返回此节点重新判断
│ 是
│ ▼
│ 场景四：全文写作
│ ① docid/id → ② 大纲 → ③ 确认 → ④ 正文
│
│ 否 ──→ chat_send 简化问答
│
├─ 搜索 / 查看文件 ──→ 场景一
│
├─ 上传文件 ──→ 场景二
│
└─ 下载文件 ──→ 场景三📌 核心概念速查
| 术语 | 说明 | 传参规则 |
|---|---|---|
| docid | 完整路径，gns:// 开头，是文档在 AnyShare 系统内的唯一标识 | 传给 folder_sub_objects、file_upload、file_osdownload、file_convert_path（均须完整 gns://…） |
| id | docid 的最后一段 | 传给 chat_send 的 source_ranges[].id（不传完整 docid，见 C5） |
| namepath | 云盘展示用路径，由 file_convert_path 返回 | 仅供阅读，不作 docid 传参 |
| sharedlink | https://anyshare.aishu.cn/link/AR... | 用 agent-browser get url 解析 item_id |
🏛️ AnyShare 在场原则（System-Internal-Only Principle）
这是本技能最根本的运行假设，所有场景均以此为前提。
原则内容
一旦通过 AnyShare 系统获取到 docid，该文档的所有后续操作都必须通过 AnyShare 工具完成，禁止跳出系统处理。
换言之：
- ✅ 持有 docid → 用
chat_send（全文写作 / 摘要 / 问答） - ✅ 持有 docid → 用
file_convert_path（查看路径） - ✅ 持有 docid → 用
file_osdownload（下载，但下载后仍须回到 AnyShare 工具链处理） - ❌ 持有 docid，却去下载文件到本地后用外部工具（markitdown、LLM 直接总结等）"替代" AnyShare 工具链 → 在场原则违规
为什么这条原则重要
docid 是文档在 AnyShare 系统内的"在场证明"。AI 一旦持有 docid，意味着文档已经在 AnyShare 的管理范围内。跳出系统去处理，等于放弃了 AnyShare 已有的权限管控、操作审计、内容安全策略，是系统性风险。
典型失控模式（供自检）
| 失控模式 | 为什么会发生 | 正确做法 |
|---|---|---|
| "已有 docid，但还是下载了 PPTX 用 markitdown 提取内容" | AI 认为"外部工具效果更好" | 用 chat_send + source_ranges 替代 |
| "已有 docid，但决定直接帮用户总结内容" | AI 认为"用 LLM 总结更快" | 用 chat_send 简化问答替代 |
| "已有 docid，但去查本地文件" | AI 遗忘了 docid 的存在 | 回到 docid，用 AnyShare 工具继续 |
在场原则与 C8 的关系
C8 约束的是"进入 chat_send 前必须持有 docid"，在场原则约束的是"持有 docid 后不得离开 AnyShare 系统"。两者共同构成了完整的边界控制：C8 管入口，在场原则管出口。
📂 场景一：文件/关键词搜索
前置阅读：tool-params.md →
file_search节（参数格式+固定字段说明）
步骤
第 1 步：file_search
{
"name": "file_search",
"arguments": {
"keyword": "<用户关键词>",
"type": "doc",
"start": 0,
"rows": 25,
"range": [],
"dimension": ["basename"],
"model": "phrase"
}
}⚠️
dimension: ["basename"]+model: "phrase"必须固定，不随关键词变化。省略会导致正文/多字段命中，而非按名匹配。
第 2 步：展示结果（必须含三要素）
对每条结果：先调 file_convert_path → 再展示：
- 名称：
basename - 大小：
size = -1→ 目录；size ≥ 0→ 实际字节数 - 云盘路径：
namepath（来自file_convert_path返回）
⚠️ C1 + C2：禁止跳过
file_convert_path；禁止用 docid/序号代替 namepath 展示。
第 3 步：用户确认 docid（如需操作）
分页提示（hits ≥ 25 时强制显示）：
找到 X 条（已展示前 25 条），是否：
- 查看更多（翻页） 2. 更换关键词 3. 缩小范围（加 range）
按文件夹名查看子文件：
- 搜索结果中找
size = -1且 basename 一致的项 - 对该 docid 先调
file_convert_path展示目录 namepath（C2） - 再调
folder_sub_objects列出子文件
📂 场景二：上传文件
步骤
第 1 步：搜索目标目录（file_search + file_convert_path，必须 C3）
展示确认模板：
即将上传到：
- 文件名：
<本地文件名>- 云盘路径：
file_convert_path返回的namepath- docid：
gns://...确认继续？回复"是"，或提供其他目标路径。
第 2 步：用户回复"是"后锁定 docid（C3）
第 3 步：file_upload
{
"name": "file_upload",
"arguments": {
"docid": "<用户确认的 docid（完整）>",
"file_path": "<本地真实路径>"
}
}第 4 步：汇报
- docid 必须展示为
gns://开头完整路径（禁止只展示 id/十六进制串） - 对新文件 docid 调
file_convert_path，一并展示namepath
📂 场景三：下载文件
步骤
第 1 步：搜索目标文件（file_search + file_convert_path，必须 C3）
展示确认模板：
即将下载：
- 文件名：
<basename>- 大小：
<size> 字节- 云盘路径：
file_convert_path返回的namepath- docid：
gns://...确认继续？回复"是"，或选择其他文件。
第 2 步：用户回复"是"后锁定 docid（C3）
第 3 步：file_osdownload
{
"name": "file_osdownload",
"arguments": {
"docid": "<用户确认的 docid（完整）>"
}
}Show full SKILL.md (251 more words)Show less
📂 场景四：全文写作
前置阅读：tool-params.md →
chat_send节（参数格式、source_ranges传参规则）
入口：用户已确认走全文写作流程。
⚠️ C8 进门卡点（C-gate 0）：进入前必须持有 docid
这是本场景的第一道门。任何时候未持有 docid，都必须先出去获取，不得绕过。
进门前自问：
"我是否已为本次写作任务持有至少一个可用的 docid？"
- 是 → 进入步骤 1
- 否（docid 尚未获取） → 必须先执行以下之一：
- 路径 A：
file_search（关键词搜索）→ 获取 docid → 返回本场景 - 路径 B：场景五（解析分享链接）→ 获取 docid → 返回本场景
- 路径 C：若用户直接提供了文件 docid → 直接进入步骤 1
- 禁止：自行判断"docid 拿不到"而改用本地写作、摘要总结等绕过手段（违者属 C8 违规）
- 路径 A：
C8 违规示例（摘录本次失控案例，供自检）：
- "这些是本地 PPTX 文件，不是知识库文档，source_ranges 用不了，所以我直接自己写"→ C8 违规，正确做法是先把文件上传 AnyShare 或找到云端对应 docid 再调用 chat_send
- "这个文档没法获取 docid，直接帮用户总结好了" → C8 违规
⚠️ 大纲门闩（C4）
禁止跳过"生成大纲 → 用户确认"直接生成正文。
步骤
第 1 步：确认文档 id（已在 C8 获取）
- 分享链接 → 场景五解析出 id
- 关键词 →
file_search确认文档 id
第 2 步：生成大纲（__全文写作__2）
{
"name": "chat_send",
"arguments": {
"query": "<用户写作任务描述>",
"selection": "",
"times": 1,
"skill_name": "__全文写作__2",
"web_search_mode": "off",
"datasource": [],
"source_ranges": [{ "id": "<文档的 id>", "type": "doc" }],
"template_id": 1,
"interrupted_parent_qa_id": ""
}
}→ 展示大纲 → 等待用户确认（C4）
第 3 步：生成正文（__大纲写作__1）
仅在大纲确认后调用（用第 2 步返回的 conversation_id）：
{
"name": "chat_send",
"arguments": {
"query": "基于大纲生成文档",
"selection": "<已确认的大纲全文>",
"conversation_id": "<步骤2返回的 conversation_id>",
"times": 1,
"skill_name": "__大纲写作__1",
"web_search_mode": "off",
"datasource": [],
"source_ranges": [{ "id": "<文档的 id>", "type": "doc" }],
"interrupted_parent_qa_id": ""
}
}第 4 步：导出（保存本地 / 上传至 AnyShare 复用场景二）
⚠️ C5：
source_ranges[].id传 id（docid 最后一段），不传完整 docid。
📂 场景五：分享链接读取
前置阅读：auth.md → 登录填表步骤（账号密码索取+snapshot -i 用法）
触发：用户提供 https://anyshare.aishu.cn/link/AR...
⚠️ C6 + C7：item_id 只能从
agent-browser get url解析，禁止 screenshot，禁止臆造。
步骤
第 1 步：无头浏览器跟随重定向
agent-browser open "https://anyshare.aishu.cn/link/<分享ID>"
agent-browser wait --load networkidle
agent-browser get url ← 获取含 item_id 的落地 URL第 1.5 步：遇登录页 → 填入账号密码
- 向用户当面索取账号 + 密码（禁止从文件读取）
agent-browser snapshot -i获取无障碍树 refsfill账号/密码 →click登录 →wait --load networkidle- 再次
get url获取登录后落地 URL
第 2 步：解析 URL 中的 item_id
- 从 URL 提取
item_id（已 URL 编码） - 解码 → 完整 docid
- 取最后一段 → id
- 根据
item_type分流：folder→ 第 3 步Afile/ 其他 → 第 3 步B
第 3 步A：文件夹
file_convert_path→ 展示目录namepath（C2）folder_sub_objects→ 列出子文件
第 3 步B：文件
- 走场景四（全文写作）：id 传给场景四第 1 步
- 或简化问答：
chat_send+source_ranges
🎯 意图模糊时的确认模板
当用户意图不清晰、无法判断是否在 AnyShare 操作或做哪类操作时，使用以下模板（仅一次，不叠套）：
请确认：
1. 目标系统：是否在 AnyShare 操作？
1) 是
2) 其他系统
2. 具体操作：
1) 搜索 / 查看文件
2) 上传或下载文件
3) 智能问答 / 全文写作
4) 其他（文档库浏览、换账号等）
回复示例：「1 2」表示在 AnyShare 上传或下载。回复 → 执行路径：
| 回复 | 场景 |
|---|---|
1 + 1 | 场景一 |
1 + 2（上传） | 场景二 |
1 + 2（下载） | 场景三 |
1 + 3 | 场景四 |
1 + 4 | 澄清子意图 |
2 | 不走本技能 |
📖 补充资料（权威来源）
| 文件 | 权威内容 | 用于 |
|---|---|---|
| setup.md | asmcp.url 写入步骤、daemon 重启、企业地址确认话术 | 首次配置（唯一权威来源） |
| references/auth.md | 认证 1 | 认证相关操作 |
| references/concepts.md | docid/id/namepath/sharedlink 完整说明 | 概念确认 |
| references/tool-params.md | 各工具参数 schema、固定字段、禁止传参 | 工具调用前 |
| references/troubleshooting.md | 错误码、常见现象与处理 | 排障 |
| SECURITY.md | 安全约束、敏感信息处理 | 安全审计 |
© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 9 other files (references) in skills/anyshare-mcp-skills of LeoYeAI/openclaw-master-skills.
- SKILL.md
- SECURITY.md
- _meta.json
- mcp.json
- openclaw.skill-entry.json
- references/auth.md
- references/concepts.md
- references/tool-params.md
- references/troubleshooting.md
- setup.md
Open the folder on GitHubat commit e5199b5
Compare with similar skills
Anyshare MCP Skills next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Anyshare MCP Skills this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~2.6k | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 4 repos | ~1.2k | Automated safety check: Pass | MIT | |
| MCP Integration for Pluginsanthropics/claude-plugins-official | 38k | 11 repos | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| Figma use_figma Plugin API Ruleswarpdotdev/warp | 65k | 4 repos | ~4.4k | Automated safety check: Pass | AGPL-3.0 | |
| Stitch to Remotion Walkthrough Videosgoogle-labs-code/stitch-skills | 8.5k | 6 repos | ~3.2k | Automated safety check: Notes | Apache-2.0 |
Similar skills
- Official
MCP Server Builder
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
- Official
MCP Integration for Plugins
anthropics/claude-plugins-official
Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.
Figma use_figma Plugin API Rules
warpdotdev/warp
Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.
- Official
Stitch to Remotion Walkthrough Videos
google-labs-code/stitch-skills
Builds walkthrough videos from Stitch design projects using Remotion, with transitions, zoom effects and text overlays on each screen.
MCP Development
coollabsio/coolify
A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.
More from LeoYeAI/openclaw-master-skills
All 1,200 skills in this repoDevOps Pipeline Management
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
Feishu Document Collaboration
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
Files Memory System
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
GEO-Claw AI Visibility Agent
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
Google Workspace CLI
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
HealthFit Health Advisors
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Related
Works with
Questions about Anyshare MCP Skills
What does Anyshare MCP Skills do?
AnyShare 企业云盘技能。支持：搜索文件、上传/下载文件、分享链接读取、全文写作（生成大纲→确认→写正文）、Bot 智能问答。触发词：AnyShare、asmcp、文档库、文件管理、知识库、anyshare.aishu.cn 分享链接。. Anyshare MCP Skills is an agent skill from LeoYeAI/openclaw-master-skills.
How do I install Anyshare MCP Skills in Claude Code?
Run `npx skills add LeoYeAI/openclaw-master-skills --skill anyshare-mcp-skills -a claude-code`. Or copy the skill folder (skills/anyshare-mcp-skills in LeoYeAI/openclaw-master-skills) into .claude/skills/anyshare-mcp-skills in your project. Claude Code loads it when a task matches its description.
How do I install Anyshare MCP Skills in Codex?
Run `npx skills add LeoYeAI/openclaw-master-skills --skill anyshare-mcp-skills -a codex`. Or copy the skill folder (skills/anyshare-mcp-skills in LeoYeAI/openclaw-master-skills) into .agents/skills/anyshare-mcp-skills in your project. Codex loads it when a task matches its description.
Can I use Anyshare MCP Skills in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill anyshare-mcp-skills -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/anyshare-mcp-skills, .gemini/skills/anyshare-mcp-skills, .github/skills/anyshare-mcp-skills and .opencode/skills/anyshare-mcp-skills in your project.
What does Anyshare MCP Skills need to run?
SKILL.md names no scripts, command-line tools or credentials: Anyshare MCP Skills is instructions for the agent only.
Does Anyshare MCP Skills access the network?
SKILL.md names 1 domain. In commands or code: anyshare.aishu.cn; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Anyshare MCP Skills safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Anyshare MCP Skills use?
Anyshare MCP Skills is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Anyshare MCP Skills use?
About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4k tokens, read only when the agent opens those files.
What are the alternatives to Anyshare MCP Skills?
Skills that share tags, products or a category with Anyshare MCP Skills: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Anyshare MCP Skills?
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.