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.
文档与智能表格操作。当用户提到企业微信文档、创建文档、编辑文档、新建文档、写文档、智能表格时激活。支持文档创建/写入和智能表格的创建及子表/字段/记录写入。注意：所有文档创建和编辑请求都应使用此 skill，不要尝试用其他方式处理文档操作。
Install Wecom Doc
$ npx skills add LeoYeAI/openclaw-master-skills --skill wecom-doc -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills wecom-doc --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/wecom-doc .claude/skills/wecom-doc && 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 "wecom-doc" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/wecom-doc into .claude/skills/wecom-doc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wecom-doc", 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/wecom-docType 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 wecom-doc -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills wecom-doc --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/wecom-doc .agents/skills/wecom-doc && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "wecom-doc" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/wecom-doc into .agents/skills/wecom-doc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wecom-doc", 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 wecom-doc -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills wecom-doc --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/wecom-doc .cursor/skills/wecom-doc && 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 "wecom-doc" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/wecom-doc into .cursor/skills/wecom-doc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wecom-doc", 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/wecom-doc--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 wecom-doc -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills wecom-doc --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/wecom-doc .gemini/skills/wecom-doc && 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 "wecom-doc" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/wecom-doc into .gemini/skills/wecom-doc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wecom-doc", 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 wecom-docInstalls 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 wecom-doc -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/wecom-doc .github/skills/wecom-doc && 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 "wecom-doc" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/wecom-doc into .github/skills/wecom-doc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wecom-doc", 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 wecom-doc -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 wecom-doc --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/wecom-doc .opencode/skills/wecom-doc && 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 "wecom-doc" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/wecom-doc into .opencode/skills/wecom-doc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wecom-doc", 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
wecom-doc- GitHub stars
- 2.2k
- Token cost
- ~2.6k tokens
- SKILL.md length
- 714 words
- Files
- 3 (incl. references)
- Skills in repo
- 1,235
- Repo updated
- First seen
- Licence
- MIT
At a glance
文档与智能表格操作。当用户提到企业微信文档、创建文档、编辑文档、新建文档、写文档、智能表格时激活。支持文档创建/写入和智能表格的创建及子表/字段/记录写入。注意：所有文档创建和编辑请求都应使用此 skill，不要尝试用其他方式处理文档操作。
- Works in 3 steps: 检查 mcporter 是否安装 → 确保 MCP Server 已配置 → 获取 Tool 列表
- Agent Workflows work in your project
- SKILL.md covers 意图处理, 前置检查（每次会话首次操作前必须执行）, docid 管理规则（重要） and 工作流, plus 3 more sections
- Calls npm; reaches doc.weixin.qq.com and baidu.com
What it does
Wecom Doc is an agent skill from LeoYeAI/openclaw-master-skills. 文档与智能表格操作。当用户提到企业微信文档、创建文档、编辑文档、新建文档、写文档、智能表格时激活。支持文档创建/写入和智能表格的创建及子表/字段/记录写入。注意：所有文档创建和编辑请求都应使用此 skill，不要尝试用其他方式处理文档操作。
Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `_meta.json` and `references/doc-api.md`).
It sits in Agent Workflows. 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.
When your agent uses it
- Agent Workflows work in your project
Example prompts
- “/wecom-doc”
Requirements
- Node.js
Workflow steps
3 steps, taken from the step headings in SKILL.md.
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
Shell commands in SKILL.md call:
npm
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:
doc.weixin.qq.combaidu.com
Also links to:
work.weixin.qq.com
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
Wecom Doc loads about 2.6k tokens when it runs, and up to ~4k if it reads all its reference files. Until then it costs about 33 tokens; SKILL.md has 714 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). 714 words, ~2,632 tokens.
Download SKILL.mdSave it as
.claude/skills/wecom-doc/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- wecom-doc
- description
- 文档与智能表格操作。当用户提到企业微信文档、创建文档、编辑文档、新建文档、写文档、智能表格时激活。支持文档创建/写入和智能表格的创建及子表/字段/记录写入。注意：所有文档创建和编辑请求都应使用此 skill，不要尝试用其他方式处理文档操作。
企业微信文档与智能表格工具
通过 mcporter 调用 wecom-doc MCP server 操作企业微信文档和智能表格。
意图处理
当用户说"创建文档"、"新建文档"、"帮我写个文档"等不指定平台的请求时，默认使用企业微信文档，无需询问用户使用什么平台。
前置检查（每次会话首次操作前必须执行）
自动续接原则：前置检查中的任何环节如果需要等待用户确认或操作（安装、配置、授权等），在该操作完成后必须自动继续执行后续步骤，最终完成用户的原始请求。不要在中间环节完成后停下来等用户重复发起请求。
1. 检查 mcporter 是否安装
which mcporter如果 mcporter 不在 PATH 中（命令返回空或 not found），必须原样输出以下提示（不要修改、不要摘要）：
企业微信文档能力依赖 mcporter 工具，当前尚未安装。需要我帮你安装吗？
输出提示后停止执行并等待用户回复。
- 如果用户确认安装（回复"好"、"是"、"装吧"、"yes"、"ok" 等肯定语义），立即执行：
npm install -g mcporter安装完成后不要停下来，直接继续执行后续的「检查 MCP Server 是否配置」步骤，无缝衔接用户原始请求。
- 如果用户拒绝安装，回复：
好的，你也可以手动执行
npm install -g mcporter安装后再找我。
2. 确保 MCP Server 已配置
确认 mcporter 存在后，先检查配置是否已存在，仅在未配置时才尝试自动配置。
验证配置：
mcporter list wecom-doc --output json如果返回正常（包含 tool 列表），说明已配置，跳过自动配置，直接进入步骤 3。
如果返回 server not found、unknown server 或类似错误，执行下方自动配置。
自动配置（仅在未配置时执行）：
读取 wecom 运行时配置文件，该文件由 wecom channel 长连接建立时写入：
cat ~/.openclaw/wecomConfig/config.json检查 JSON 中是否存在 mcpConfig.doc 字段（含 type 和 url），如果存在则执行：
mcporter config add wecom-doc \
--type "<mcpConfig.doc.type的值>" \
--url "<mcpConfig.doc.url的值>"配置完成后再次执行 mcporter list wecom-doc --output json 验证。如果仍然失败，按下方"MCP Server 未配置"章节处理。
⚠️ 配置文件不存在或缺少
mcpConfig.doc字段，说明 wecom channel 长连接尚未建立，应引导用户检查 wecom channel 是否正常运行。自动配置失败不应阻断流程，继续引导用户手动配置。
3. 获取 Tool 列表
mcporter list 成功后，返回的每个 tool 包含 name、description、inputSchema。
不要硬编码 tool name 和参数，据此构造 mcporter call wecom-doc.<tool> --args '{...}' --output json 调用。
docid 管理规则（重要）
仅支持对通过本 skill 创建的文档或智能表格进行编辑。
docid 的获取方式
docid 只能通过 create_doc 的返回结果获取。创建成功后需要保存返回的 docid，后续编辑操作依赖此 ID。
不支持从 URL 解析 docid
从文档 URL（如 https://doc.weixin.qq.com/doc/...）中无法解析到可用的 docid。如果用户提供了文档 URL 并要求编辑，不要尝试从 URL 中提取 docid。
编辑操作的 docid 校验
当用户请求编辑文档或智能表格时，如果当前会话中没有通过 create_doc 获取到的 docid，必须原样输出以下提示（不要修改、不要摘要）：
仅支持对机器人创建的文档进行编辑
docid 类型判断
| doc_id 前缀 | 类型 | doc_type |
|---|---|---|
w3_ | 文档 | 3 |
s3_ | 智能表格 | 10 |
工作流
文档操作流
- 如需新建文档 →
create_doc（doc_type: 3）→ 保存返回的docid - 如需编辑内容 → 先确认当前会话中有通过
create_doc获取的docid，若无则提示"仅支持对机器人创建的文档进行编辑" →edit_doc_content（content_type: 1使用 markdown，全量覆写）
edit_doc_content是全量覆写操作。如需追加内容，应先了解原有内容再拼接。
智能表格操作流
操作层级：文档（docid）→ 子表（sheet_id）→ 字段（field_id）/ 记录（record_id）
- 如需新建智能表 →
create_doc（doc_type: 10）→ 保存返回的docid - 如需编辑已有智能表 → 先确认当前会话中有通过
create_doc获取的docid，若无则提示"仅支持对机器人创建的文档进行编辑" - 查询已有子表 →
smartsheet_get_sheet→ 获取sheet_id - 如需新建子表 →
smartsheet_add_sheet→ 获取新的sheet_id - 查询已有字段 →
smartsheet_get_fields→ 获取field_id、field_title、field_type - 如需添加字段 →
wedoc_smartsheet_add_fields - 如需更新字段 →
wedoc_smartsheet_update_fields（不能改变字段类型） - 添加数据记录 →
smartsheet_add_records（values 的 key 必须使用字段标题 field_title，不能用 field_id）
从零创建智能表完整流程
create_doc(doc_type=10) → docid
└→ smartsheet_add_sheet(docid) → sheet_id
└→ wedoc_smartsheet_add_fields(docid, sheet_id, fields) → field_ids
└→ smartsheet_add_records(docid, sheet_id, records)向已有智能表添加数据流程
smartsheet_get_sheet(docid) → sheet_id
└→ smartsheet_get_fields(docid, sheet_id) → field_ids + field_titles + field_types
└→ smartsheet_add_records(docid, sheet_id, records)重要：添加记录前必须先通过
smartsheet_get_fields获取字段信息，确保values中的 key 和 value 格式正确。
业务知识（MCP Schema 中缺失的上下文）
以下信息是 MCP tool 的 inputSchema 中没有的，Agent 构造参数时必须参考。
FieldType 枚举（16 种）
| 类型 | 说明 | 使用场景建议 |
|---|---|---|
FIELD_TYPE_TEXT | 文本 | 通用文本内容；当用户只提供了成员姓名（而非 user_id）时，也应使用 TEXT 而非 USER |
FIELD_TYPE_NUMBER | 数字 | 数值型数据（金额、数量、评分等） |
FIELD_TYPE_CHECKBOX | 复选框 | 是/否、完成/未完成等布尔状态 |
FIELD_TYPE_DATE_TIME | 日期时间 | 日期、截止时间、创建时间等 |
FIELD_TYPE_IMAGE | 图片 | 需要展示图片的场景 |
FIELD_TYPE_USER | 成员 | 仅在明确知道成员 user_id 时使用；若用户只提供了姓名，应使用 TEXT 代替 |
FIELD_TYPE_URL | 链接 | 网址、外部链接 |
FIELD_TYPE_SELECT | 多选 | 标签、多分类等允许多选的场景 |
FIELD_TYPE_SINGLE_SELECT | 单选 | 状态、优先级、严重程度、分类等有固定选项的字段 |
FIELD_TYPE_PROGRESS | 进度 | 完成进度、完成百分比（值为 0-100 整数） |
FIELD_TYPE_PHONE_NUMBER | 手机号 | 手机号码 |
FIELD_TYPE_EMAIL | 邮箱 | 邮箱地址 |
FIELD_TYPE_LOCATION | 位置 | 地理位置信息 |
FIELD_TYPE_CURRENCY | 货币 | 金额（带货币符号） |
FIELD_TYPE_PERCENTAGE | 百分比 | 百分比数值（值为 0~1） |
FIELD_TYPE_BARCODE | 条码 | 条形码、ISBN 等 |
FieldType ↔ CellValue 对照表
添加记录（smartsheet_add_records）时，values 中每个字段的 key 必须使用字段标题（field_title），不能使用 field_id。value 必须匹配其字段类型：
| 字段类型 | CellValue 格式 | 示例 |
|---|---|---|
TEXT | CellTextValue 数组 | [{"type": "text", "text": "内容"}] |
NUMBER | number | 85 |
CHECKBOX | boolean | true |
DATE_TIME | 日期时间字符串 | "2023-01-01 12:00:00"、"2023-01-01 12:00"、"2023-01-01" |
URL | CellUrlValue 数组（限 1 个） | [{"type": "url", "text": "百度", "link": "https://baidu.com"}] |
USER | CellUserValue 数组 | [{"user_id": "zhangsan"}] |
IMAGE | CellImageValue 数组 | [{"image_url": "https://..."}]（id、title 可选） |
SELECT | Option 数组（多选） | [{"text": "选项A"}, {"text": "选项B"}] |
SINGLE_SELECT | Option 数组（限 1 个） | [{"text": "选项A"}] |
PROGRESS | number（0~100 整数） | 85（表示 85%） |
CURRENCY | number | 99.5 |
PERCENTAGE | number（0~1） | 0.85 |
PHONE_NUMBER | string | "13800138000" |
EMAIL | string | "user@example.com" |
BARCODE | string | "978-3-16-148410-0" |
LOCATION | CellLocationValue 数组（限 1 个） | [{"source_type": 1, "id": "xxx", "latitude": "39.9", "longitude": "116.3", "title": "北京"}] |
Option 格式说明：
SINGLE_SELECT/SELECT的选项支持style字段（1~27 对应不同颜色），如[{"text": "紧急", "style": 1}]。style为可选字段，不传则使用默认颜色。
Show full SKILL.md (289 more words)Show less
易错点
DATE_TIME的值是日期时间字符串，支持"YYYY-MM-DD HH:MM:SS"（精确到秒）、"YYYY-MM-DD HH:MM"（精确到分）、"YYYY-MM-DD"（精确到天），系统自动按东八区转换为时间戳，无需手动计算CellUrlValue的链接字段名是link，不是urlTEXT类型的值必须使用数组格式[{"type": "text", "text": "内容"}]，外层方括号不可省略，不能传单个对象{"type":"text","text":"内容"}SINGLE_SELECT/SELECT类型的值必须使用数组格式[{"text": "选项内容"}]，不能直接传字符串PROGRESS的值范围是 0~100 整数（85 = 85%）；PERCENTAGE的值范围是 0~1（0.85 = 85%），两者不同注意区分wedoc_smartsheet_update_fields不能更改字段类型，只能改标题和属性values的 key 必须使用字段标题（field_title），不能使用 field_id- 不可写入的字段类型：创建时间、最后编辑时间、创建人、最后编辑人
错误处理
MCP 错误响应处理（重要）
当 mcporter call 返回结果中 errcode 不为 0 且 help_message 有值时，将 help_message 中面向用户的内容输出给用户。
输出原则：
- 完整性：不截断、不摘要
- 原样性：不改写、不重新排版
- 用户可读性：只输出面向用户的内容，过滤掉给 Agent 的元指令（如"将以下内容告知用户"等引导语）；直接以 markdown 形式输出，不要包裹在代码块中
错误码 850001：需要用户提供配置
当 errcode 为 850001 时：
- 将
help_message中面向用户的内容原样输出（遵循上方输出原则） - 输出后等待用户回复，后续流程与「MCP Server 未配置」的场景 A / B / C 一致。配置成功后不要停下来，立即回到「前置检查」的步骤 2 重新验证配置，验证通过后继续执行用户的原始请求。
MCP Server 未配置
如果 mcporter call wecom-doc.* 或 mcporter list wecom-doc 返回 server not found、unknown server 或类似错误，说明 wecom-doc MCP server 尚未配置。
此时需要检测运行环境以提供针对性的提示。按以下步骤执行：
步骤一：检测是否在 OpenClaw 运行时中
通过检测 OPENCLAW_SHELL 环境变量判断当前是否运行在 OpenClaw 中。该变量是 OpenClaw 运行时自动注入到子进程中的标记，不会因为机器上安装了 openclaw 就存在——只有 skill 确实在 OpenClaw 中被调用时，exec 执行的命令才会携带此变量。
echo "OPENCLAW_SHELL=${OPENCLAW_SHELL:-}" && command -v openclaw 2>/dev/null && echo "OPENCLAW_CLI=FOUND" || echo "OPENCLAW_CLI=NOT_FOUND"判断规则：
OPENCLAW_SHELL为空（输出OPENCLAW_SHELL=）→ 当前不在 OpenClaw 运行时中，跳到**「通用提示」**。OPENCLAW_SHELL非空（如exec、tui-local等）且OPENCLAW_CLI=FOUND→ 确认在 OpenClaw 中且 CLI 可用，继续步骤二。OPENCLAW_SHELL非空但OPENCLAW_CLI=NOT_FOUND→ 虽然在 OpenClaw 中但 CLI 不可用，跳到**「通用提示」**。
为什么不能仅用
command -v openclaw：同一台机器可能同时安装了 openclaw 和 claude 等其他 AI 工具。仅检测 CLI 是否存在无法区分"装了 openclaw"和"正在 openclaw 中运行"。OPENCLAW_SHELL是进程级的运行时标记，从根本上解决此问题。
步骤二：查询 wecom channel 的 botId 配置
openclaw config get channels.wecom.botId 2>&1- 如果命令返回了具体的 botId 值（非空、非报错），保存该值，跳到**「OpenClaw 场景 + 有 botId 提示」**。
- 如果返回
Config path not found、报错或为空，跳到**「通用提示」**。
异常容错
如果上述任何命令执行失败（如 exec 工具不可用、命令超时等），一律跳到**「通用提示」**。
OpenClaw 场景 + 有 botId 提示
当确认是 OpenClaw 环境且获取到了 botId 时，必须原样输出以下提示（不要修改、不要摘要），将 XXXX 替换为实际获取到的 botId 值：
若你是智能机器人创建者，可以点击这里授权当前机器人文档使用权限； 若你不是机器人创建者，可联系该机器人创建者，前往企业微信「工作台-智能机器人」找到对应机器人进行授权 若你已授权，可将对应机器人文档MCP的接入配置（StreamableHttp URL或者JSON Config）发送给我
输出提示后等待用户回复，后续流程与下方「通用提示」的后续流程一致（场景 A / B / C）。配置成功后不要停下来，立即回到「前置检查」的步骤 2 重新验证配置，验证通过后继续执行用户的原始请求。
通用提示
当非 OpenClaw 环境、无法判断环境、或 OpenClaw 环境但未配置 wecom channel / botId 时，必须原样输出以下提示文案（不要修改、不要摘要）：
机器人可通过MCP方式调用文档相关能力，当前暂未完成所需配置。请参考以下配置指引：
请前往「企业微信-工作台-智能机器人应用」，以API模式创建机器人（如已创建，可忽略该步骤）
授权该机器人「文档」使用权限。授权后，可自行选择StreamableHttp URL 或 JSON Config 进行配置。
输出提示后等待用户回复。用户可能：
场景 A：用户提供了 StreamableHttp URL
从用户消息中提取 URL，执行：
mcporter config add wecom-doc \
--type streamable-http \
--url "<用户提供的URL>"配置完成后不要停下来，立即回到「前置检查」的步骤 2 重新验证配置，验证通过后继续执行用户的原始请求。
场景 B：用户提供了 JSON 配置
如果用户提供了类似以下格式的 JSON：
{
"name": "wecom-doc",
"type": "streamable-http",
"url": "http://xxx"
}从 JSON 中提取 url 字段，执行：
mcporter config add wecom-doc \
--type streamable-http \
--url "<从JSON提取的url>"配置完成后不要停下来，立即回到「前置检查」的步骤 2 重新验证配置，验证通过后继续执行用户的原始请求。
场景 C：用户自行完成了配置
用户可能在管理后台或其他途径自行完成配置后告知已配置好，此时直接继续执行原来的操作。
配置检测：当用户输入的内容包含 URL（如
http://...）或 JSON（含"type": "streamable-http"），应判断用户意图是在提供 MCP server 配置信息，自动执行配置命令。
Daemon 未启动
如果返回 connection refused 或 daemon not running 错误，提示用户：
mcporter daemon start注意事项
- 所有调用通过
mcporter call wecom-doc.<tool>执行，不要直接调用企业微信 API create_doc返回的docid需要保存，后续操作依赖此 ID- 添加记录前必须先
smartsheet_get_fields获取字段元信息
© 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 2 other files (references) in skills/wecom-doc of LeoYeAI/openclaw-master-skills.
- SKILL.md
- _meta.json
- references/doc-api.md
Open the folder on GitHubat commit e5199b5
Compare with similar skills
Wecom Doc 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 |
|---|---|---|---|---|---|---|
| Wecom Doc 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 | 5 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 | |
| MemPalace Memory SearchMemPalace/mempalace | 59k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Crush Configurationcharmbracelet/crush | 29k | — | ~3.7k | Automated safety check: Pass | Custom licence |
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.
MemPalace Memory Search
MemPalace/mempalace
Mines project files and conversation exports into a local, searchable memory palace and recalls past work by semantic search through the mempalace CLI.
Crush Configuration
charmbracelet/crush
Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.
Context Mode Output Sandbox
mksglu/context-mode
Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.
More from LeoYeAI/openclaw-master-skills
All 1,235 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
Categories
Questions about Wecom Doc
What does Wecom Doc do?
文档与智能表格操作。当用户提到企业微信文档、创建文档、编辑文档、新建文档、写文档、智能表格时激活。支持文档创建/写入和智能表格的创建及子表/字段/记录写入。注意：所有文档创建和编辑请求都应使用此 skill，不要尝试用其他方式处理文档操作。. Wecom Doc is an agent skill from LeoYeAI/openclaw-master-skills.
When should I use Wecom Doc?
Wecom Doc fits situations like: agent Workflows work in your project.
How do I install Wecom Doc in Claude Code?
Run `npx skills add LeoYeAI/openclaw-master-skills --skill wecom-doc -a claude-code`. Or copy the skill folder (skills/wecom-doc in LeoYeAI/openclaw-master-skills) into .claude/skills/wecom-doc in your project. Claude Code loads it when a task matches its description.
How do I install Wecom Doc in Codex?
Run `npx skills add LeoYeAI/openclaw-master-skills --skill wecom-doc -a codex`. Or copy the skill folder (skills/wecom-doc in LeoYeAI/openclaw-master-skills) into .agents/skills/wecom-doc in your project. Codex loads it when a task matches its description.
Can I use Wecom Doc 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 wecom-doc -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wecom-doc, .gemini/skills/wecom-doc, .github/skills/wecom-doc and .opencode/skills/wecom-doc in your project.
What does Wecom Doc need to run?
Going by SKILL.md and its folder, Wecom Doc needs the command-line tools its instructions call (npm). Our summary lists: Node.js.
Does Wecom Doc access the network?
SKILL.md names 3 domains. In commands or code: doc.weixin.qq.com and baidu.com; the agent is likely to contact these when it follows the instructions. As links in the text: work.weixin.qq.com. This is read from the text; nothing was executed.
Is Wecom Doc 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 Wecom Doc use?
Wecom Doc 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 Wecom Doc use?
About 2.6k tokens (SKILL.md is roughly 11k 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 1.4k tokens, read only when the agent opens those files.
What are the alternatives to Wecom Doc?
Skills that share tags, products or a category with Wecom Doc: 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 MemPalace Memory Search (MemPalace/mempalace, 59k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Wecom Doc?
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,160 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.