Configure Channel
openclaw/openclaw
Configure and prove a chat channel with non-interactive one-liners; secrets only as SecretRefs.
Agent skill
Dingtalk Channel Rules
by DingTalk-Real-AI in DingTalk-Real-AI/dingtalk-openclaw-connector
“钉钉会话输出规则。在钉钉会话中始终生效。”
MITAuto-check passed
Install Dingtalk Channel Rules
$ npx skills add DingTalk-Real-AI/dingtalk-openclaw-connector --skill dingtalk-channel-rules -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install DingTalk-Real-AI/dingtalk-openclaw-connector dingtalk-channel-rules --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/DingTalk-Real-AI/dingtalk-openclaw-connector.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/dingtalk-channel-rules .claude/skills/dingtalk-channel-rules && 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 "dingtalk-channel-rules" agent skill from https://github.com/DingTalk-Real-AI/dingtalk-openclaw-connector/tree/main/skills/dingtalk-channel-rules into .claude/skills/dingtalk-channel-rules/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dingtalk-channel-rules", 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/DingTalk-Real-AI/dingtalk-openclaw-connector/tree/main/skills/dingtalk-channel-rulesType 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 DingTalk-Real-AI/dingtalk-openclaw-connector --skill dingtalk-channel-rules -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install DingTalk-Real-AI/dingtalk-openclaw-connector dingtalk-channel-rules --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DingTalk-Real-AI/dingtalk-openclaw-connector.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/dingtalk-channel-rules .agents/skills/dingtalk-channel-rules && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "dingtalk-channel-rules" agent skill from https://github.com/DingTalk-Real-AI/dingtalk-openclaw-connector/tree/main/skills/dingtalk-channel-rules into .agents/skills/dingtalk-channel-rules/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dingtalk-channel-rules", 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 DingTalk-Real-AI/dingtalk-openclaw-connector --skill dingtalk-channel-rules -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install DingTalk-Real-AI/dingtalk-openclaw-connector dingtalk-channel-rules --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DingTalk-Real-AI/dingtalk-openclaw-connector.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/dingtalk-channel-rules .cursor/skills/dingtalk-channel-rules && 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 "dingtalk-channel-rules" agent skill from https://github.com/DingTalk-Real-AI/dingtalk-openclaw-connector/tree/main/skills/dingtalk-channel-rules into .cursor/skills/dingtalk-channel-rules/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dingtalk-channel-rules", 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/DingTalk-Real-AI/dingtalk-openclaw-connector.git --path skills/dingtalk-channel-rules--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 DingTalk-Real-AI/dingtalk-openclaw-connector --skill dingtalk-channel-rules -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install DingTalk-Real-AI/dingtalk-openclaw-connector dingtalk-channel-rules --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DingTalk-Real-AI/dingtalk-openclaw-connector.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/dingtalk-channel-rules .gemini/skills/dingtalk-channel-rules && 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 "dingtalk-channel-rules" agent skill from https://github.com/DingTalk-Real-AI/dingtalk-openclaw-connector/tree/main/skills/dingtalk-channel-rules into .gemini/skills/dingtalk-channel-rules/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dingtalk-channel-rules", 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 DingTalk-Real-AI/dingtalk-openclaw-connector dingtalk-channel-rulesInstalls 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 DingTalk-Real-AI/dingtalk-openclaw-connector --skill dingtalk-channel-rules -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/DingTalk-Real-AI/dingtalk-openclaw-connector.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/dingtalk-channel-rules .github/skills/dingtalk-channel-rules && 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 "dingtalk-channel-rules" agent skill from https://github.com/DingTalk-Real-AI/dingtalk-openclaw-connector/tree/main/skills/dingtalk-channel-rules into .github/skills/dingtalk-channel-rules/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dingtalk-channel-rules", 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 DingTalk-Real-AI/dingtalk-openclaw-connector --skill dingtalk-channel-rules -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install DingTalk-Real-AI/dingtalk-openclaw-connector dingtalk-channel-rules --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DingTalk-Real-AI/dingtalk-openclaw-connector.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/dingtalk-channel-rules .opencode/skills/dingtalk-channel-rules && 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 "dingtalk-channel-rules" agent skill from https://github.com/DingTalk-Real-AI/dingtalk-openclaw-connector/tree/main/skills/dingtalk-channel-rules into .opencode/skills/dingtalk-channel-rules/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dingtalk-channel-rules", 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
dingtalk-channel-rules- GitHub stars
- 2.1k
- Token cost
- ~595 tokens
- SKILL.md length
- 177 words
- Files
- 1
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
- SKILL.md covers 写作风格, 消息格式, AI Card 使用约定 and 目标格式, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
About this skill
Dingtalk Channel Rules is a skill in DingTalk-Real-AI/dingtalk-openclaw-connector (2.1k stars). Its SKILL.md is about 595 tokens. Licence: MIT.
What it can do on your machine
Read from SKILL.md and the folder at commit 5fef12d. 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.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Dingtalk Channel Rules loads about 595 tokens when it runs. Until then it costs about 11 tokens; SKILL.md has 177 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 DingTalk-Real-AI/dingtalk-openclaw-connector at commit 5fef12d, republished under its MIT licence (© DingTalk-Real-AI). 177 words, ~595 tokens.
Download SKILL.mdSave it as
.claude/skills/dingtalk-channel-rules/SKILL.md (or your agent's skills folder).- name
- dingtalk-channel-rules
- description
- 钉钉会话输出规则。在钉钉会话中始终生效。
- alwaysActive
- true
钉钉会话输出规则
写作风格
- 简洁、对话式、低仪式感 — 像同事聊天，不像操作手册
- 简短回答优先用完整句子，不要每次都用列表
- 直奔主题，说完就停 — 不需要每次都加总结段落
消息格式
- 钉钉支持 Markdown 消息格式（标题、加粗、链接、代码块等）
- 单条消息长度限制 2000 字符，超长内容会自动分块发送
- 群聊中需要 @机器人 才会触发响应（除非配置了
requireMention: false）
AI Card 使用约定
- 流式响应通过 AI Card 实现，支持打字机效果
- 长内容优先使用 AI Card 展示，提供更好的阅读体验
- Card 内支持 Markdown 渲染
目标格式
- 回复当前会话：省略
target参数（自动推断） - 指定用户：
user:userId - 指定群聊：
group:conversationId
能力路由：Connector vs DWS
核心原则：Connector 只负责"消息通道"，所有钉钉业务操作一律通过
dwsCLI 实现。 当用户提到任何钉钉业务功能时，不要思考"connector 是否有这个能力"，直接走 dws。
Connector 自动处理的能力（无需你操心）
以下能力由 Connector 在底层自动完成，你不需要做任何额外操作：
- 消息收发：接收用户消息、回复当前会话、AI Card 流式响应
- 媒体处理：接收和发送图片/语音/视频/文件附件
- 会话管理：多轮对话上下文保持、会话隔离
通过 dws 实现的钉钉业务功能
当用户的请求涉及以下钉钉业务功能时，立即使用 dws 命令，不要犹豫：
| 用户意图关键词 | dws 产品 | 典型操作 |
|---|---|---|
| 文档、钉钉文档、在线文档 | dws doc | 创建、追加、搜索、列举钉钉文档 |
| 日程、日历、会议、会议室、忙闲 | dws calendar | 创建/查询日程、自动带钉钉会议链接、DING 提醒、忙闲查询 |
| 表格、多维表、AI表格、记录、数据表 | dws aitable | 创建表格、读写行数据、条件查询 |
| 待办、TODO、任务 | dws todo | 创建个人/群待办、查状态、设截止时间 |
| 日志、日报、周报 | dws report | 提交日报/周报、查历史日志 |
| 文件、云盘、上传、下载 | dws drive | 上传/下载文件到钉钉云盘 |
| DING、紧急消息、强提醒 | dws ding | 向用户/群发送强提醒 DING |
🔑 多机器人场景：bot 凭证隔离（重要）
当配置了多个钉钉机器人时，必须确保 dws 命令使用当前对话机器人的凭据，避免"串台"（用错误的机器人身份操作）。
当前 bot 的 clientId 获取方式：
每条用户消息的上下文中会自动包含 [DingTalk Bot Context] 标记，其中含有当前对话 bot 的 clientId。在执行 dws chat message send-by-bot 命令时，必须从该上下文中提取 clientId 并传给 --client-id 参数。
示例：
用户消息上下文中包含:
[DingTalk Bot Context] Current bot clientId: dingXXXXXXXX. ...
执行命令时注入:
dws chat message send-by-bot --client-id dingXXXXXXXX --robot-code <code> --users "userId" \
--title "通知" --text "消息内容" --format json⚠️ 如果不传
--client-id，dws 会使用默认登录的机器人凭据，可能导致消息从错误的机器人发出。 每次执行dws chat相关命令时都必须从上下文中获取并传入--client-id。
易混淆场景速查
| 场景 | 正确选择 | 错误选择 |
|---|---|---|
| 用户说"帮我创建个文档" | dws doc | |
| 用户说"查一下明天的日程" | dws calendar | |
| 用户说"帮我创建个待办" | dws todo | |
| 用户说"写个日报" | dws report | |
| 用户说"帮我操作表格数据" | dws aitable | |
| 用户说"DING 一下某某" | dws ding | |
| 用户只是在聊天/问问题 | 直接回复（connector 自动处理） |
© DingTalk-Real-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/dingtalk-channel-rules of DingTalk-Real-AI/dingtalk-openclaw-connector.
Open the folder on GitHubat commit 5fef12d
Compare with similar skills
Dingtalk Channel Rules 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 |
|---|---|---|---|---|---|---|
| Dingtalk Channel Rules this skillDingTalk-Real-AI/dingtalk-openclaw-connector | 2.1k | — | ~595 | Automated safety check: Pass | MIT | |
| Configure Channelopenclaw/openclaw | 392k | — | ~946 | Automated safety check: Pass | MIT | |
| Counterparty Channel Disciplineaffaan-m/ECC | 277k | — | ~2.3k | Automated safety check: Pass | MIT | |
| Channel Message Flowsopenclaw/openclaw | 392k | — | ~306 | Automated safety check: Pass | MIT | |
| Trellis Channelmindfold-ai/Trellis | 15k | 4 repos | ~1.2k | Automated safety check: Pass | AGPL-3.0 | |
| NanoClaw Channel Wiringnanocoai/nanoclaw | 31k | — | ~2.6k | Automated safety check: Notes | MIT |
Similar skills
Counterparty Channel Discipline
affaan-m/ECC
Per-channel strict prompts, mention gating, silent observation, and a communication autonomy policy for agents that sit in shared channels with external counterparties.
Channel Message Flows
openclaw/openclaw
A skill your agent uses when running QA Lab channel message flow evidence.
Trellis Channel
mindfold-ai/Trellis
Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.
NanoClaw Channel Wiring
nanocoai/nanoclaw
Connects messaging channels to NanoClaw agent groups, sets isolation and engagement defaults, and reports which channels are wired, unwired or not configured.
Lightning Channel Factories
sickn33/agentic-awesome-skills
Technical reference on Lightning Network channel factories, multi-party channels, LSP architectures, and Bitcoin Layer 2 scaling without soft forks.
Questions about Dingtalk Channel Rules
How do I install Dingtalk Channel Rules in Claude Code?
Run `npx skills add DingTalk-Real-AI/dingtalk-openclaw-connector --skill dingtalk-channel-rules -a claude-code`. Or copy the skill folder (skills/dingtalk-channel-rules in DingTalk-Real-AI/dingtalk-openclaw-connector) into .claude/skills/dingtalk-channel-rules in your project. Claude Code loads it when a task matches its description.
How do I install Dingtalk Channel Rules in Codex?
Run `npx skills add DingTalk-Real-AI/dingtalk-openclaw-connector --skill dingtalk-channel-rules -a codex`. Or copy the skill folder (skills/dingtalk-channel-rules in DingTalk-Real-AI/dingtalk-openclaw-connector) into .agents/skills/dingtalk-channel-rules in your project. Codex loads it when a task matches its description.
Can I use Dingtalk Channel Rules 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 DingTalk-Real-AI/dingtalk-openclaw-connector --skill dingtalk-channel-rules -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dingtalk-channel-rules, .gemini/skills/dingtalk-channel-rules, .github/skills/dingtalk-channel-rules and .opencode/skills/dingtalk-channel-rules in your project.
What does Dingtalk Channel Rules need to run?
SKILL.md names no scripts, command-line tools or credentials: Dingtalk Channel Rules is instructions for the agent only.
Does Dingtalk Channel Rules access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Dingtalk Channel Rules 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 Dingtalk Channel Rules use?
Dingtalk Channel Rules 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 Dingtalk Channel Rules use?
About 595 tokens (SKILL.md is roughly 2.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Dingtalk Channel Rules?
Skills that share tags, products or a category with Dingtalk Channel Rules: Configure Channel (openclaw/openclaw, 392k stars), Counterparty Channel Discipline (affaan-m/ECC, 277k stars), Channel Message Flows (openclaw/openclaw, 392k stars) and Trellis Channel (mindfold-ai/Trellis, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Dingtalk Channel Rules?
DingTalk-Real-AI (a GitHub organization) maintains it in DingTalk-Real-AI/dingtalk-openclaw-connector, which has 2,131 GitHub stars. The repository was last updated on September 26, 2026.
Source: DingTalk-Real-AI/dingtalk-openclaw-connector on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.