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 EthanYoQ/Skill-hub --skill feishu-automationgit clone --depth 1 https://github.com/EthanYoQ/Skill-hubWrote 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/ethanyoq/skill-hub/feishu-automation)<a href="https://agentmods.dev/skills/ethanyoq/skill-hub/feishu-automation"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/feishu-automation/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/ethanyoq/skill-hub/feishu-automation"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/feishu-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00062 | $0.00961 |
| Opus 5 | $0.00031 | $0.00481 |
| Sonnet 5 | $0.00012 | $0.00192 |
| Haiku 4.5 | $0.00006 | $0.00096 |
Grade B, and why
feishu-automation scanned grade B with 1 finding 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 12d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
3. 脚本会优先写入 `~/.codex/config.toml`，仅在 Codex 配置不存在时回退到 `~/.claude.json`。 How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
飞书自动化
这个 Skill 以飞书官方文档与官方仓库为准，不再把 Skill 自己当作事实源。
官方来源
- OpenAPI MCP 官方仓库: https://github.com/larksuite/lark-openapi-mcp
- MCP 概览: https://open.feishu.cn/document/uAjLw4CM/ukTMukTMukTM/mcp_integration/mcp_introduction
- 自建应用开发流程: https://open.feishu.cn/document/home/introduction-to-custom-app-development/self-built-application-development-process
- 官方配置指南: https://github.com/larksuite/lark-openapi-mcp/blob/main/docs/usage/configuration/configuration.md
- 官方 CLI 参考: https://github.com/larksuite/lark-openapi-mcp/blob/main/docs/reference/cli/cli.md
使用前提
- 当前会话必须已经加载
mcp__lark-mcp_*。 - 如果工具不存在，先运行：
node .agents/skills/feishu-automation/feishu-mcp-setup.js <app_id> <app_secret>
- 脚本会优先写入
~/.codex/config.toml，仅在 Codex 配置不存在时回退到~/.claude.json。 - 配置完成后必须重启 Codex，新 MCP server 才会生效。
官方 MCP 配置原则
- 使用官方包：
@larksuiteoapi/lark-mcp - 默认使用应用身份，不启用 OAuth
- 默认使用飞书中国区，不额外传
--domain - 工具命名固定为
camel
对应官方 MCP 命令形态为：
npx -y @larksuiteoapi/lark-mcp mcp \
-a <app_id> \
-s <app_secret> \
-t preset.light,preset.default,preset.im.default,preset.base.default,preset.base.batch,preset.doc.default,preset.task.default,preset.calendar.default,docx.v1.documentBlock.patch,docx.v1.documentBlockChildren.create,docx.v1.documentBlockChildren.batchDelete \
-c camel \
-l zh \
--token-mode tenant_access_token
如果后续必须访问用户私有资源，再执行官方登录命令：
npx -y @larksuiteoapi/lark-mcp login -a <app_id> -s <app_secret>
然后在 MCP 配置里追加：
--oauth --token-mode user_access_token
适合交给 MCP 的能力
- 消息发送与查询
- 群组创建、搜索、成员管理
- Base 创建、表结构与记录读写
- 文档查询、导入、权限设置
- 任务、日历等开放接口能力
不适合交给 MCP 的能力
以下动作属于飞书开放平台控制台，不应假设能由这个 Skill 自动完成：
- 事件订阅配置
- 权限开关勾选
- 机器人“仅接收被 @ 消息”等后场范围设置
- 发布新版本
另外，基于官方仓库当前说明，以下能力仍有限制：
- 文件上传/下载暂不支持
- 飞书云文档直接编辑暂不支持
因此，本项目的 PDF/DOCX 下载与解析继续保留在后端实现，不迁移到 MCP。
使用规则
- 用户要求“飞书自动化”时，优先确认
mcp__lark-mcp_*是否可用。 - 如果工具不可用，先补 MCP，再继续自动化，不要把 Skill 本身假装成 MCP。
- 若任务涉及开放平台后台发布或权限切换，明确说明这是控制台动作，再把 MCP 用于后续 OpenAPI 验证或数据同步。
- 对当前仓库，优先把 MCP 用在 Bot、群、Base、文档导入、消息发送等动作上。
What ships with it
1 file 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.
- 12d ago First seen · 92 lines · 62 tokens per session scan B 5e980803a362
feishu-automation is a skill published in the GitHub repository EthanYoQ/Skill-hub (9 stars, last pushed 5d ago), licensed MIT. It adds 62 tokens to every session and 961 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
gws-workflow-email-to-task
Google Workflow: Convert a Gmail message into a Google Tasks entry.
gws-workflow-standup-report
Google Workflow: Today's meetings + open tasks as a standup summary.
n8n-pto-pipeline
Create n8n workflow for daily task assignment from PTO engineer to foreman via Telegram bot with status reporting.
toolbox
Pre/post dev toolbox — named bundles of skills/agents loaded before development work and councils of experts invoked after. Run /toolbox or the toolbox.py CLI to list, activate, initialize, export, import, and validate toolboxes. Invoke at the start or end of a dev session, when setting up a new repo, or when sharing…
lark-workflow-standup-report
A workflow that combines calendar events with unfinished Lark tasks to produce a daily or weekly work summary.
update-scheduled-task
Modify scheduled task settings WITHOUT deleting. Can modify notifyonstart, notifyoncomplete, enabled. Common uses - (1) 'Turn off notification' = notify=false, (2) 'Pause task' = enabled=false, (3) 'Resume task' = enabled=true.