Menu
创建 lark-cli 的自定义 Skill。当用户需要把飞书 API 操作封装成可复用的 Skill（包装原子 API 或编排多步流程）时使用。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | lark-skill-maker |
| version | 1.0.0 |
| description | 创建 lark-cli 的自定义 Skill。当用户需要把飞书 API 操作封装成可复用的 Skill（包装原子 API 或编排多步流程）时使用。 |
| metadata | {"requires":{"bins":["lark-cli"]}} |
基于 lark-cli 创建新 Skill。Skill = 一份 SKILL.md，教 AI 用 CLI 命令完成任务。
lark-cli <service> <resource> <method> # 已注册 API
lark-cli <service> +<verb> # Shortcut（高级封装）
lark-cli api <METHOD> <path> [--data/--params] # 任意飞书 OpenAPI
lark-cli schema <service.resource.method> # 查参数定义
优先级：Shortcut > 已注册 API > api 裸调。
# 1. 查看已有的 API 资源和 Shortcut
lark-cli <service> --help
# 2. 查参数定义
lark-cli schema <service.resource.method>
# 3. 未注册的 API，用 api 直接调用
lark-cli api GET /open-apis/vc/v1/rooms --params '{"page_size":"50"}'
lark-cli api POST /open-apis/vc/v1/rooms/search --data '{"query":"5F"}'
如果以上命令无法覆盖需求（CLI 没有对应的已注册 API 或 Shortcut），使用 lark-openapi-explorer 从飞书官方文档库逐层挖掘原生 OpenAPI 接口，获取完整的方法、路径、参数和权限信息，再通过 lark-cli api 裸调完成任务。
通过以上流程确定需要哪些 API、参数和 scope。
文件放在 skills/lark-<name>/SKILL.md：
---
name: lark-<name>
version: 1.0.0
description: "<功能描述>。当用户需要<触发场景>时使用。"
metadata:
requires:
bins: ["lark-cli"]
---
# <标题>
> **前置条件：** 先阅读 [`../lark-shared/SKILL.md`](../lark-shared/SKILL.md)。
## 命令
\```bash
# 单步操作
lark-cli api POST /open-apis/xxx --data '{...}'
# 多步编排：说明步骤间数据传递
# Step 1: ...（记录返回的 xxx_id）
# Step 2: 使用 Step 1 的 xxx_id
\```
## 权限
| 操作 | 所需 scope |
|------|-----------|
| xxx | `scope:name` |
cli-skills/lark-shared/SKILL.md §Agent 代理发起认证 canonical 模板补：缺基础 scope 跑 --recommend，缺推荐之外的高敏感 scope 跑 --scope <name>，两者都通过 agent 自己 --no-wait --json + 后台 --device-code。文档里指向 canonical 模板，不要重复贴整条 lark-cli auth login 命令，也不要再教 --domain。--dry-run 预览Debug why a session/agent/daemon behaved incorrectly. Load when user mentions a session id (ses_/mvs_*), wants logs, root-cause analysis, or asks about stuck runs, retries, permissions, or recovery. Keywords: 排查, 调试, 卡住, 为什么, log, debug, inspect, retry, recovery.
Coordinate a Mavis multi-agent team plan. Use only when the user explicitly invokes /mavis-team or /team, or 100% unambiguously asks to use an agent team / multi-agent team. Do not infer team use from complexity, deep research, long-running work, parallelism, specialist value, or verification risk.
Nightly batch skill maintenance. Reads pending signals and proposals, plans which skills to create/refine via team engine. Managed by daemon's internal scheduler — not visible to agents or users. Do not load this skill manually -- it is designed for automated nightly runs.
Create one agent on disk. Load when you need to add a new role to the team — typically called by `mavis-team` (when planning analysis says no existing agent fits and the user has consented), by `init` (when bootstrapping `.harness/reins/`), or directly when the user says 'add an agent for X' / 'new an agent' / '加一个 agent' / '建一个 rein'. Two output paths: `~/.mavis/agents/<name>/` (default — cross-project helper) or `<repo>/.harness/reins/<name>/` (when caller specifies project target — coding project rein). Do NOT load to decide WHETHER to create (that lives in `mavis-team` router) or to create a skill (use `skill-creator`).
Coordinate a Mavis multi-agent team plan. Use only when the user explicitly unambiguously asks to use an agent team
Unified DOCX skill — create, template-apply, edit/fill, read, repair, and compare Word documents. Use for formal Word deliverables and DOCX diagnosis. Not for PDF/PPT or casual plain-text drafting.